[llvm] [llvm-mca][FeatureRequest] Itimeline graph, note source of delay for each instruction (PR #136423)

via llvm-commits llvm-commits at lists.llvm.org
Mon Apr 21 04:54:31 PDT 2025


https://github.com/sommersun updated https://github.com/llvm/llvm-project/pull/136423

>From a5203ee1275c1b0ed5f74a7034a58aa2d11433fb Mon Sep 17 00:00:00 2001
From: sxx <948074686 at qq.com>
Date: Sat, 19 Apr 2025 18:54:34 +0800
Subject: [PATCH] [llvm-mca][FeatureRequest] Itimeline graph, note source of
 delay for each instruction #123756

---
 .../llvm-mca/AArch64/Cortex/A510-writeback.s  |   91 +
 .../llvm-mca/AArch64/Cortex/A53-carry-over.s  |    1 +
 .../llvm-mca/AArch64/Cortex/A53-writeback.s   |   91 +
 .../AArch64/Cortex/A55-add-sequence.s         |    1 +
 .../llvm-mca/AArch64/Cortex/A55-all-views.s   |    1 +
 .../AArch64/Cortex/A55-in-order-retire.s      |    1 +
 .../AArch64/Cortex/A55-load-readadv.s         |    1 +
 .../AArch64/Cortex/A55-load-store-alias.s     |    1 +
 .../AArch64/Cortex/A55-load-store-noalias.s   |    1 +
 .../AArch64/Cortex/A55-out-of-order-retire.s  |    1 +
 .../AArch64/Cortex/A55-store-readadv.s        |    1 +
 .../llvm-mca/AArch64/Cortex/A55-writeback.s   |   91 +
 .../llvm-mca/AArch64/Cortex/A57-writeback.s   |  715 +++--
 .../llvm-mca/AArch64/Cortex/direct-branch.s   |    1 +
 .../llvm-mca/AArch64/Cortex/forwarding-A57.s  | 2746 +++++++++++++++--
 .../AArch64/HiSilicon/tsv110-forwarding.s     |   10 +-
 .../AArch64/HiSilicon/tsv110-writeback.s      |  575 ++--
 .../llvm-mca/AArch64/Neoverse/N1-writeback.s  | 1333 ++++----
 .../llvm-mca/AArch64/Neoverse/N2-writeback.s  | 1557 +++++-----
 .../llvm-mca/AArch64/Neoverse/N3-writeback.s  | 1541 ++++-----
 .../AArch64/Neoverse/V1-clear-upper-regs.s    |  102 +-
 .../llvm-mca/AArch64/Neoverse/V1-forwarding.s |  517 ++--
 .../llvm-mca/AArch64/Neoverse/V1-writeback.s  | 1621 +++++-----
 .../AArch64/Neoverse/V1-zero-dependency.s     |    9 +-
 .../AArch64/Neoverse/V2-clear-upper-regs.s    |   96 +-
 .../llvm-mca/AArch64/Neoverse/V2-forwarding.s |  669 ++--
 .../llvm-mca/AArch64/Neoverse/V2-writeback.s  |  757 +++--
 .../test/tools/llvm-mca/AMDGPU/carried-over.s |    1 +
 .../llvm-mca/AMDGPU/gfx10-add-sequence.s      |    1 +
 .../test/tools/llvm-mca/AMDGPU/gfx10-double.s |    1 +
 llvm/test/tools/llvm-mca/AMDGPU/gfx10-trans.s |    1 +
 .../test/tools/llvm-mca/AMDGPU/gfx11-double.s |    1 +
 .../AMDGPU/gfx12-pseudo-scalar-trans.s        |    1 +
 .../tools/llvm-mca/AMDGPU/gfx9-retireooo.s    |    1 +
 .../tools/llvm-mca/ARM/cortex-a57-carryover.s |   27 +-
 llvm/test/tools/llvm-mca/ARM/m55-storefwd.s   |    1 +
 .../llvm-mca/ARM/m7-negative-readadvance.s    |    1 +
 llvm/test/tools/llvm-mca/ARM/memcpy-ldm-stm.s |    7 +-
 .../tools/llvm-mca/ARM/vld1-index-update.s    |   19 +-
 llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s   |    9 +-
 .../tools/llvm-mca/RISCV/SiFive7/div-fdiv.s   |    1 +
 .../llvm-mca/RISCV/SiFive7/gpr-bypass-c.s     |    1 +
 .../tools/llvm-mca/RISCV/SiFive7/gpr-bypass.s |    1 +
 llvm/test/tools/llvm-mca/RISCV/SiFive7/jump.s |    1 +
 .../SiFiveX280/different-lmul-instruments.s   |    1 +
 .../SiFiveX280/different-sew-instruments.s    |    1 +
 .../llvm-mca/RISCV/SiFiveX280/disable-im.s    |    1 +
 .../SiFiveX280/lmul-instrument-at-start.s     |    1 +
 .../SiFiveX280/lmul-instrument-in-middle.s    |    1 +
 .../SiFiveX280/lmul-instrument-in-region.s    |    1 +
 .../lmul-instrument-straddles-region.s        |    1 +
 .../multiple-same-lmul-instruments.s          |    1 +
 .../multiple-same-sew-instruments.s           |    1 +
 .../SiFiveX280/needs-sew-but-only-lmul.s      |    1 +
 .../RISCV/SiFiveX280/no-vsetvli-to-start.s    |    1 +
 .../SiFiveX280/sew-instrument-at-start.s      |    1 +
 .../SiFiveX280/sew-instrument-in-middle.s     |    3 +-
 .../SiFiveX280/sew-instrument-in-region.s     |    1 +
 .../sew-instrument-straddles-region.s         |    1 +
 .../SiFiveX280/vsetivli-lmul-instrument.s     |    1 +
 .../SiFiveX280/vsetivli-lmul-sew-instrument.s |    1 +
 .../SiFiveX280/vsetvli-lmul-instrument.s      |    1 +
 .../SiFiveX280/vsetvli-lmul-sew-instrument.s  |    1 +
 .../llvm-mca/RISCV/SyntacoreSCR/SCR4_5-FPU.s  |    1 +
 .../llvm-mca/RISCV/XiangShan/gpr-bypass.s     |  179 +-
 .../llvm-mca/RISCV/XiangShan/load-to-alu.s    |    3 +-
 llvm/test/tools/llvm-mca/SystemZ/stm-lm.s     |    9 +-
 .../X86/AlderlakeP/independent-load-stores.s  |   11 +-
 .../llvm-mca/X86/AlderlakeP/zero-idioms.s     |  145 +-
 .../tools/llvm-mca/X86/Atom/zero-idioms.s     |    1 +
 .../X86/Barcelona/clear-super-register-1.s    |   13 +-
 .../X86/Barcelona/clear-super-register-2.s    |   22 +-
 .../X86/Barcelona/dependency-breaking-cmp.s   |   11 +-
 .../Barcelona/dependency-breaking-pcmpeq.s    |   37 +-
 .../Barcelona/dependency-breaking-pcmpgt.s    |   17 +-
 .../X86/Barcelona/dependency-breaking-sbb-1.s |   11 +-
 .../X86/Barcelona/dependency-breaking-sbb-2.s |   11 +-
 .../X86/Barcelona/int-to-fpu-forwarding-3.s   |   13 +-
 .../X86/Barcelona/load-store-throughput.s     |   18 +-
 .../llvm-mca/X86/Barcelona/load-throughput.s  |    6 +
 .../tools/llvm-mca/X86/Barcelona/one-idioms.s |    9 +-
 .../X86/Barcelona/partial-reg-update-2.s      |    3 +-
 .../X86/Barcelona/partial-reg-update-3.s      |    9 +-
 .../X86/Barcelona/partial-reg-update-4.s      |   11 +-
 .../X86/Barcelona/partial-reg-update-5.s      |    1 +
 .../X86/Barcelona/partial-reg-update-6.s      |    5 +-
 .../X86/Barcelona/partial-reg-update-7.s      |   47 +-
 .../X86/Barcelona/partial-reg-update.s        |    5 +-
 .../llvm-mca/X86/Barcelona/read-advance-1.s   |    1 +
 .../llvm-mca/X86/Barcelona/read-advance-2.s   |    1 +
 .../llvm-mca/X86/Barcelona/read-advance-3.s   |    1 +
 .../X86/Barcelona/reg-move-elimination-1.s    |    7 +-
 .../X86/Barcelona/reg-move-elimination-2.s    |   37 +-
 .../X86/Barcelona/reg-move-elimination-3.s    |   31 +-
 .../X86/Barcelona/reg-move-elimination-4.s    |   17 +-
 .../X86/Barcelona/reg-move-elimination-5.s    |   17 +-
 .../X86/Barcelona/reg-move-elimination-6.s    |   21 +-
 .../llvm-mca/X86/Barcelona/store-throughput.s |   30 +-
 .../llvm-mca/X86/Barcelona/zero-idioms.s      |   33 +-
 .../tools/llvm-mca/X86/BdVer2/add-sequence.s  |   55 +-
 .../X86/BdVer2/clear-super-register-1.s       |   13 +-
 .../X86/BdVer2/clear-super-register-2.s       |   55 +-
 .../X86/BdVer2/clear-super-register-3.s       |   14 +-
 .../X86/BdVer2/dependency-breaking-cmp.s      |    7 +-
 .../X86/BdVer2/dependency-breaking-pcmpeq.s   |    7 +-
 .../X86/BdVer2/dependency-breaking-pcmpgt.s   |    1 +
 .../X86/BdVer2/dependency-breaking-sbb-1.s    |   11 +-
 .../X86/BdVer2/dependency-breaking-sbb-2.s    |   13 +-
 .../X86/BdVer2/dependent-pmuld-paddd.s        |   59 +-
 .../tools/llvm-mca/X86/BdVer2/dot-product.s   |   13 +-
 .../X86/BdVer2/hadd-read-after-ld-1.s         |    1 +
 .../X86/BdVer2/hadd-read-after-ld-2.s         |    1 +
 .../X86/BdVer2/int-to-fpu-forwarding-3.s      |   13 +-
 .../llvm-mca/X86/BdVer2/load-store-alias.s    |   15 +-
 .../X86/BdVer2/load-store-throughput.s        |   18 +-
 .../llvm-mca/X86/BdVer2/load-throughput.s     |    7 +
 .../llvm-mca/X86/BdVer2/memcpy-like-test.s    |    9 +-
 .../tools/llvm-mca/X86/BdVer2/one-idioms.s    |    7 +-
 .../X86/BdVer2/partial-reg-update-2.s         |    5 +-
 .../X86/BdVer2/partial-reg-update-3.s         |   17 +-
 .../X86/BdVer2/partial-reg-update-4.s         |   17 +-
 .../X86/BdVer2/partial-reg-update-5.s         |    5 +-
 .../X86/BdVer2/partial-reg-update-6.s         |   13 +-
 .../llvm-mca/X86/BdVer2/partial-reg-update.s  |    5 +-
 .../tools/llvm-mca/X86/BdVer2/pipes-fpu.s     |    1 +
 llvm/test/tools/llvm-mca/X86/BdVer2/pr37790.s |    1 +
 llvm/test/tools/llvm-mca/X86/BdVer2/rank.s    |   43 +-
 .../llvm-mca/X86/BdVer2/read-advance-1.s      |    1 +
 .../llvm-mca/X86/BdVer2/read-advance-2.s      |    1 +
 .../llvm-mca/X86/BdVer2/read-advance-3.s      |    1 +
 .../X86/BdVer2/reg-move-elimination-1.s       |    7 +-
 .../X86/BdVer2/reg-move-elimination-2.s       |   29 +-
 .../X86/BdVer2/reg-move-elimination-3.s       |   31 +-
 .../X86/BdVer2/reg-move-elimination-4.s       |   19 +-
 .../X86/BdVer2/reg-move-elimination-5.s       |   19 +-
 .../llvm-mca/X86/BdVer2/register-files-1.s    |   19 +-
 .../llvm-mca/X86/BdVer2/register-files-2.s    |   19 +-
 .../llvm-mca/X86/BdVer2/register-files-3.s    |    1 +
 .../llvm-mca/X86/BdVer2/register-files-4.s    |    5 +-
 .../llvm-mca/X86/BdVer2/register-files-5.s    |   35 +-
 .../llvm-mca/X86/BdVer2/store-throughput.s    |   33 +-
 .../X86/BdVer2/vbroadcast-operand-latency.s   |    1 +
 .../X86/BdVer2/vec-logic-read-after-ld-1.s    |    1 +
 .../X86/BdVer2/vec-logic-read-after-ld-2.s    |    1 +
 .../X86/BdVer2/xop-super-registers-1.s        |   19 +-
 .../X86/BdVer2/xop-super-registers-2.s        |   19 +-
 .../llvm-mca/X86/BdVer2/zero-idioms-avx-256.s |   27 +-
 .../tools/llvm-mca/X86/BdVer2/zero-idioms.s   |    1 +
 .../llvm-mca/X86/Broadwell/zero-idioms.s      |   27 +-
 .../X86/BtVer2/adc-sequence-readadvance.s     |    7 +-
 .../tools/llvm-mca/X86/BtVer2/add-sequence.s  |   45 +-
 .../llvm-mca/X86/BtVer2/bottleneck-hints-1.s  |    7 +-
 .../llvm-mca/X86/BtVer2/bottleneck-hints-2.s  |    1 +
 .../llvm-mca/X86/BtVer2/bottleneck-hints-3.s  |   15 +-
 .../X86/BtVer2/clear-super-register-1.s       |    7 +-
 .../X86/BtVer2/clear-super-register-2.s       |   15 +-
 .../X86/BtVer2/cmpxchg-read-advance.s         |   16 +-
 .../X86/BtVer2/dependency-breaking-cmp.s      |    7 +-
 .../X86/BtVer2/dependency-breaking-pcmpeq.s   |    1 +
 .../X86/BtVer2/dependency-breaking-pcmpgt.s   |    1 +
 .../X86/BtVer2/dependency-breaking-sbb-1.s    |   11 +-
 .../X86/BtVer2/dependency-breaking-sbb-2.s    |    9 +-
 .../X86/BtVer2/dependent-pmuld-paddd.s        |   59 +-
 .../tools/llvm-mca/X86/BtVer2/dot-product.s   |   13 +-
 .../X86/BtVer2/hadd-read-after-ld-1.s         |    1 +
 .../X86/BtVer2/hadd-read-after-ld-2.s         |    1 +
 .../X86/BtVer2/independent-load-stores.s      |   33 +-
 .../X86/BtVer2/int-to-fpu-forwarding-3.s      |   13 +-
 .../llvm-mca/X86/BtVer2/load-store-alias.s    |   15 +-
 .../llvm-mca/X86/BtVer2/memcpy-like-test.s    |    9 +-
 .../X86/BtVer2/negative-read-advance.s        |   11 +-
 .../tools/llvm-mca/X86/BtVer2/one-idioms.s    |    1 +
 .../X86/BtVer2/partial-reg-update-2.s         |    5 +-
 .../X86/BtVer2/partial-reg-update-3.s         |   17 +-
 .../X86/BtVer2/partial-reg-update-4.s         |   17 +-
 .../X86/BtVer2/partial-reg-update-5.s         |    5 +-
 .../X86/BtVer2/partial-reg-update-6.s         |   13 +-
 .../X86/BtVer2/partial-reg-update-7.s         |   45 +-
 .../llvm-mca/X86/BtVer2/partial-reg-update.s  |    5 +-
 .../tools/llvm-mca/X86/BtVer2/pipes-fpu.s     |    1 +
 llvm/test/tools/llvm-mca/X86/BtVer2/pr37790.s |    1 +
 llvm/test/tools/llvm-mca/X86/BtVer2/rank.s    |   33 +-
 .../llvm-mca/X86/BtVer2/read-advance-1.s      |    1 +
 .../llvm-mca/X86/BtVer2/read-advance-2.s      |    1 +
 .../llvm-mca/X86/BtVer2/read-advance-3.s      |    1 +
 .../X86/BtVer2/reg-move-elimination-1.s       |    1 +
 .../X86/BtVer2/reg-move-elimination-2.s       |    1 +
 .../X86/BtVer2/reg-move-elimination-3.s       |    1 +
 .../X86/BtVer2/reg-move-elimination-4.s       |    1 +
 .../X86/BtVer2/reg-move-elimination-5.s       |    1 +
 .../X86/BtVer2/reg-move-elimination-6.s       |   13 +-
 .../llvm-mca/X86/BtVer2/register-files-1.s    |   19 +-
 .../llvm-mca/X86/BtVer2/register-files-2.s    |   19 +-
 .../llvm-mca/X86/BtVer2/register-files-3.s    |    1 +
 .../llvm-mca/X86/BtVer2/register-files-4.s    |    5 +-
 .../llvm-mca/X86/BtVer2/register-files-5.s    |   23 +-
 .../X86/BtVer2/rmw-adc-sequence-readadvance.s |    1 +
 .../X86/BtVer2/rmw-add-sequence-readadvance.s |    1 +
 .../llvm-mca/X86/BtVer2/stmxcsr-ldmxcsr.s     |   17 +-
 .../X86/BtVer2/unsupported-instruction.s      |  115 +-
 .../X86/BtVer2/vbroadcast-operand-latency.s   |    7 +-
 .../X86/BtVer2/vec-logic-read-after-ld-1.s    |    1 +
 .../X86/BtVer2/vec-logic-read-after-ld-2.s    |    1 +
 llvm/test/tools/llvm-mca/X86/BtVer2/xadd.s    |   38 +-
 llvm/test/tools/llvm-mca/X86/BtVer2/xchg.s    |   19 +-
 .../llvm-mca/X86/BtVer2/zero-idioms-avx-256.s |    5 +
 .../tools/llvm-mca/X86/BtVer2/zero-idioms.s   |    1 +
 .../X86/Generic/avx512-super-registers-1.s    |   19 +-
 .../X86/Generic/avx512-super-registers-2.s    |   19 +-
 .../X86/Generic/avx512-super-registers-3.s    |   19 +-
 .../X86/Generic/xop-super-registers-1.s       |   19 +-
 .../X86/Generic/xop-super-registers-2.s       |   17 +-
 .../X86/Haswell/adcx-adox-read-advance.s      |    6 +-
 .../tools/llvm-mca/X86/Haswell/cmpxchg16b.s   |    5 +-
 .../X86/Haswell/independent-load-stores.s     |   19 +-
 .../X86/Haswell/mulx-hi-read-advance.s        |    6 +-
 .../llvm-mca/X86/Haswell/mulx-lo-reg-use.s    |    6 +-
 .../llvm-mca/X86/Haswell/mulx-read-advance.s  |    6 +-
 .../llvm-mca/X86/Haswell/mulx-same-regs.s     |    6 +-
 .../llvm-mca/X86/Haswell/stmxcsr-ldmxcsr.s    |   17 +-
 .../tools/llvm-mca/X86/Haswell/zero-idioms.s  |   27 +-
 .../IceLakeServer/independent-load-stores.s   |   19 +-
 .../llvm-mca/X86/IceLakeServer/zero-idioms.s  |   49 +-
 .../test/tools/llvm-mca/X86/SLM/zero-idioms.s |   45 +-
 .../llvm-mca/X86/SandyBridge/zero-idioms.s    |   33 +-
 .../SapphireRapids/independent-load-stores.s  |   11 +-
 .../llvm-mca/X86/SapphireRapids/zero-idioms.s |  251 +-
 .../SkylakeClient/independent-load-stores.s   |   33 +-
 .../X86/SkylakeClient/mulx-hi-read-advance.s  |    6 +-
 .../X86/SkylakeClient/mulx-lo-reg-use.s       |    6 +-
 .../X86/SkylakeClient/mulx-same-regs.s        |    6 +-
 .../llvm-mca/X86/SkylakeClient/zero-idioms.s  |   29 +-
 .../SkylakeServer/independent-load-stores.s   |   33 +-
 .../llvm-mca/X86/SkylakeServer/zero-idioms.s  |   49 +-
 .../X86/Znver1/partial-reg-update-2.s         |    5 +-
 .../X86/Znver1/partial-reg-update-3.s         |   35 +-
 .../X86/Znver1/partial-reg-update-4.s         |   41 +-
 .../X86/Znver1/partial-reg-update-5.s         |   15 +-
 .../X86/Znver1/partial-reg-update-6.s         |   19 +-
 .../X86/Znver1/partial-reg-update-7.s         |    5 +-
 .../llvm-mca/X86/Znver1/partial-reg-update.s  |    5 +-
 .../tools/llvm-mca/X86/Znver1/zero-idioms.s   |    1 +
 .../X86/Znver2/adcx-adox-read-advance.s       |    6 +-
 .../X86/Znver2/mulx-hi-read-advance.s         |    6 +-
 .../llvm-mca/X86/Znver2/mulx-read-advance.s   |    6 +-
 .../X86/Znver2/partial-reg-update-2.s         |    5 +-
 .../X86/Znver2/partial-reg-update-3.s         |   35 +-
 .../X86/Znver2/partial-reg-update-4.s         |   41 +-
 .../X86/Znver2/partial-reg-update-5.s         |   15 +-
 .../X86/Znver2/partial-reg-update-6.s         |   19 +-
 .../X86/Znver2/partial-reg-update-7.s         |    5 +-
 .../llvm-mca/X86/Znver2/partial-reg-update.s  |    5 +-
 .../tools/llvm-mca/X86/Znver2/zero-idioms.s   |    1 +
 .../X86/Znver3/dependency-breaking-gpr.s      |   42 +-
 .../X86/Znver3/mulx-hi-read-advance.s         |    6 +-
 .../llvm-mca/X86/Znver3/mulx-lo-reg-use.s     |    6 +-
 .../llvm-mca/X86/Znver3/mulx-read-advance.s   |    6 +-
 .../llvm-mca/X86/Znver3/mulx-same-regs.s      |    6 +-
 .../llvm-mca/X86/Znver3/one-idioms-avx-xmm.s  |   20 +-
 .../llvm-mca/X86/Znver3/one-idioms-avx-ymm.s  |   20 +-
 .../llvm-mca/X86/Znver3/one-idioms-mmx.s      |   15 +-
 .../llvm-mca/X86/Znver3/one-idioms-sse-xmm.s  |   20 +-
 .../X86/Znver3/partial-reg-update-2.s         |    5 +-
 .../X86/Znver3/partial-reg-update-3.s         |   35 +-
 .../X86/Znver3/partial-reg-update-4.s         |   41 +-
 .../X86/Znver3/partial-reg-update-5.s         |   15 +-
 .../X86/Znver3/partial-reg-update-6.s         |   21 +-
 .../X86/Znver3/partial-reg-update-7.s         |    5 +-
 .../llvm-mca/X86/Znver3/partial-reg-update.s  |    5 +-
 .../X86/Znver3/reg-move-elimination-avx-xmm.s |    6 +
 .../X86/Znver3/reg-move-elimination-avx-ymm.s |    6 +
 .../X86/Znver3/reg-move-elimination-gpr.s     |    4 +
 .../X86/Znver3/reg-move-elimination-mmx.s     |  153 +-
 .../X86/Znver3/reg-move-elimination-sse-xmm.s |    6 +
 .../X86/Znver3/reg-move-elimination-x87.s     |    1 +
 .../llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s |   34 +-
 .../llvm-mca/X86/Znver3/zero-idioms-avx-ymm.s |   48 +-
 .../llvm-mca/X86/Znver3/zero-idioms-gpr.s     |    4 +
 .../llvm-mca/X86/Znver3/zero-idioms-sse-xmm.s |   90 +-
 .../X86/Znver4/independent-load-stores.s      |   33 +-
 .../partially-overlapping-group-resources.s   |    1 +
 .../tools/llvm-mca/X86/Znver4/zero-idioms.s   |   11 +-
 .../tools/llvm-mca/X86/bextr-read-after-ld.s  |    1 +
 .../tools/llvm-mca/X86/bzhi-read-after-ld.s   |    1 +
 .../tools/llvm-mca/X86/fma3-read-after-ld-1.s |    1 +
 .../tools/llvm-mca/X86/fma3-read-after-ld-2.s |    1 +
 .../tools/llvm-mca/X86/option-all-views-1.s   |   19 +-
 .../tools/llvm-mca/X86/option-all-views-2.s   |   19 +-
 .../tools/llvm-mca/X86/option-no-stats-1.s    |   19 +-
 .../test/tools/llvm-mca/X86/read-after-ld-1.s |   23 +-
 .../test/tools/llvm-mca/X86/read-after-ld-2.s |   59 +-
 .../test/tools/llvm-mca/X86/read-after-ld-3.s |    1 +
 .../tools/llvm-mca/X86/sqrt-rsqrt-rcp-memop.s |   68 +-
 .../X86/variable-blend-read-after-ld-1.s      |    9 +
 .../X86/variable-blend-read-after-ld-2.s      |    9 +
 llvm/tools/llvm-mca/Views/TimelineView.cpp    |   19 +-
 llvm/tools/llvm-mca/Views/TimelineView.h      |    2 +
 297 files changed, 10262 insertions(+), 6582 deletions(-)

diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A510-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A510-writeback.s
index 94439acafe370..2a082c5c95d2e 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A510-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A510-writeback.s
@@ -1171,6 +1171,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -1217,6 +1218,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1263,6 +1265,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -1309,6 +1312,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1355,6 +1359,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1401,6 +1406,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1447,6 +1453,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1493,6 +1500,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1539,6 +1547,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1585,6 +1594,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1631,6 +1641,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1677,6 +1688,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1723,6 +1735,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
@@ -1769,6 +1782,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -1815,6 +1829,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -1861,6 +1876,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -1907,6 +1923,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -1953,6 +1970,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -1999,6 +2017,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2045,6 +2064,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
@@ -2091,6 +2111,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -2137,6 +2158,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -2183,6 +2205,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2229,6 +2252,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2275,6 +2299,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2321,6 +2346,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2367,6 +2393,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
@@ -2413,6 +2440,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2459,6 +2487,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2505,6 +2534,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -2551,6 +2581,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2597,6 +2628,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2643,6 +2675,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2689,6 +2722,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2735,6 +2769,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2781,6 +2816,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
@@ -2827,6 +2863,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2873,6 +2910,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2919,6 +2957,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2965,6 +3004,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3011,6 +3051,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3057,6 +3098,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3103,6 +3145,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3149,6 +3192,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -3195,6 +3239,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -3241,6 +3286,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -3287,6 +3333,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -3333,6 +3380,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -3379,6 +3427,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -3425,6 +3474,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -3471,6 +3521,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -3517,6 +3568,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
@@ -3563,6 +3615,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3609,6 +3662,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3655,6 +3709,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3701,6 +3756,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3747,6 +3803,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3793,6 +3850,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3839,6 +3897,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3885,6 +3944,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3931,6 +3991,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3977,6 +4038,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 18.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4023,6 +4085,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4069,6 +4132,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4115,6 +4179,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 11.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -4161,6 +4226,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -4207,6 +4273,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
@@ -4253,6 +4320,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4299,6 +4367,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4345,6 +4414,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4391,6 +4461,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4437,6 +4508,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4483,6 +4555,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -4521,6 +4594,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4567,6 +4641,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4613,6 +4688,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4659,6 +4735,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4705,6 +4782,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4751,6 +4829,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4797,6 +4876,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4843,6 +4923,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4889,6 +4970,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4935,6 +5017,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -4977,6 +5060,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012
 
 # CHECK:      [0,0]     DE.   stp	s1, s2, [x27], #248
@@ -5010,6 +5094,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DE   .   stp	q1, q2, [x27], #992
@@ -5055,6 +5140,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DE   .   stp	x1, x2, [x27], #496
@@ -5100,6 +5186,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DE   .   str	s1, [x27], #254
@@ -5145,6 +5232,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DE   .   str	s1, [x27, #254]!
@@ -5190,6 +5278,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DE   .   str	w1, [x27, #254]!
@@ -5235,6 +5324,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01
 
 # CHECK:      [0,0]     DE   strh	w1, [x27, #254]!
@@ -5264,6 +5354,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeE .   ldr	x1, [x27], #254
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A53-carry-over.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A53-carry-over.s
index a5715b9652109..44abfbfdbf3d0 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A53-carry-over.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A53-carry-over.s
@@ -58,6 +58,7 @@ add  w19, w20, w21
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -     add	w19, w20, w21
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeE. .   ldp	w3, w5, [x10], #4
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A53-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A53-writeback.s
index ed5b0869e53de..9985e2e2b76f3 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A53-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A53-writeback.s
@@ -1171,6 +1171,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1217,6 +1218,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1263,6 +1265,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1309,6 +1312,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -1355,6 +1359,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -1401,6 +1406,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -1447,6 +1453,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 13.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
@@ -1493,6 +1500,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 15.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1539,6 +1547,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 15.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1585,6 +1594,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 17.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1631,6 +1641,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1677,6 +1688,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1723,6 +1735,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 17.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1769,6 +1782,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1815,6 +1829,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1861,6 +1876,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1907,6 +1923,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1953,6 +1970,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1999,6 +2017,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2045,6 +2064,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 18.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2091,6 +2111,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2137,6 +2158,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -2183,6 +2205,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2229,6 +2252,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2275,6 +2299,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2321,6 +2346,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2367,6 +2393,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -2413,6 +2440,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2459,6 +2487,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 19.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2505,6 +2534,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2551,6 +2581,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2597,6 +2628,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2643,6 +2675,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2689,6 +2722,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2735,6 +2769,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2781,6 +2816,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 21.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2827,6 +2863,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 24.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2873,6 +2910,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 25.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0
 
@@ -2919,6 +2957,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2965,6 +3004,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3011,6 +3051,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3057,6 +3098,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3103,6 +3145,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3149,6 +3192,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -3195,6 +3239,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3241,6 +3286,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3287,6 +3333,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3333,6 +3380,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3379,6 +3427,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3425,6 +3474,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3471,6 +3521,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3517,6 +3568,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3563,6 +3615,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3609,6 +3662,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3655,6 +3709,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3701,6 +3756,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3747,6 +3803,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3793,6 +3850,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3839,6 +3897,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3885,6 +3944,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3931,6 +3991,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3977,6 +4038,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4023,6 +4085,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4069,6 +4132,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4115,6 +4179,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -4161,6 +4226,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -4207,6 +4273,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
@@ -4253,6 +4320,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -4299,6 +4367,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -4345,6 +4414,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -4391,6 +4461,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -4437,6 +4508,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -4483,6 +4555,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -4521,6 +4594,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -4567,6 +4641,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 15.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -4613,6 +4688,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 11.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
@@ -4659,6 +4735,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4705,6 +4782,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 11.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
@@ -4751,6 +4829,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 15.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -4797,6 +4876,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -4843,6 +4923,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -4889,6 +4970,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4935,6 +5017,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -4977,6 +5060,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeE.  .   stp	s1, s2, [x27], #248
@@ -5010,6 +5094,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -5056,6 +5141,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -5102,6 +5188,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -5148,6 +5235,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -5194,6 +5282,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -5240,6 +5329,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeeeE   strh	w1, [x27, #254]!
@@ -5269,6 +5359,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeE.  .   ldr	x1, [x27], #254
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-add-sequence.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-add-sequence.s
index dbcb3c53b22f0..fac1087c406c3 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-add-sequence.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-add-sequence.s
@@ -56,6 +56,7 @@ add      w1, w0, #4
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -     add	w1, w0, #4
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeE .  .   add	w2, w3, #1
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-all-views.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-all-views.s
index 86314c8f3f101..950ead53c8432 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-all-views.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-all-views.s
@@ -90,6 +90,7 @@ str	w0, [x21, x18, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -     1.00   str	w0, [x21, x18, lsl #2]
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-in-order-retire.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-in-order-retire.s
index 8502d0950fec1..36ebf4e9cffe8 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-in-order-retire.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-in-order-retire.s
@@ -90,6 +90,7 @@ add	w7, w9, w0
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -     add	w7, w9, w0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-readadv.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-readadv.s
index b5a6a23c64244..3946923338b0a 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-readadv.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-readadv.s
@@ -509,6 +509,7 @@ ldpsw    x0, x1, [x2], #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -     1.00    -      -     ldpsw	x0, x1, [x2], #16
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          012345
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-store-alias.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-store-alias.s
index 3906975b41f6b..ba5c5cbd4bc2a 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-store-alias.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-store-alias.s
@@ -64,6 +64,7 @@ ldr x3, [x10]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -     1.00    -      -     ldr	x3, [x10]
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-store-noalias.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-store-noalias.s
index dc681f4ce9479..2215a7a6a8c06 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-store-noalias.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-load-store-noalias.s
@@ -62,6 +62,7 @@ ldr x3, [x10]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -     1.00    -      -     ldr	x3, [x10]
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-out-of-order-retire.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-out-of-order-retire.s
index 7c51ceef1489d..fc119ca7a376c 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-out-of-order-retire.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-out-of-order-retire.s
@@ -88,6 +88,7 @@ add	w7, w9, w0
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -     add	w7, w9, w0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-store-readadv.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-store-readadv.s
index ad49a96c27c57..6e0a32f69c37f 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-store-readadv.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-store-readadv.s
@@ -401,6 +401,7 @@ stp      x0, x1, [x2], #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -     1.00   stp	x0, x1, [x2], #16
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          012345678
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-writeback.s
index 0fded5f8f08f4..00b5a0598e223 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-writeback.s
@@ -1171,6 +1171,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -1217,6 +1218,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -1263,6 +1265,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -1309,6 +1312,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1355,6 +1359,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1401,6 +1406,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1447,6 +1453,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1493,6 +1500,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 24.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1539,6 +1547,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 21.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -1585,6 +1594,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 27.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
@@ -1631,6 +1641,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 28.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123
 
@@ -1677,6 +1688,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 28.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123
 
@@ -1723,6 +1735,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 29.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234
 
@@ -1769,6 +1782,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1815,6 +1829,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1861,6 +1876,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1907,6 +1923,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1953,6 +1970,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1999,6 +2017,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2045,6 +2064,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 18.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2091,6 +2111,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2137,6 +2158,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -2183,6 +2205,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2229,6 +2252,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2275,6 +2299,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2321,6 +2346,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2367,6 +2393,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2413,6 +2440,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 21.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2459,6 +2487,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 24.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2505,6 +2534,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 19.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2551,6 +2581,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2597,6 +2628,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2643,6 +2675,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2689,6 +2722,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2735,6 +2769,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2781,6 +2816,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 26.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01
 
@@ -2827,6 +2863,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 32.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234567
 
@@ -2873,6 +2910,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 32.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234567
 
@@ -2919,6 +2957,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2965,6 +3004,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3011,6 +3051,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3057,6 +3098,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3103,6 +3145,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3149,6 +3192,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -3195,6 +3239,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
@@ -3241,6 +3286,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3287,6 +3333,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3333,6 +3380,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3379,6 +3427,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3425,6 +3474,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3471,6 +3521,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3517,6 +3568,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3563,6 +3615,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3609,6 +3662,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3655,6 +3709,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3701,6 +3756,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3747,6 +3803,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3793,6 +3850,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3839,6 +3897,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3885,6 +3944,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3931,6 +3991,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -3977,6 +4038,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 18.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4023,6 +4085,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4069,6 +4132,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4115,6 +4179,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 11.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -4161,6 +4226,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -4207,6 +4273,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
@@ -4253,6 +4320,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4299,6 +4367,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4345,6 +4414,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4391,6 +4461,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4437,6 +4508,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4483,6 +4555,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -4521,6 +4594,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4567,6 +4641,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4613,6 +4688,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4659,6 +4735,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4705,6 +4782,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4751,6 +4829,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4797,6 +4876,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 20.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4843,6 +4923,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4889,6 +4970,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -4935,6 +5017,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -4977,6 +5060,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DE   ..   stp	s1, s2, [x27], #248
@@ -5010,6 +5094,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5056,6 +5141,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5102,6 +5188,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5148,6 +5235,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5194,6 +5282,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5240,6 +5329,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DE  .   strh	w1, [x27, #254]!
@@ -5269,6 +5359,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeE .  .   ldr	x1, [x27], #254
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A57-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A57-writeback.s
index 5248392188f03..8ef8b8ad7a869 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A57-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A57-writeback.s
@@ -1171,19 +1171,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER ..   ld1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeER..   ld1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,5]     . D=eE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE---R..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeER.   ld1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,7]     .  D=eE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE---R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeER   ld1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,9]     .   D=eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1217,19 +1218,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER ..   ld1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeER..   ld1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,5]     . D=eE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE---R..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeER.   ld1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE---R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeER   ld1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1263,19 +1265,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER ..   ld1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeER..   ld1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE---R..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeER.   ld1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE---R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeER   ld1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1309,19 +1312,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  . .   ld1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER . .   ld1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE---R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
 # CHECK-NEXT: [0,5]     .  DeE----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     .   D=eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     .    D=eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .   DPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     .    DPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1355,19 +1359,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   ld1	{ v1.4s, v2.4s }, [x27], #32
 # CHECK-NEXT: [0,1]     .DeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .D=eeeeeER.   .   ld1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     . D=eE---R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     . DPeE---R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  DeeeeeeER  .   ld1	{ v1.8h, v2.8h }, [x27], #32
 # CHECK-NEXT: [0,5]     .   DeE----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    DeeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
 # CHECK-NEXT: [0,7]     .    .DeE----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .D=eeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .    . D=eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    . DPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1401,19 +1406,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .  .   ld1	{ v1.2d, v2.2d }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeE----R .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .D=eeeeeER.  .   ld1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     . D=eE---R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D=eeeeeER  .   ld1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .  D=eE---R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     . DPeE---R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPeeeeeER  .   ld1	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .  DPeE---R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .   DeeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
 # CHECK-NEXT: [0,7]     .    DeE----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    D=eeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .D=eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    .DPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1447,6 +1453,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 11.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -1459,7 +1466,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,6]     .    .DeeeeeeeER .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
 # CHECK-NEXT: [0,7]     .    . DeE-----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .  D=eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,9]     .    .   D=eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    .   DPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1493,6 +1500,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 13.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
@@ -1501,11 +1509,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . DeeeeeeeER   .   .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
 # CHECK-NEXT: [0,3]     .  DeE-----R   .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D=eeeeeeER .   .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,5]     .    D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .D=eeeeeeeER  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,7]     .    . D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    . DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .  D==eeeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,9]     .    .   D==eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    .   DPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1539,6 +1547,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1547,11 +1556,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . DeeeeeeeER   .  .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
 # CHECK-NEXT: [0,3]     .  DeE-----R   .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D=eeeeeeER .  .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .    D=eE----R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    DPeE----R .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .D=eeeeeeER  .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .    . D=eE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    . DPeE----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .  D=eeeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .   D=eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    .   DPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1585,6 +1594,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1593,11 +1603,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . DeeeeeeeER   .    .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 # CHECK-NEXT: [0,3]     .  DeE-----R   .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D=eeeeeeeER.    .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .    D=eE-----R.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    DPeE-----R.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .D==eeeeeeER   .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,7]     .    . D==eE----R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D==eeeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,9]     .    .   D==eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    . DPPeE----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DP=eeeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,9]     .    .   DPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1631,6 +1641,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -1641,9 +1652,9 @@ add x0, x27, 1
 # CHECK-NEXT: [0,4]     .   DeeeeeeeeER.    .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,5]     .    DeE------R.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .D==eeeeeeER   .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,7]     .    . D==eE----R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D==eeeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,9]     .    .   D==eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    . DPPeE----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DP=eeeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,9]     .    .   DPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1677,19 +1688,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
 # CHECK-NEXT: [0,1]     .DeE------R    .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . D==eeeeeeER  .    .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     .  D==eE----R  .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D==eeeeeeeeER   .   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     .    D==eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D====eeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .    . D====eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D====eeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .   D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .  DPPeE----R  .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DP=eeeeeeeeER   .   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DP===eeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPP=eeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .   DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1723,19 +1735,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 15.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .  .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeE------R    .    .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . D==eeeeeeER  .    .    .  .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     .  D==eE----R  .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D==eeeeeeeeER   .    .  .   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     .    D==eE------R   .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D====eeeeeeeeER    .  .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .    . D====eE------R    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D==========eeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,9]     .    .   D==========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .  DPPeE----R  .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DP=eeeeeeeeER   .    .  .   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPeE------R   .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DP===eeeeeeeeER    .  .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPPPeE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPPPPPPeeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1769,19 +1782,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.b }[8], [x27], #1
 # CHECK-NEXT: [0,1]     .DeE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D======eeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .  D======eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D============eeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,5]     .    D============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D==================eeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .    . D==================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D========================eeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,9]     .    .   D========================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1815,19 +1829,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .   .   ld1	{ v1.h }[0], [x27], x28
 # CHECK-NEXT: [0,1]     .DeE------R    .    .    .    .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D======eeeeeeeeER .    .    .    .   .   ld1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,3]     .  D======eE------R .    .    .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D============eeeeeeeeER   .    .   .   ld1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .    D============eE------R   .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D==================eeeeeeeeER.   .   ld1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .    . D==================eE------R.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    . D=========================eeeeeER   ld1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .    .  D=========================eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPeeeeeeeeER .    .    .    .   .   ld1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPeE------R .    .    .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .   .   ld1	{ v1.s }[0], [x27], #4
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPPPeE------R   .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.   .   ld1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPeE------R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   ld1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1861,13 +1876,14 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    ..   ld1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .    ..   ld1r	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,3]     .D=eE---R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeeER  ..   ld1r	{ v1.2d }, [x27], #8
 # CHECK-NEXT: [0,5]     .  DeE------R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .   DeeeeeeeeER..   ld1r	{ v1.2s }, [x27], #4
@@ -1907,6 +1923,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
@@ -1953,6 +1970,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1999,6 +2017,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -2045,6 +2064,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -2091,6 +2111,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
@@ -2137,19 +2158,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .    .    .    .    .    .  .   ld2	{ v1.16b, v2.16b }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeE-------R   .    .    .    .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D=======eeeeeeeeER.    .    .    .    .  .   ld2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,3]     .  D=======eE------R.    .    .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D=============eeeeeeeeER  .    .    .  .   ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,5]     .    D=============eE------R  .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D===================eeeeeeeeER    .  .   ld2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .    . D===================eE------R    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D=========================eeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     .    .   D=========================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPPeeeeeeeeER.    .    .    .    .  .   ld2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,3]     .  DPPPPPPPeE------R.    .    .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPPeeeeeeeeER  .    .    .  .   ld2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPPPPeE------R  .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPPeeeeeeeeER    .  .   ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPPeE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2183,19 +2205,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    .   ld2	{ v1.h, v2.h }[0], [x27], #4
 # CHECK-NEXT: [0,1]     .DeE------R    .    .    .    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D======eeeeeeeeER .    .    .    .    .   ld2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,3]     .  D======eE------R .    .    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D============eeeeeeeeER   .    .    .   ld2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .    D============eE------R   .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D==================eeeeeeeeER.    .   ld2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .    . D==================eE------R.    .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D========================eeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .    .   D========================eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPeeeeeeeeER .    .    .    .    .   ld2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,3]     .  DPPPPPPeE------R .    .    .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .    .   ld2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPPPeE------R   .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.    .   ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPeE------R.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2229,19 +2252,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeeER .    .    .    ..   ld2	{ v1.s, v2.s }[0], [x27], x28
 # CHECK-NEXT: [0,1]     .DeE----R .    .    .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D====eeeeeeeeER   .    ..   ld2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,3]     .  D====eE------R   .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D==========eeeeeeeeER..   ld2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .    D==========eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    D==========eeeeeE--R..   ld2r	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,7]     .    .D==========eE-----R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    . D=========eeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     .    .  D=========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPeeeeeeeeER   .    ..   ld2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,3]     .  DPPPPeE------R   .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPeeeeeeeeER..   ld2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    DPPPPPPPPPPeeeeeE--R..   ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,7]     .    .DPPPPPPPPPPeE-----R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    . DPPPPPPPPPeeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     .    .  DPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2275,6 +2299,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -2321,13 +2346,14 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    . .   ld2r	{ v1.16b, v2.16b }, [x27], #2
 # CHECK-NEXT: [0,1]     .DeE------R    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . DeeeeeE-R    . .   ld2r	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     . D=eE----R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     . DPeE----R    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  DeeeeeeeeER . .   ld2r	{ v1.2d, v2.2d }, [x27], x28
 # CHECK-NEXT: [0,5]     .   DeE------R . .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    DeeeeeeeeER .   ld2r	{ v1.2s, v2.2s }, [x27], x28
@@ -2367,6 +2393,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -2413,6 +2440,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
@@ -2459,6 +2487,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -2467,11 +2496,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     .  DeeeeeeeeER .    .  .   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
 # CHECK-NEXT: [0,3]     .   DeE------R .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    D==eeeeeeeeeER .  .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .    .D==eE-------R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    . D==eeeeeeeeeER  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .    .  D==eE-------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .   D==eeeeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .D=eE--------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    .DPPeE-------R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    . DP=eeeeeeeeeER  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .    .  DPPeE-------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .   DP=eeeeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .    .DPeE--------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2505,6 +2534,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -2514,10 +2544,10 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     .   DeE-------R.    .    .    .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    DeeeeeeeeeeER  .    .    .    .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: [0,5]     .    . DeE-------R  .    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .  D=======eeeeeeeeeER   .    .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,7]     .    .   D=======eE-------R   .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    D==============eeeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,9]     .    .    .D==============eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .  DPPPPPPPeeeeeeeeeER   .    .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,7]     .    .   DPPPPPPPeE-------R   .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    DPPPPPPPPPPPPPPeeeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,9]     .    .    .DPPPPPPPPPPPPPPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2551,19 +2581,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234567
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .    .    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], x28
 # CHECK-NEXT: [0,1]     .DeE-------R   .    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D=======eeeeeeeeeER    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     .  D=======eE-------R    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D==============eeeeeeeeeER.    .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,5]     .    D==============eE-------R.    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D=====================eeeeeeeeeER .    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,7]     .    . D=====================eE-------R .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D============================eeeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .    .   D============================eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPPeeeeeeeeeER    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPPeE-------R    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPPPeeeeeeeeeER.    .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPPPPPeE-------R.    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeER .    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPPPPeE-------R .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2597,19 +2628,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .    .    .    .    .   .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], x28
 # CHECK-NEXT: [0,1]     .DeE-------R   .    .    .    .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D=======eeeeeeeeER.    .    .    .   .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,3]     .  D=======eE------R.    .    .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D=============eeeeeeeeER  .    .   .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .    D=============eE------R  .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D===================eeeeeeER .   .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,7]     .    . D===================eE----R .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D=======================eeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .    .   D=======================eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPPeeeeeeeeER.    .    .    .   .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,3]     .  DPPPPPPPeE------R.    .    .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPPeeeeeeeeER  .    .   .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPPPPeE------R  .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPPeeeeeeER .   .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPPeE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2643,6 +2675,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2689,6 +2722,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
@@ -2735,6 +2769,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
@@ -2781,6 +2816,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 13.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -2789,10 +2825,10 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . DeeeeeeeeER  .    .  .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
 # CHECK-NEXT: [0,3]     .  DeE------R  .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D==eeeeeeeeeER  .  .   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,5]     .    D==eE-------R  .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D==eeeeeeeeeER.  .   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,7]     .    . D==eE-------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D==eeeeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,5]     .    DPPeE-------R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DP=eeeeeeeeeER.  .   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,7]     .    . DPPeE-------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DP=eeeeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,9]     .    .    .DeE---------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
@@ -2827,6 +2863,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2839,7 +2876,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,6]     .    .    DeeeeeeeeER    .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: [0,7]     .    .    .DeE------R    .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .    . D==eeeeeeeeeER   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .  D==eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    .    .  DPPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2873,6 +2910,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
@@ -2919,19 +2957,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 11.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234567
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .    .    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
 # CHECK-NEXT: [0,1]     . DeE------R   .    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .  D======eeeeeeeeeER    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,3]     .    D=====eE-------R    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    .D============eeeeeeeeeER.    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .    .  D===========eE-------R.    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .   D==================eeeeeeeeeER .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,7]     .    .    .D=================eE-------R .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    . D========================eeeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .    .    .   D=======================eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .  DPPPPPPeeeeeeeeeER    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,3]     .    DPPPPPeE-------R    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    .DPPPPPPPPPPPPeeeeeeeeeER.    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .    .  DPPPPPPPPPPPeE-------R.    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .   DPPPPPPPPPPPPPPPPPPeeeeeeeeeER .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: [0,7]     .    .    .DPPPPPPPPPPPPPPPPPeE-------R .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .    .    .   DPPPPPPPPPPPPPPPPPPPPPPPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2965,19 +3004,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012345
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .    .    .    .    .    .    .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
 # CHECK-NEXT: [0,1]     . DeE------R   .    .    .    .    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .  D======eeeeeeeeeER    .    .    .    .    .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .    D=====eE-------R    .    .    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    .D============eeeeeeeeeER.    .    .    .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,5]     .    .  D===========eE-------R.    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .   D==================eeeeeeeeER  .    .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .    .    D==================eE------R  .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    .D========================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .    .    . D========================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .  DPPPPPPeeeeeeeeeER    .    .    .    .    .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .    DPPPPPeE-------R    .    .    .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    .DPPPPPPPPPPPPeeeeeeeeeER.    .    .    .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,5]     .    .  DPPPPPPPPPPPeE-------R.    .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .   DPPPPPPPPPPPPPPPPPPeeeeeeeeER  .    .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .    .    DPPPPPPPPPPPPPPPPPPeE------R  .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3011,19 +3051,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .    .    .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
 # CHECK-NEXT: [0,1]     . DeE------R   .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .  D======eeeeeeeeeER    .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .    D=====eE-------R    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    .D=====eeeeeeE-R    .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,5]     .    . D=====eE-----R    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .  D=====eeeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: [0,7]     .    .    D====eE-------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    .D====eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
-# CHECK-NEXT: [0,9]     .    .    . D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .  DPPPPPPeeeeeeeeeER    .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .    DPPPPPeE-------R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    .DPPPP=eeeeeeE-R    .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,5]     .    . DPPPPPeE-----R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .  DPPPP=eeeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: [0,7]     .    .    DPPPPeE-------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    .DPPP=eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: [0,9]     .    .    . DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3057,6 +3098,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
@@ -3103,6 +3145,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -3149,6 +3192,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -3195,6 +3239,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
@@ -3241,6 +3286,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -3287,19 +3333,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .  .   ldr	b1, [x27], #254
-# CHECK-NEXT: [0,1]     D=====eER .    .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D====eeeeeER  .    .    .  .   ldr	h1, [x27], #254
-# CHECK-NEXT: [0,3]     .D=========eER .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D========eeeeeER  .    .  .   ldr	s1, [x27], #254
-# CHECK-NEXT: [0,5]     . D=============eER .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D============eeeeeER  .  .   ldr	d1, [x27], #254
-# CHECK-NEXT: [0,7]     .  D=================eER .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D================eeeeeER.   ldr	q1, [x27], #254
-# CHECK-NEXT: [0,9]     .   D=====================eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPPPPPeER .    .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPeeeeeER  .    .    .  .   ldr	h1, [x27], #254
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPeER .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPeeeeeER  .    .  .   ldr	s1, [x27], #254
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPeER .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPeeeeeER  .  .   ldr	d1, [x27], #254
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPeER .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPeeeeeER.   ldr	q1, [x27], #254
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3333,19 +3380,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ldr	b1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER ..   ldr	h1, [x27, #254]!
-# CHECK-NEXT: [0,3]     .D=eE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeER..   ldr	s1, [x27, #254]!
-# CHECK-NEXT: [0,5]     . D=eE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE---R..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeER.   ldr	d1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .  D=eE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE---R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeER   ldr	q1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .   D=eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3379,19 +3427,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	w1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,3]     .D=eE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeER .   ldr	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     . D=eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE--R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeER.   ldr	x1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .  D=eE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE--R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeER   ldrb	w1, [x27], #254
-# CHECK-NEXT: [0,9]     .   D=eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3425,19 +3474,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  .   ldrh	w1, [x27], #254
-# CHECK-NEXT: [0,3]     .D=eE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeER .   ldrh	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     . D=eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE--R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeER.   ldrsb	w1, [x27], #254
-# CHECK-NEXT: [0,7]     .  D=eE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE--R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeER   ldrsb	x1, [x27], #254
-# CHECK-NEXT: [0,9]     .   D=eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3471,19 +3521,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrsb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  .   ldrsb	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     .D=eE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeER .   ldrsh	w1, [x27], #254
-# CHECK-NEXT: [0,5]     . D=eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE--R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeER.   ldrsh	x1, [x27], #254
-# CHECK-NEXT: [0,7]     .  D=eE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE--R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeER   ldrsh	w1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .   D=eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3517,16 +3568,17 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   ldrsh	x1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER.   ldrsw	x1, [x27], #254
-# CHECK-NEXT: [0,3]     .D=eE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R.   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeER   ldrsw	x1, [x27, #254]!
-# CHECK-NEXT: [0,5]     . D=eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE--R   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeE--R   st1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,7]     .  D=eE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE-R   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.2d }, [x27], #16
 # CHECK-NEXT: [0,9]     .    DeER   add	x0, x27, #1
 
@@ -3562,16 +3614,17 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .   .   st1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeER.   .   st1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,3]     .D=eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER  .   st1	{ v1.4s }, [x27], #16
 # CHECK-NEXT: [0,5]     .  DeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eER .   st1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,7]     .   D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .   DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    DeeER   st1	{ v1.8h }, [x27], #16
 # CHECK-NEXT: [0,9]     .    .DeER   add	x0, x27, #1
 
@@ -3607,19 +3660,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   st1	{ v1.16b }, [x27], #16
 # CHECK-NEXT: [0,1]     .DeER.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .D=eER    .   st1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     . D=eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     . DPeER   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  DeeER  .   st1	{ v1.2d }, [x27], x28
 # CHECK-NEXT: [0,5]     .   DeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .   D=eER .   st1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .    D=eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    D=eER.   st1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    DPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    DPeER.   st1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3653,13 +3707,14 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    ..   st1	{ v1.4s }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeER.    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .D=eER    ..   st1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     . D=eER   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     . DPeER   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  DeeER  ..   st1	{ v1.8h }, [x27], x28
 # CHECK-NEXT: [0,5]     .   DeER  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    DeeER..   st1	{ v1.16b }, [x27], x28
@@ -3699,19 +3754,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    ..   st1	{ v1.2d, v2.2d }, [x27], #32
 # CHECK-NEXT: [0,1]     .DeE--R   .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . D==eeER .    ..   st1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,3]     .  D==eER .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D==eeER    ..   st1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,5]     .    D==eER    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D==eeeeER..   st1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,7]     .    . D==eE--R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D====eeER   st1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,9]     .    .   D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .  DPPeER .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DP=eeER    ..   st1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,5]     .    DPPeER    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DP=eeeeER..   st1	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,7]     .    . DPPeE--R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DP===eeER   st1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,9]     .    .   DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3745,19 +3801,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    .  .   st1	{ v1.8h, v2.8h }, [x27], #32
 # CHECK-NEXT: [0,1]     .DeE--R   .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . D==eeeeER    .  .   st1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,3]     .  D==eE--R    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D====eeER  .  .   st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,5]     .    D====eER  .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D====eeeeER .   st1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     .    . D====eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D======eeER   st1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .   D======eER   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .  DPPeE--R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DP===eeER  .  .   st1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPPPeER  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPP=eeeeER .   st1	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPP===eeER   st1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3791,6 +3848,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -3799,11 +3857,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . DeeeeER .    .  .   st1	{ v1.4s, v2.4s }, [x27], x28
 # CHECK-NEXT: [0,3]     .  DeE--R .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D==eeER    .  .   st1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     .    D==eER    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D==eeeeER.  .   st1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .    . D==eE--R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D====eeeeER   st1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .   D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    DPPeER    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DP=eeeeER.  .   st1	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPeE--R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DP===eeeeER   st1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .   DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3837,6 +3895,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 21.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -3845,11 +3904,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . D=eeeeeeER   .    .  .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
 # CHECK-NEXT: [0,3]     .   DeE----R   .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    D====eeeER.    .  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,5]     .    .D====eE-R.    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    . D=====eeeER  .  .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,7]     .    .  D=====eE-R  .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .   D======eeeeeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,9]     .    .    .D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    .DPPPPeE-R.    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    . DPPP==eeeER  .  .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,7]     .    .  DPPPPPeE-R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .   DPPPP==eeeeeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,9]     .    .    .DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3883,6 +3942,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 24.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
@@ -3891,11 +3951,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . D=eeeeeeER   .    .    ..   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
 # CHECK-NEXT: [0,3]     .   DeE----R   .    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    D====eeeeeeER  .    ..   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,5]     .    . D===eE----R  .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .  D=======eeeER    ..   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .    .   D=======eE-R    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    D========eeeeeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    . D=======eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    . DPPPeE----R  .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .  DPP=====eeeER    ..   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .    .   DPPPPPPPeE-R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    DPPPPPP==eeeeeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .    . DPPPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3929,19 +3989,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 21.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
 # CHECK:      [0,0]     DeeeER    .    .    .  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeE-R    .    .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . D=eeeER .    .    .  .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .  D=eE-R .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .  DPeE-R .    .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D==eeeeeeER.    .  .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .    .D=eE----R.    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    .DPeE----R.    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    . D=====eeeER  .  .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .    .  D=====eE-R  .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .   D======eeeeeeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    .  DPPPPPeE-R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .   DPPPP==eeeeeeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .    .DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3975,19 +4036,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 26.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeER .    .    .    .  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: [0,1]     . DeE---R .    .    .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .  D===eeeeER  .    .    .  .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,3]     .   D===eE--R  .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    D=====eeeeeeeeER    .  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,5]     .    .  D===eE------R    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .   D=========eeeeER.  .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,7]     .    .    D=========eE--R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    .D===========eeeeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,9]     .    .    . D===========eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .   DPPPeE--R  .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    DPP===eeeeeeeeER    .  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,5]     .    .  DPPPeE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .   DPP=======eeeeER.  .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,7]     .    .    DPPPPPPPPPeE--R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    .DPPPPPPPP===eeeeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,9]     .    .    . DPPPPPPPPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4021,19 +4083,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 32.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .   .   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,1]     .  DeE----R    .    .    .    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .   D====eeeeER.    .    .    .   .   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,3]     .    D====eE--R.    .    .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    .D======eeeeeeeeER  .    .   .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,5]     .    .   D====eE------R  .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .    D==========eeeeeeeeER   .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,7]     .    .    .  D========eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    .   D==============eeeeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .    D==============eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .    DPPPPeE--R.    .    .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    .DPPP===eeeeeeeeER  .    .   .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,5]     .    .   DPPPPeE------R  .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .    DPPP=======eeeeeeeeER   .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,7]     .    .    .  DPPPPPPPPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    .   DPPPPPPP=======eeeeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .    .    DPPPPPPPPPPPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4067,19 +4130,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 28.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: [0,1]     .  DeE----R    .    .    .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .   D====eeeeER.    .    .    .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .    D====eE--R.    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    .D======eeeeER .    .    .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .    . D======eE--R .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .  D========eeeeeeeeER   .   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .    .    .D======eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    . D============eeeeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .  D============eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .    DPPPPeE--R.    .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    .DPPP===eeeeER .    .    .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .    . DPPPPPPeE--R .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .  DPPPPP===eeeeeeeeER   .   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .    .    .DPPPPPPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    . DPPPPP=======eeeeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .    .  DPPPPPPPPPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4113,19 +4177,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 19.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    . .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
 # CHECK-NEXT: [0,1]     .  DeE----R    .    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .   D====eeeeeeeeER . .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .    . D==eE------R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    . D=========eER. .   st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,5]     .    .  D=========eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .  D=========eER .   st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,7]     .    .   D=========eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .   D=========eER.   st1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .    .    D=========eER   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .    . DPPeE------R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    . DPP=======eER. .   st1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,5]     .    .  DPPPPPPPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .  DPPPPPPPPPeER .   st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: [0,7]     .    .   DPPPPPPPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .   DPPPPPPPPPeER.   st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .    .    DPPPPPPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4159,18 +4224,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   st1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeER.  .   st1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeER  .   st1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeER .   st1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeER.   st1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4204,13 +4270,14 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    . .   st1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eER.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeER.    . .   st1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeER  . .   st1	{ v1.d }[0], [x27], #8
 # CHECK-NEXT: [0,5]     .  DeE-R  . .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .   DeeeER. .   st1	{ v1.d }[0], [x27], x28
@@ -4250,6 +4317,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
@@ -4260,7 +4328,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,4]     .   DeeeeER    ..   st2	{ v1.4s, v2.4s }, [x27], #32
 # CHECK-NEXT: [0,5]     .    .DeE-R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    . D=eeeER ..   st2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,7]     .    .  D=eE-R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    .  DPeE-R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .   D=eeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
 # CHECK-NEXT: [0,9]     .    .    .DeE--R   add	x0, x27, #1
 
@@ -4296,19 +4364,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 16.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    .  .   st2	{ v1.16b, v2.16b }, [x27], #32
 # CHECK-NEXT: [0,1]     . DeE-R   .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .  D=eeeeER    .  .   st2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .   D=eE--R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .   DPeE--R    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    D===eeeER .  .   st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .    .D===eE-R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    . D===eeeER  .   st2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .    .  D===eE-R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .   D===eeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .D==eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    .DPPPeE-R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    . DPP=eeeER  .   st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .    .  DPPPeE-R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .   DPP=eeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .    .DPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4342,6 +4411,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
@@ -4352,9 +4422,9 @@ add x0, x27, 1
 # CHECK-NEXT: [0,4]     .    D=eeeeER  ..   st2	{ v1.16b, v2.16b }, [x27], x28
 # CHECK-NEXT: [0,5]     .    . DeE--R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .  D==eeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .    .   D==eE-R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    D=eeeER   st2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,9]     .    .    .D=eE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    .   DPPeE-R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    DPeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,9]     .    .    .DPeE-R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4388,6 +4458,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -4434,6 +4505,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -4480,15 +4552,16 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
 # CHECK-NEXT: [0,1]     . DeE---R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .  D===eeeER  .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,3]     .    D==eE-R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    .D===eeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,5]     .    .  D==eE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .    DPPeE-R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    .DP==eeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,5]     .    .  DPPeE-R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4518,19 +4591,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 27.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    .    .    .   .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
 # CHECK-NEXT: [0,1]     .  DeE--R .    .    .    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .   D==eeeER   .    .    .   .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,3]     .    .D=eE-R   .    .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .    .DPeE-R   .    .    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    . D==eeeeeeER  .    .   .   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
 # CHECK-NEXT: [0,5]     .    .    DeE----R  .    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .    .D====eeeeeeER .   .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,7]     .    .    .   D==eE----R .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    .    D======eeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .    . D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    .    .   DPPeE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    .    DP=====eeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .    .    . DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4564,6 +4638,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 21.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -4574,7 +4649,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,4]     .    .DeeeeeeER.    .  .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
 # CHECK-NEXT: [0,5]     .    .   DeE--R.    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .    D==eeeER  .  .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .    .    . D=eE-R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    .    . DPeE-R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .    .  D==eeeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 # CHECK-NEXT: [0,9]     .    .    .    .DeE----R   add	x0, x27, #1
 
@@ -4610,15 +4685,16 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: [0,1]     .  DeE--R .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .   D==eeeER   .   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,3]     .    D==eE-R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    .D=eeeER  .   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,5]     .    . D=eE-R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .    DPPeE-R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    .DPeeeER  .   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,5]     .    . DPeE-R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .  DeeeER .   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
 # CHECK-NEXT: [0,7]     .    .   DeE-R .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .    DeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
@@ -4656,6 +4732,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -4702,19 +4779,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 19.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
 # CHECK:      [0,0]     DeeeER    .    .    ..   st3	{ v1.s, v2.s, v3.s }[0], [x27], x28
 # CHECK-NEXT: [0,1]     .DeE-R    .    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . D=eeeER .    .    ..   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,3]     .  D=eE-R .    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .  DPeE-R .    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D=eeeER    .    ..   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .    D=eE-R    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    DPeE-R    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    .D=eeeeeeeeER  ..   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
 # CHECK-NEXT: [0,7]     .    .   DeE-----R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .    D=====eeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,9]     .    .    . D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    .    . DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4748,6 +4826,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 32.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -4756,11 +4835,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     .  D=eeeeeeeeER.    .    .    .   .   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,3]     .    . DeE----R.    .    .    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    .  D====eeeeER .    .    .   .   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,5]     .    .    D===eE--R .    .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .    .D=====eeeeeeeeER   .   .   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,7]     .    .    .    D==eE------R   .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    .    .D========eeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,9]     .    .    .    .    D=====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    .    DPPPeE--R .    .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .    .DPP===eeeeeeeeER   .   .   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,7]     .    .    .    DPPeE------R   .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    .    .DP=======eeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,9]     .    .    .    .    DPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4794,19 +4873,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 28.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: [0,1]     .  DeE----R    .    .    .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .   D====eeeeER.    .    .    .   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .    .D===eE--R.    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .    . D=====eeeeER .    .    .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .    .   D====eE--R .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .    D======eeeeeeeeER   .   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .    .    .   D===eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    .    D=========eeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .    . D========eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .    .DPPPeE--R.    .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .    . DPP===eeeeER .    .    .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .    .   DPPPPeE--R .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .    DPPP===eeeeeeeeER   .   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .    .    .   DPPPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    .    DPP=======eeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .    .    .    . DPPPPPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4840,6 +4920,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 19.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -4848,11 +4929,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     .    D===eeeeeeeeER .  .   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
 # CHECK-NEXT: [0,3]     .    .   DeE------R .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    .    D======eeeER .   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .    .    .D======eE-R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .    . D=====eeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,7]     .    .    .  D=====eE-R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .    .   D====eeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .    .    .    D====eE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    .    .DPPPPPPeE-R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .    . DPPPPPeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,7]     .    .    .  DPPPPPeE-R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .    .   DPPPPeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .    .    .    DPPPPeE-R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4886,6 +4967,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -4932,17 +5014,18 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
 # CHECK-NEXT: [0,1]     .DeE--R   .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . D==eeeeER    .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .  D==eE--R    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D====eeeER .   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,5]     .    D====eE-R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D====eeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .    . D====eE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .  DPPeE--R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DP===eeeER .   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
+# CHECK-NEXT: [0,5]     .    DPPPPeE-R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPP=eeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPPPeE-R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4974,6 +5057,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   stp	s1, s2, [x27], #248
@@ -5007,19 +5091,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    ..   stp	q1, q2, [x27], #992
 # CHECK-NEXT: [0,1]     . DeE-R   .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .  D=eER  .    ..   stp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     .   D=eER .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .   DPeER .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .    D=eeER    ..   stp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .    .D=eER    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .    .DPeER    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    . D=eeeeER..   stp	q1, q2, [x27, #992]!
 # CHECK-NEXT: [0,7]     .    .   DeE--R..   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .    D==eER.   stp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     .    .    .D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    .    .DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5053,6 +5138,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5099,6 +5185,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5145,6 +5232,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5191,6 +5279,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -5237,6 +5326,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   strh	w1, [x27, #254]!
@@ -5266,12 +5356,13 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D===eeeeER   ldr	x2, [x1], #254
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPeeeeER   ldr	x2, [x1], #254
 # CHECK-NEXT: [0,3]     .DeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/direct-branch.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/direct-branch.s
index 3a0187fd132a2..5ebfae9f1337a 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/direct-branch.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/direct-branch.s
@@ -43,6 +43,7 @@
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -     b	t
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   b	t
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/forwarding-A57.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/forwarding-A57.s
index 07113df465ade..f1d67bc6ccf42 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/forwarding-A57.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/forwarding-A57.s
@@ -1,285 +1,6 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
 # RUN: llvm-mca -mtriple=aarch64 -mcpu=cortex-a57 -iterations=1 -timeline < %s | FileCheck %s
 
-# CHECK: [0] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      12
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  ..   fmul   v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     DeeeeeeeeeER   fmla   v0.2s, v1.2s, v2.2s
-
-# CHECK: [1] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      13
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  . .   fmul  v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,1]     DeeeeeeeeeeER   fmla  v0.4s, v1.4s, v2.4s
-
-# CHECK: [2] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      12
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  ..   fmulx  v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     DeeeeeeeeeER   fmls   v0.2s, v1.2s, v2.2s
-
-# CHECK: [3] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      13
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  . .   fmulx v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,1]     DeeeeeeeeeeER   fmls  v0.4s, v1.4s, v2.4s
-
-# CHECK: [4] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      16
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeeeeeER   .   fmla       v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D====eeeeeeeeeER   fmla       v0.2s, v3.2s, v4.2s
-
-# CHECK: [5] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      16
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeeeeeER   .   fmls       v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D====eeeeeeeeeER   fmls       v0.2s, v3.2s, v4.2s
-
-# CHECK: [6] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      12
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  ..   fmul   d4, d5, d6
-# CHECK-NEXT: [0,1]     DeeeeeeeeeER   fmadd  d1, d2, d3, d4
-
-# CHECK: [7] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      12
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  ..   fmul   d4, d5, d6
-# CHECK-NEXT: [0,1]     DeeeeeeeeeER   fmadd  d1, d2, d3, d4
-
-# CHECK: [8] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      16
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeeeeeER   .   fmadd      d4, d5, d6, d7
-# CHECK-NEXT: [0,1]     D====eeeeeeeeeER   fmadd      d1, d2, d3, d4
-
-# CHECK: [9] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      16
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeeeeeER   .   fmsub      d4, d5, d6, d7
-# CHECK-NEXT: [0,1]     D====eeeeeeeeeER   fmsub      d1, d2, d3, d4
-
-# CHECK: [10] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      16
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeeeeeER   .   fnmadd     d4, d5, d6, d7
-# CHECK-NEXT: [0,1]     D====eeeeeeeeeER   fnmadd     d1, d2, d3, d4
-
-# CHECK: [11] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      16
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeeeeeER   .   fnmsub     d4, d5, d6, d7
-# CHECK-NEXT: [0,1]     D====eeeeeeeeeER   fnmsub     d1, d2, d3, d4
-
-# CHECK: [12] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   saba       v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeER   saba       v0.2s, v3.2s, v4.2s
-
-# CHECK: [13] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   sabal      v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeER   sabal      v0.2d, v3.2s, v4.2s
-
-# CHECK: [14] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   uaba       v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeER   uaba       v0.2s, v3.2s, v4.2s
-
-# CHECK: [15] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   uabal      v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeER   uabal      v0.2d, v3.2s, v4.2s
-
-# CHECK: [16] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   sadalp     v0.1d, v1.2s
-# CHECK-NEXT: [0,1]     D=eeeeER   sadalp     v0.1d, v2.2s
-
-# CHECK: [17] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   uadalp     v0.1d, v1.2s
-# CHECK-NEXT: [0,1]     D=eeeeER   uadalp     v0.1d, v2.2s
-
-# CHECK: [18] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   srsra      v0.8b, v1.8b, #3
-# CHECK-NEXT: [0,1]     D=eeeeER   srsra      v0.8b, v2.8b, #3
-
-# CHECK: [19] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   ursra      v0.8b, v1.8b, #3
-# CHECK-NEXT: [0,1]     D=eeeeER   ursra      v0.8b, v2.8b, #3
-
-# CHECK: [20] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      8
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeER.   usra       v0.4s, v1.4s, #3
-# CHECK-NEXT: [0,1]     D=eeeeER   usra       v0.4s, v2.4s, #3
-
-# CHECK: [21] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   mul       v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   mla       v0.2s, v1.2s, v2.2s
-
-# CHECK: [22] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      13
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  . .   pmul  v0.8b, v1.8b, v2.8b
-# CHECK-NEXT: [0,1]     D=====eeeeeER   mla   v0.8b, v1.8b, v2.8b
-
-# CHECK: [23] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      13
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  . .   sqdmulh       v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=====eeeeeER   mla   v0.2s, v1.2s, v2.2s
-
-# CHECK: [24] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      13
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER  . .   sqrdmulh      v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=====eeeeeER   mla   v0.2s, v1.2s, v2.2s
-
-# CHECK: [25] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   smull     v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   smlal     v0.2d, v1.2s, v2.2s
-
-# CHECK: [26] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   umull     v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   umlal     v0.2d, v1.2s, v2.2s
-
-# CHECK: [27] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      13
-# CHECK: Timeline view:
-# CHECK: [0,0] DeeeeeER . . sqdmull v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=====eeeeeER   smlal v0.2d, v1.2s, v2.2s
-
-# CHECK: [28] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      13
-# CHECK: Timeline view:
-# CHECK: [0,0] DeeeeeER . . pmull v0.8h, v1.8b, v2.8b
-# CHECK-NEXT: [0,1]     D=====eeeeeER   smlal v0.8h, v1.8b, v2.8b
-
-# CHECK: [29] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      13
-# CHECK: Timeline view:
-# CHECK: [0,0] DeeeeeER . . pmull2 v0.8h, v1.16b, v2.16b
-# CHECK-NEXT: [0,1]     D=====eeeeeER   smlal v0.8h, v1.8b, v2.8b
-
-# CHECK: [30] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   mla       v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   mla       v0.2s, v1.2s, v2.2s
-
-# CHECK: [31] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      11
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeeER .   mla     v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,1]     .D=eeeeeeER   mla     v0.4s, v1.4s, v2.4s
-
-# CHECK: [32] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   mls       v0.2s, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   mls       v0.2s, v1.2s, v2.2s
-
-# CHECK: [33] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      11
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeeER .   mls     v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,1]     .D=eeeeeeER   mls     v0.4s, v1.4s, v2.4s
-
-# CHECK: [34] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   smlal     v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   smlal     v0.2d, v1.2s, v2.2s
-
-# CHECK: [35] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   smlsl     v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   smlsl     v0.2d, v1.2s, v2.2s
-
-# CHECK: [36] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   umlal     v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   umlal     v0.2d, v1.2s, v2.2s
-
-# CHECK: [37] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      9
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER.   umlsl     v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D=eeeeeER   umlsl     v0.2d, v1.2s, v2.2s
-
-# CHECK: [38] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      10
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER .   sqdmlal  v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D==eeeeeER   sqdmlal  v0.2d, v1.2s, v2.2s
-
-# CHECK: [39] Code Region
-# CHECK: Instructions:      2
-# CHECK-NEXT: Total Cycles:      10
-# CHECK: Timeline view:
-# CHECK: [0,0]     DeeeeeER .   sqdmlsl  v0.2d, v1.2s, v2.2s
-# CHECK-NEXT: [0,1]     D==eeeeeER   sqdmlsl  v0.2d, v1.2s, v2.2s
-
 # ASIMD FP Instructions
 # FMUL, FMULX, FMLA, FMLS are impacted
 # testing only a subset of combinations
@@ -313,7 +34,6 @@ fmls v0.2s, v1.2s, v2.2s
 fmls v0.2s, v3.2s, v4.2s
 # LLVM-MCA-END
 
-
 # FP Multiply Instructions
 # FMUL, FMUL, FNMUL, FMADD, FMSUB, FNMADD, FNMSUB are impacted
 # testing only a subset of combinations
@@ -347,8 +67,6 @@ fnmsub d4, d5, d6, d7
 fnmsub d1, d2, d3, d4
 # LLVM-MCA-END
 
-
-
 # ASIMD Integer Instructions X-Unit
 # SABA, UABA, SABAL, UABAL, SADALP, UADALP, SRSRA, USRA, URSRA are impacted
 # testing only a subset of combinations
@@ -398,7 +116,6 @@ usra v0.4s, v1.4s, #3
 usra v0.4s, v2.4s, #3
 # LLVM-MCA-END
 
-
 # ASIMD Multiply Instructions X-Unit
 # pmuls and sqd/sqrdmuls dont forward
 
@@ -448,7 +165,6 @@ pmull2.8h v0, v1, v2
 smlal.8h v0, v1, v2
 # LLVM-MCA-END
 
-
 # MLAs
 # LLVM-MCA-BEGIN
 mla v0.2s, v1.2s, v2.2s
@@ -499,3 +215,2463 @@ sqdmlal v0.2d, v1.2s, v2.2s
 sqdmlsl v0.2d, v1.2s, v2.2s
 sqdmlsl v0.2d, v1.2s, v2.2s
 # LLVM-MCA-END
+
+# CHECK:      [0] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      12
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.17
+# CHECK-NEXT: IPC:               0.17
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     0.50                        fmul	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      9     0.50                        fmla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fmul	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fmla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     01
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  ..   fmul	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DeeeeeeeeeER   fmla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmul	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     1.0    0.0    0.0       fmla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.0    0.5    0.0       <total>
+
+# CHECK:      [1] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      13
+# CHECK-NEXT: Total uOps:        3
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.23
+# CHECK-NEXT: IPC:               0.15
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      5     1.00                        fmul	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:  1      10    1.00                        fmla	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00   2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   fmul	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -     fmla	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  . .   fmul	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,1]     DeeeeeeeeeeER   fmla	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmul	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: 1.     1     1.0    0.0    0.0       fmla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:        1     1.0    0.5    0.0       <total>
+
+# CHECK:      [2] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      12
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.17
+# CHECK-NEXT: IPC:               0.17
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     0.50                        fmulx	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      9     0.50                        fmls	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fmulx	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fmls	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     01
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  ..   fmulx	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DeeeeeeeeeER   fmls	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmulx	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     1.0    0.0    0.0       fmls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.0    0.5    0.0       <total>
+
+# CHECK:      [3] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      13
+# CHECK-NEXT: Total uOps:        3
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.23
+# CHECK-NEXT: IPC:               0.15
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      5     1.00                        fmulx	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:  1      10    1.00                        fmls	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00   2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   fmulx	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -     fmls	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  . .   fmulx	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,1]     DeeeeeeeeeeER   fmls	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmulx	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: 1.     1     1.0    0.0    0.0       fmls	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:        1     1.0    0.5    0.0       <total>
+
+# CHECK:      [4] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      16
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.13
+# CHECK-NEXT: IPC:               0.13
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      9     0.50                        fmla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      9     0.50                        fmla	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fmla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fmla	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012345
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeeeER   .   fmla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPPPPeeeeeeeeeER   fmla	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     5.0    0.0    0.0       fmla	v0.2s, v3.2s, v4.2s
+# CHECK-NEXT:        1     3.0    0.5    0.0       <total>
+
+# CHECK:      [5] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      16
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.13
+# CHECK-NEXT: IPC:               0.13
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      9     0.50                        fmls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      9     0.50                        fmls	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fmls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fmls	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012345
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeeeER   .   fmls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPPPPeeeeeeeeeER   fmls	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     5.0    0.0    0.0       fmls	v0.2s, v3.2s, v4.2s
+# CHECK-NEXT:        1     3.0    0.5    0.0       <total>
+
+# CHECK:      [6] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      12
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.17
+# CHECK-NEXT: IPC:               0.17
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     0.50                        fmul	d4, d5, d6
+# CHECK-NEXT:  1      9     0.50                        fmadd	d1, d2, d3, d4
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fmul	d4, d5, d6
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fmadd	d1, d2, d3, d4
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     01
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  ..   fmul	d4, d5, d6
+# CHECK-NEXT: [0,1]     DeeeeeeeeeER   fmadd	d1, d2, d3, d4
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmul	d4, d5, d6
+# CHECK-NEXT: 1.     1     1.0    0.0    0.0       fmadd	d1, d2, d3, d4
+# CHECK-NEXT:        1     1.0    0.5    0.0       <total>
+
+# CHECK:      [7] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      12
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.17
+# CHECK-NEXT: IPC:               0.17
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     0.50                        fmul	d4, d5, d6
+# CHECK-NEXT:  1      9     0.50                        fmadd	d1, d2, d3, d4
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fmul	d4, d5, d6
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fmadd	d1, d2, d3, d4
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     01
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  ..   fmul	d4, d5, d6
+# CHECK-NEXT: [0,1]     DeeeeeeeeeER   fmadd	d1, d2, d3, d4
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmul	d4, d5, d6
+# CHECK-NEXT: 1.     1     1.0    0.0    0.0       fmadd	d1, d2, d3, d4
+# CHECK-NEXT:        1     1.0    0.5    0.0       <total>
+
+# CHECK:      [8] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      16
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.13
+# CHECK-NEXT: IPC:               0.13
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      9     0.50                        fmadd	d4, d5, d6, d7
+# CHECK-NEXT:  1      9     0.50                        fmadd	d1, d2, d3, d4
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fmadd	d4, d5, d6, d7
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fmadd	d1, d2, d3, d4
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012345
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeeeER   .   fmadd	d4, d5, d6, d7
+# CHECK-NEXT: [0,1]     DPPPPeeeeeeeeeER   fmadd	d1, d2, d3, d4
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmadd	d4, d5, d6, d7
+# CHECK-NEXT: 1.     1     5.0    0.0    0.0       fmadd	d1, d2, d3, d4
+# CHECK-NEXT:        1     3.0    0.5    0.0       <total>
+
+# CHECK:      [9] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      16
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.13
+# CHECK-NEXT: IPC:               0.13
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      9     0.50                        fmsub	d4, d5, d6, d7
+# CHECK-NEXT:  1      9     0.50                        fmsub	d1, d2, d3, d4
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fmsub	d4, d5, d6, d7
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fmsub	d1, d2, d3, d4
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012345
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeeeER   .   fmsub	d4, d5, d6, d7
+# CHECK-NEXT: [0,1]     DPPPPeeeeeeeeeER   fmsub	d1, d2, d3, d4
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fmsub	d4, d5, d6, d7
+# CHECK-NEXT: 1.     1     5.0    0.0    0.0       fmsub	d1, d2, d3, d4
+# CHECK-NEXT:        1     3.0    0.5    0.0       <total>
+
+# CHECK:      [10] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      16
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.13
+# CHECK-NEXT: IPC:               0.13
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      9     0.50                        fnmadd	d4, d5, d6, d7
+# CHECK-NEXT:  1      9     0.50                        fnmadd	d1, d2, d3, d4
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fnmadd	d4, d5, d6, d7
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fnmadd	d1, d2, d3, d4
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012345
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeeeER   .   fnmadd	d4, d5, d6, d7
+# CHECK-NEXT: [0,1]     DPPPPeeeeeeeeeER   fnmadd	d1, d2, d3, d4
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fnmadd	d4, d5, d6, d7
+# CHECK-NEXT: 1.     1     5.0    0.0    0.0       fnmadd	d1, d2, d3, d4
+# CHECK-NEXT:        1     3.0    0.5    0.0       <total>
+
+# CHECK:      [11] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      16
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.13
+# CHECK-NEXT: IPC:               0.13
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      9     0.50                        fnmsub	d4, d5, d6, d7
+# CHECK-NEXT:  1      9     0.50                        fnmsub	d1, d2, d3, d4
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     1.00   1.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   fnmsub	d4, d5, d6, d7
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     fnmsub	d1, d2, d3, d4
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012345
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeeeER   .   fnmsub	d4, d5, d6, d7
+# CHECK-NEXT: [0,1]     DPPPPeeeeeeeeeER   fnmsub	d1, d2, d3, d4
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       fnmsub	d4, d5, d6, d7
+# CHECK-NEXT: 1.     1     5.0    0.0    0.0       fnmsub	d1, d2, d3, d4
+# CHECK-NEXT:        1     3.0    0.5    0.0       <total>
+
+# CHECK:      [12] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        saba	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      4     1.00                        saba	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   saba	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   saba	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   saba	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeER   saba	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       saba	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       saba	v0.2s, v3.2s, v4.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [13] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        sabal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      4     1.00                        sabal	v0.2d, v3.2s, v4.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   sabal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   sabal	v0.2d, v3.2s, v4.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   sabal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeER   sabal	v0.2d, v3.2s, v4.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       sabal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       sabal	v0.2d, v3.2s, v4.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [14] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        uaba	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      4     1.00                        uaba	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   uaba	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   uaba	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   uaba	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeER   uaba	v0.2s, v3.2s, v4.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       uaba	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       uaba	v0.2s, v3.2s, v4.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [15] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        uabal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      4     1.00                        uabal	v0.2d, v3.2s, v4.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   uabal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   uabal	v0.2d, v3.2s, v4.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   uabal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeER   uabal	v0.2d, v3.2s, v4.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       uabal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       uabal	v0.2d, v3.2s, v4.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [16] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        sadalp	v0.1d, v1.2s
+# CHECK-NEXT:  1      4     1.00                        sadalp	v0.1d, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   sadalp	v0.1d, v1.2s
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   sadalp	v0.1d, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   sadalp	v0.1d, v1.2s
+# CHECK-NEXT: [0,1]     DPeeeeER   sadalp	v0.1d, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       sadalp	v0.1d, v1.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       sadalp	v0.1d, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [17] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        uadalp	v0.1d, v1.2s
+# CHECK-NEXT:  1      4     1.00                        uadalp	v0.1d, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   uadalp	v0.1d, v1.2s
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   uadalp	v0.1d, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   uadalp	v0.1d, v1.2s
+# CHECK-NEXT: [0,1]     DPeeeeER   uadalp	v0.1d, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       uadalp	v0.1d, v1.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       uadalp	v0.1d, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [18] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        srsra	v0.8b, v1.8b, #3
+# CHECK-NEXT:  1      4     1.00                        srsra	v0.8b, v2.8b, #3
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   srsra	v0.8b, v1.8b, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   srsra	v0.8b, v2.8b, #3
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   srsra	v0.8b, v1.8b, #3
+# CHECK-NEXT: [0,1]     DPeeeeER   srsra	v0.8b, v2.8b, #3
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       srsra	v0.8b, v1.8b, #3
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       srsra	v0.8b, v2.8b, #3
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [19] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        ursra	v0.8b, v1.8b, #3
+# CHECK-NEXT:  1      4     1.00                        ursra	v0.8b, v2.8b, #3
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   ursra	v0.8b, v1.8b, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   ursra	v0.8b, v2.8b, #3
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   ursra	v0.8b, v1.8b, #3
+# CHECK-NEXT: [0,1]     DPeeeeER   ursra	v0.8b, v2.8b, #3
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       ursra	v0.8b, v1.8b, #3
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       ursra	v0.8b, v2.8b, #3
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [20] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      8
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.25
+# CHECK-NEXT: IPC:               0.25
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      4     1.00                        usra	v0.4s, v1.4s, #3
+# CHECK-NEXT:  1      4     1.00                        usra	v0.4s, v2.4s, #3
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   usra	v0.4s, v1.4s, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   usra	v0.4s, v2.4s, #3
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     01234567
+
+# CHECK:      [0,0]     DeeeeER.   usra	v0.4s, v1.4s, #3
+# CHECK-NEXT: [0,1]     DPeeeeER   usra	v0.4s, v2.4s, #3
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       usra	v0.4s, v1.4s, #3
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       usra	v0.4s, v2.4s, #3
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [21] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        mul	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mul	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   mul	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       mul	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       mla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [22] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      13
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.15
+# CHECK-NEXT: IPC:               0.15
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        pmul	v0.8b, v1.8b, v2.8b
+# CHECK-NEXT:  1      5     1.00                        mla	v0.8b, v1.8b, v2.8b
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     pmul	v0.8b, v1.8b, v2.8b
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mla	v0.8b, v1.8b, v2.8b
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  . .   pmul	v0.8b, v1.8b, v2.8b
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER   mla	v0.8b, v1.8b, v2.8b
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       pmul	v0.8b, v1.8b, v2.8b
+# CHECK-NEXT: 1.     1     6.0    0.0    0.0       mla	v0.8b, v1.8b, v2.8b
+# CHECK-NEXT:        1     3.5    0.5    0.0       <total>
+
+# CHECK:      [23] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      13
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.15
+# CHECK-NEXT: IPC:               0.15
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        sqdmulh	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     sqdmulh	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  . .   sqdmulh	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER   mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       sqdmulh	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     6.0    0.0    0.0       mla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:        1     3.5    0.5    0.0       <total>
+
+# CHECK:      [24] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      13
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.15
+# CHECK-NEXT: IPC:               0.15
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        sqrdmulh	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     sqrdmulh	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  . .   sqrdmulh	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER   mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       sqrdmulh	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     6.0    0.0    0.0       mla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:        1     3.5    0.5    0.0       <total>
+
+# CHECK:      [25] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        smull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   smull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       smull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       smlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [26] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        umull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        umlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     umull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     umlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   umull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   umlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       umull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       umlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [27] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      13
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.15
+# CHECK-NEXT: IPC:               0.15
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        sqdmull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     sqdmull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  . .   sqdmull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER   smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       sqdmull	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     6.0    0.0    0.0       smlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     3.5    0.5    0.0       <total>
+
+# CHECK:      [28] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      13
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.15
+# CHECK-NEXT: IPC:               0.15
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        pmull	v0.8h, v1.8b, v2.8b
+# CHECK-NEXT:  1      5     1.00                        smlal	v0.8h, v1.8b, v2.8b
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     pmull	v0.8h, v1.8b, v2.8b
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smlal	v0.8h, v1.8b, v2.8b
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  . .   pmull	v0.8h, v1.8b, v2.8b
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER   smlal	v0.8h, v1.8b, v2.8b
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       pmull	v0.8h, v1.8b, v2.8b
+# CHECK-NEXT: 1.     1     6.0    0.0    0.0       smlal	v0.8h, v1.8b, v2.8b
+# CHECK-NEXT:        1     3.5    0.5    0.0       <total>
+
+# CHECK:      [29] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      13
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.15
+# CHECK-NEXT: IPC:               0.15
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        pmull2	v0.8h, v1.16b, v2.16b
+# CHECK-NEXT:  1      5     1.00                        smlal	v0.8h, v1.8b, v2.8b
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     pmull2	v0.8h, v1.16b, v2.16b
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smlal	v0.8h, v1.8b, v2.8b
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     012
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER  . .   pmull2	v0.8h, v1.16b, v2.16b
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER   smlal	v0.8h, v1.8b, v2.8b
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       pmull2	v0.8h, v1.16b, v2.16b
+# CHECK-NEXT: 1.     1     6.0    0.0    0.0       smlal	v0.8h, v1.8b, v2.8b
+# CHECK-NEXT:        1     3.5    0.5    0.0       <total>
+
+# CHECK:      [30] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        mla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   mla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   mla	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       mla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       mla	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [31] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      11
+# CHECK-NEXT: Total uOps:        4
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.36
+# CHECK-NEXT: IPC:               0.18
+# CHECK-NEXT: Block RThroughput: 4.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      6     2.00                        mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:  2      6     2.00                        mla	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     4.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -     mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -     mla	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     0
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeER .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,1]     .DPeeeeeeER   mla	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [32] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        mls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        mls	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     mls	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   mls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   mls	v0.2s, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       mls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       mls	v0.2s, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [33] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      11
+# CHECK-NEXT: Total uOps:        4
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.36
+# CHECK-NEXT: IPC:               0.18
+# CHECK-NEXT: Block RThroughput: 4.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      6     2.00                        mls	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:  2      6     2.00                        mls	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     4.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -     mls	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -     mls	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT:                     0
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeER .   mls	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,1]     .DPeeeeeeER   mls	v0.4s, v1.4s, v2.4s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       mls	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       mls	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [34] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        smlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   smlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   smlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       smlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       smlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [35] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        smlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        smlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     smlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   smlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   smlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       smlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       smlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [36] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        umlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        umlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     umlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     umlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   umlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   umlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       umlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       umlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [37] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      9
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.22
+# CHECK-NEXT: IPC:               0.22
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        umlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        umlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     umlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     umlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeeeeeER.   umlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPeeeeeER   umlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       umlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     2.0    0.0    0.0       umlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     1.5    0.5    0.0       <total>
+
+# CHECK:      [38] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      10
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.20
+# CHECK-NEXT: IPC:               0.20
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        sqdmlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        sqdmlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     sqdmlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     sqdmlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER .   sqdmlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPPeeeeeER   sqdmlal	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       sqdmlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     3.0    0.0    0.0       sqdmlal	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     2.0    0.5    0.0       <total>
+
+# CHECK:      [39] Code Region
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      10
+# CHECK-NEXT: Total uOps:        2
+
+# CHECK:      Dispatch Width:    3
+# CHECK-NEXT: uOps Per Cycle:    0.20
+# CHECK-NEXT: IPC:               0.20
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        sqdmlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  1      5     1.00                        sqdmlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - A57UnitB
+# CHECK-NEXT: [1.0] - A57UnitI
+# CHECK-NEXT: [1.1] - A57UnitI
+# CHECK-NEXT: [2]   - A57UnitL
+# CHECK-NEXT: [3]   - A57UnitM
+# CHECK-NEXT: [4]   - A57UnitS
+# CHECK-NEXT: [5]   - A57UnitW
+# CHECK-NEXT: [6]   - A57UnitX
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]
+# CHECK-NEXT:  -      -      -      -      -      -     2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1.0]  [1.1]  [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     sqdmlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -     sqdmlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeER .   sqdmlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: [0,1]     DPPeeeeeER   sqdmlsl	v0.2d, v1.2s, v2.2s
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       sqdmlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT: 1.     1     3.0    0.0    0.0       sqdmlsl	v0.2d, v1.2s, v2.2s
+# CHECK-NEXT:        1     2.0    0.5    0.0       <total>
diff --git a/llvm/test/tools/llvm-mca/AArch64/HiSilicon/tsv110-forwarding.s b/llvm/test/tools/llvm-mca/AArch64/HiSilicon/tsv110-forwarding.s
index b29697ea7972b..5728c7fa2f3ee 100644
--- a/llvm/test/tools/llvm-mca/AArch64/HiSilicon/tsv110-forwarding.s
+++ b/llvm/test/tools/llvm-mca/AArch64/HiSilicon/tsv110-forwarding.s
@@ -28,12 +28,13 @@ madd x0, x0, x0, x0
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   mul	x0, x1, x2
-# CHECK-NEXT: [0,1]     D====eER .   add	x0, x0, x1
-# CHECK-NEXT: [0,2]     D=====eER.   add	x0, x0, x1
-# CHECK-NEXT: [0,3]     D======eER   add	x0, x0, x1
+# CHECK-NEXT: [0,1]     DPPPPeER .   add	x0, x0, x1
+# CHECK-NEXT: [0,2]     DPPPPPeER.   add	x0, x0, x1
+# CHECK-NEXT: [0,3]     DPPPPPPeER   add	x0, x0, x1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -61,13 +62,14 @@ madd x0, x0, x0, x0
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   mul	x0, x1, x2
 # CHECK-NEXT: [0,1]     D==eeeeER ..   madd	x0, x1, x2, x0
 # CHECK-NEXT: [0,2]     D=eeeeE-R ..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [0,3]     D=====eeeeER   madd	x0, x0, x0, x0
+# CHECK-NEXT: [0,3]     DPPPPPeeeeER   madd	x0, x0, x0, x0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/HiSilicon/tsv110-writeback.s b/llvm/test/tools/llvm-mca/AArch64/HiSilicon/tsv110-writeback.s
index 2738f0b54c243..791650948a428 100644
--- a/llvm/test/tools/llvm-mca/AArch64/HiSilicon/tsv110-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/HiSilicon/tsv110-writeback.s
@@ -729,14 +729,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   ld1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   ld1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   ld1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,4]     . D==eeeeeER   ld1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   ld1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   ld1	{ v1.2s }, [x27], #8
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   ld1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   ld1	{ v1.4s }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -765,14 +766,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   ld1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   ld1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   ld1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeER   ld1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   ld1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   ld1	{ v1.16b }, [x27], #16
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   ld1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   ld1	{ v1.2d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -801,14 +803,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   ld1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   ld1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   ld1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeER   ld1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   ld1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   ld1	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   ld1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   ld1	{ v1.8h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -837,14 +840,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   ld1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   ld1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,4]     . D==eeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   ld1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   ld1	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -873,14 +877,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   ld1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   ld1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,4]     . D==eeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   ld1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   ld1	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -909,14 +914,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   ld1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   ld1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   ld1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   ld1	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -945,14 +951,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .  .   ld1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER .  .   ld1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeeER  .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,3]     . D=eeeeeeER .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,4]     .  D==eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,1]     DPeeeeeER .  .   ld1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeeER  .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
+# CHECK-NEXT: [0,3]     . DPeeeeeeER .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,4]     .  DP=eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -981,14 +988,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
 # CHECK-NEXT: [0,1]     .DeeeeeeER.   .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
 # CHECK-NEXT: [0,2]     . D=eeeeeeER  .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,3]     .  D=eeeeeeER .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,4]     .   D==eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,3]     .  DPeeeeeeER .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,4]     .   DP=eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1017,14 +1025,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeeeeeeER.   .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
 # CHECK-NEXT: [0,2]     . D=eeeeeeER  .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .  D=eeeeeeER .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,4]     .   D==eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     .  DPeeeeeeER .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,4]     .   DP=eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1053,14 +1062,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeeeeeeER.   .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 # CHECK-NEXT: [0,2]     . D=eeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .  D=eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,4]     .   D==eeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,3]     .  DPeeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,4]     .   DP=eeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1089,6 +1099,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -1125,6 +1136,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -1161,6 +1173,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1168,7 +1181,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: [0,1]     .DeeeeeeER.    .  .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 # CHECK-NEXT: [0,2]     . DeeeeeeER    .  .   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
 # CHECK-NEXT: [0,3]     .  DeeeeeeER   .  .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,4]     .   D=====eeeeeeeER   ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,4]     .   DPPPPPeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1197,14 +1210,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,1]     .D======eeeeeeeER   .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,2]     . D============eeeeeeeER .    .    . .   ld1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     .  D==================eeeeeeeER    . .   ld1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,4]     .   D========================eeeeeeeER   ld1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,1]     .DPPPPPPeeeeeeeER   .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,2]     . DPPPPPPPPPPPPeeeeeeeER .    .    . .   ld1	{ v1.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1233,14 +1247,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,1]     .D======eeeeeeeER   .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,2]     . D============eeeeeeeER .    .    . .   ld1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,3]     .  D==================eeeeeeeER    . .   ld1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,4]     .   D========================eeeeeeeER   ld1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,1]     .DPPPPPPeeeeeeeER   .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,2]     . DPPPPPPPPPPPPeeeeeeeER .    .    . .   ld1	{ v1.s }[0], [x27], #4
+# CHECK-NEXT: [0,3]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1269,6 +1284,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -1305,6 +1321,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -1341,6 +1358,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -1377,6 +1395,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -1413,6 +1432,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -1449,6 +1469,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -1485,14 +1506,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     .D======eeeeeeeER   .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,2]     . D============eeeeeeeER .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,3]     .  D==================eeeeeeeER    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,4]     .   D========================eeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,1]     .DPPPPPPeeeeeeeER   .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,2]     . DPPPPPPPPPPPPeeeeeeeER .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,3]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1521,14 +1543,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,1]     .D======eeeeeeeER   .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,2]     . D============eeeeeeeER .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .  D==================eeeeeeeER    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,4]     .   D========================eeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,1]     .DPPPPPPeeeeeeeER   .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,2]     . DPPPPPPPPPPPPeeeeeeeER .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1557,14 +1580,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .   ld2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     .D======eeeeeeeER   .    .   ld2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,2]     . D============eeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .  D============eeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,4]     .   D============eeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
+# CHECK-NEXT: [0,1]     .DPPPPPPeeeeeeeER   .    .   ld2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,2]     . DPPPPPPPPPPPPeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPPPPPPPeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1593,6 +1617,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -1629,6 +1654,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -1665,6 +1691,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
@@ -1701,6 +1728,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1737,6 +1765,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1773,14 +1802,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
 # CHECK-NEXT: [0,1]     . DeeeeeeeeER  .    .    .    .   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 # CHECK-NEXT: [0,2]     .   DeeeeeeeeER.    .    .    .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .    .D======eeeeeeeeER  .    .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,4]     .    .  D============eeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,3]     .    .DPPPPPPeeeeeeeeER  .    .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,4]     .    .  DPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1809,14 +1839,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     . D======eeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,2]     .   D============eeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,3]     .    .D==================eeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,4]     .    .  D========================eeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,1]     . DPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,2]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: [0,3]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,4]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1845,14 +1876,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     . D======eeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,2]     .   D============eeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .    .D==================eeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,4]     .    .  D========================eeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,1]     . DPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,2]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,4]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1881,6 +1913,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1917,6 +1950,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1953,6 +1987,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -1989,6 +2024,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 10.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
@@ -2025,6 +2061,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 11.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -2061,6 +2098,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 11.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -2097,14 +2135,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,1]     . D======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,2]     .   D============eeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .    .D==================eeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,4]     .    .  D========================eeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,1]     . DPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,2]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: [0,4]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2133,14 +2172,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,1]     . D======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,2]     .   D============eeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,3]     .    .D==================eeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,4]     .    .  D========================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,1]     . DPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,2]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,3]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,4]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2169,14 +2209,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    . .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,1]     . D======eeeeeeeeER . .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,2]     .   D=====eeeeeeeeER. .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,3]     .    .D=====eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: [0,4]     .    .  D====eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: [0,1]     . DPPPPPPeeeeeeeeER . .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,2]     .   DPPPPPeeeeeeeeER. .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,3]     .    .DPPPP=eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: [0,4]     .    .  DPPPPeeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2205,6 +2246,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -2241,6 +2283,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -2277,6 +2320,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
@@ -2313,6 +2357,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -2349,6 +2394,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -2385,14 +2431,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ldr	b1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   ldr	h1, [x27], #254
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   ldr	s1, [x27], #254
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   ldr	d1, [x27], #254
-# CHECK-NEXT: [0,4]     . D==eeeeeER   ldr	q1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   ldr	h1, [x27], #254
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   ldr	s1, [x27], #254
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   ldr	d1, [x27], #254
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   ldr	q1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2421,14 +2468,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ldr	b1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   ldr	h1, [x27, #254]!
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   ldr	s1, [x27, #254]!
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   ldr	d1, [x27, #254]!
-# CHECK-NEXT: [0,4]     . D==eeeeeER   ldr	q1, [x27, #254]!
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   ldr	h1, [x27, #254]!
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   ldr	s1, [x27, #254]!
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   ldr	d1, [x27, #254]!
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   ldr	q1, [x27, #254]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2457,14 +2505,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	w1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eeeeER  .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,2]     .D=eeeeER .   ldr	w1, [x27, #254]!
-# CHECK-NEXT: [0,3]     .D==eeeeER.   ldr	x1, [x27, #254]!
-# CHECK-NEXT: [0,4]     . D==eeeeER   ldrb	w1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeeeeER  .   ldr	x1, [x27], #254
+# CHECK-NEXT: [0,2]     .DPeeeeER .   ldr	w1, [x27, #254]!
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   ldr	x1, [x27, #254]!
+# CHECK-NEXT: [0,4]     . DPPeeeeER   ldrb	w1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2493,14 +2542,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeeeER  .   ldrh	w1, [x27], #254
-# CHECK-NEXT: [0,2]     .D=eeeeER .   ldrh	w1, [x27, #254]!
-# CHECK-NEXT: [0,3]     .D==eeeeER.   ldrsb	w1, [x27], #254
-# CHECK-NEXT: [0,4]     . D==eeeeER   ldrsb	x1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeeeeER  .   ldrh	w1, [x27], #254
+# CHECK-NEXT: [0,2]     .DPeeeeER .   ldrh	w1, [x27, #254]!
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   ldrsb	w1, [x27], #254
+# CHECK-NEXT: [0,4]     . DPPeeeeER   ldrsb	x1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2529,14 +2579,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrsb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeeeER  .   ldrsb	x1, [x27, #254]!
-# CHECK-NEXT: [0,2]     .D=eeeeER .   ldrsh	w1, [x27], #254
-# CHECK-NEXT: [0,3]     .D==eeeeER.   ldrsh	x1, [x27], #254
-# CHECK-NEXT: [0,4]     . D==eeeeER   ldrsh	w1, [x27, #254]!
+# CHECK-NEXT: [0,1]     DPeeeeER  .   ldrsb	x1, [x27, #254]!
+# CHECK-NEXT: [0,2]     .DPeeeeER .   ldrsh	w1, [x27], #254
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   ldrsh	x1, [x27], #254
+# CHECK-NEXT: [0,4]     . DPPeeeeER   ldrsh	w1, [x27, #254]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2565,13 +2616,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   ldrsh	x1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeeeER .   ldrsw	x1, [x27], #254
-# CHECK-NEXT: [0,2]     .D=eeeeER.   ldrsw	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     .D==eeeER.   st1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,4]     . D==eeeER   st1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeeER .   ldrsw	x1, [x27], #254
+# CHECK-NEXT: [0,2]     .DPeeeeER.   ldrsw	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     .DPPeeeER.   st1	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,4]     . DPPeeeER   st1	{ v1.2d }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2600,13 +2652,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER   .   st1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eeeER  .   st1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,2]     .D=eeeER .   st1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,3]     .D==eeeER.   st1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,4]     . D==eeeER   st1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeER  .   st1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,2]     .DPeeeER .   st1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,3]     .DPPeeeER.   st1	{ v1.8b }, [x27], #8
+# CHECK-NEXT: [0,4]     . DPPeeeER   st1	{ v1.8h }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2635,13 +2688,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER   .   st1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eeeER  .   st1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeER .   st1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeER.   st1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeER   st1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeER  .   st1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeER .   st1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeER.   st1	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeER   st1	{ v1.4h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2670,14 +2724,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .   st1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeER   .   st1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeER  .   st1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeER .   st1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeER   st1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeER   .   st1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeER  .   st1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeER .   st1	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st1	{ v1.1d, v2.1d }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2706,14 +2761,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,2]     .D=eeeeER .   st1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,3]     .D==eeeeER.   st1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,4]     . D==eeeeER   st1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,2]     .DPeeeeER .   st1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   st1	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st1	{ v1.8b, v2.8b }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2742,14 +2798,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,2]     .D=eeeeER .   st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeER.   st1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeER   st1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,2]     .DPeeeeER .   st1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   st1	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st1	{ v1.2s, v2.2s }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2778,14 +2835,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeER .   st1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeER.   st1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeER   st1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeER .   st1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   st1	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st1	{ v1.16b, v2.16b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2814,14 +2872,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,4]     . D==eeeeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2850,14 +2909,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2886,14 +2946,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2922,14 +2983,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  . .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,2]     .D=eeeeeeER .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,3]     .D==eeeeeeER.   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,4]     . D==eeeeeeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,2]     .DPeeeeeeER .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,3]     .DPPeeeeeeER.   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,4]     . DPPeeeeeeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2958,14 +3020,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,2]     .D=eeeeeeER .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,3]     .D==eeeeeeER.   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,4]     . D==eeeeeeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,2]     .DPeeeeeeER .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,3]     .DPPeeeeeeER.   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,4]     . DPPeeeeeeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2994,14 +3057,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3030,13 +3094,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER.   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeE--R   st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,3]     .D==eeeE-R   st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,4]     . D==eeeER   st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeE--R   st1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,3]     .DPPeeeE-R   st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: [0,4]     . DPPeeeER   st1	{ v1.b }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3065,13 +3130,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER   .   st1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeER  .   st1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,2]     .D=eeeER .   st1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,3]     .D==eeeER.   st1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeER   st1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeER  .   st1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,2]     .DPeeeER .   st1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,3]     .DPPeeeER.   st1	{ v1.h }[0], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeER   st1	{ v1.h }[4], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3100,14 +3166,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .   st1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eeeER   .   st1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeER  .   st1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,3]     .D==eeeER .   st1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,1]     DPeeeER   .   st1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeER  .   st1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,3]     .DPPeeeER .   st1	{ v1.d }[0], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3136,14 +3203,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,2]     .D=eeeeER .   st2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,3]     .D==eeeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,4]     . D==eeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,2]     .DPeeeeER .   st2	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3172,14 +3240,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3208,14 +3277,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeER .   st2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,4]     . D==eeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeER .   st2	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3244,14 +3314,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,3]     .D==eeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,4]     . D==eeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3280,14 +3351,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,2]     .D=eeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,4]     . D==eeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,2]     .DPeeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,4]     . DPPeeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3316,11 +3388,12 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eeeeeER.   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,2]     .D=eeeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,1]     DPeeeeeER.   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,2]     .DPeeeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3347,14 +3420,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,4]     . D==eeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3383,14 +3457,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3419,14 +3494,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3455,14 +3531,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,1]     D=eeeeeER ..   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,2]     .D=eeeeeER..   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeER.   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,1]     DPeeeeeER ..   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,2]     .DPeeeeeER..   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeER.   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3491,14 +3568,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .   .   st3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER .   .   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,2]     .D=eeeeeER.   .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,4]     . D==eeeeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,1]     DPeeeeeER .   .   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,2]     .DPeeeeeER.   .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,4]     . DPPeeeeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3527,14 +3605,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,2]     .D=eeeeeeeeER .   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,4]     . D==eeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,2]     .DPeeeeeeeeER .   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,4]     . DPPeeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3563,14 +3642,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeeeeER .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeeeeER .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3599,14 +3679,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER .   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER.   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeeE-R.   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,3]     .D==eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,4]     . D==eeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER.   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeeE-R.   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
+# CHECK-NEXT: [0,3]     .DPPeeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,4]     . DPPeeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3635,14 +3716,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,2]     .D=eeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,3]     .D==eeeeeeER.   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,2]     .DPeeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
+# CHECK-NEXT: [0,3]     .DPPeeeeeeER.   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3671,13 +3753,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,1]     D=eeeeeeER..   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,3]     .D==eeeeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER..   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
+# CHECK-NEXT: [0,3]     .DPPeeeeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3705,6 +3788,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeeER..   stp	s1, s2, [x27], #248
@@ -3734,14 +3818,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 9.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    ..   stp	q1, q2, [x27], #992
 # CHECK-NEXT: [0,1]     .D=eeER   ..   stp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,2]     . D==eeER ..   stp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,3]     .  D===eeER.   stp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,4]     .   D====eER   stp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,2]     . DP=eeER ..   stp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,3]     .  DPP=eeER.   stp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,4]     .   DPPP=eER   stp	w1, w2, [x27], #248
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3770,13 +3855,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   stp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eER. .   stp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,2]     .D=eER .   stp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,3]     .D==eER.   str	b1, [x27], #254
-# CHECK-NEXT: [0,4]     . D==eER   str	h1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeER. .   stp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,2]     .DPeER .   stp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,3]     .DPPeER.   str	b1, [x27], #254
+# CHECK-NEXT: [0,4]     . DPPeER   str	h1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3805,13 +3891,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   str	s1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eER. .   str	d1, [x27], #254
-# CHECK-NEXT: [0,2]     .D=eER .   str	q1, [x27], #254
-# CHECK-NEXT: [0,3]     .D==eER.   str	b1, [x27, #254]!
-# CHECK-NEXT: [0,4]     . D==eER   str	h1, [x27, #254]!
+# CHECK-NEXT: [0,1]     DPeER. .   str	d1, [x27], #254
+# CHECK-NEXT: [0,2]     .DPeER .   str	q1, [x27], #254
+# CHECK-NEXT: [0,3]     .DPPeER.   str	b1, [x27, #254]!
+# CHECK-NEXT: [0,4]     . DPPeER   str	h1, [x27, #254]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3840,13 +3927,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   str	s1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER. .   str	d1, [x27, #254]!
-# CHECK-NEXT: [0,2]     .D=eER .   str	q1, [x27, #254]!
-# CHECK-NEXT: [0,3]     .D==eER.   str	w1, [x27], #254
-# CHECK-NEXT: [0,4]     . D==eER   str	x1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeER. .   str	d1, [x27, #254]!
+# CHECK-NEXT: [0,2]     .DPeER .   str	q1, [x27, #254]!
+# CHECK-NEXT: [0,3]     .DPPeER.   str	w1, [x27], #254
+# CHECK-NEXT: [0,4]     . DPPeER   str	x1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3875,13 +3963,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   str	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER. .   str	x1, [x27, #254]!
-# CHECK-NEXT: [0,2]     .D=eER .   strb	w1, [x27], #254
-# CHECK-NEXT: [0,3]     .D==eER.   strb	w1, [x27, #254]!
-# CHECK-NEXT: [0,4]     . D==eER   strh	w1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeER. .   str	x1, [x27, #254]!
+# CHECK-NEXT: [0,2]     .DPeER .   strb	w1, [x27], #254
+# CHECK-NEXT: [0,3]     .DPPeER.   strb	w1, [x27, #254]!
+# CHECK-NEXT: [0,4]     . DPPeER   strh	w1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3910,6 +3999,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeER   strh	w1, [x27, #254]!
@@ -3936,11 +4026,12 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,1]     D====eeeeER   ldr	x2, [x1], #254
+# CHECK-NEXT: [0,1]     DPPPPeeeeER   ldr	x2, [x1], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/N1-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/N1-writeback.s
index 8fe21167a5bd3..3cdcf14bb9290 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/N1-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/N1-writeback.s
@@ -1171,19 +1171,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER ..   ld1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeER..   ld1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ld1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeER   ld1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER ..   ld1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeER..   ld1	{ v1.2s }, [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ld1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeER   ld1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1217,19 +1218,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER ..   ld1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeER..   ld1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ld1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeER   ld1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER ..   ld1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeER..   ld1	{ v1.16b }, [x27], #16
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ld1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeER   ld1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1263,19 +1265,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER ..   ld1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeER..   ld1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ld1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeER   ld1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER ..   ld1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeER..   ld1	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ld1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeER   ld1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1309,19 +1312,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER ..   ld1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeER..   ld1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER ..   ld1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeER..   ld1	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1355,19 +1359,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER ..   ld1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeER..   ld1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER ..   ld1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeER..   ld1	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1401,19 +1406,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ld1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER ..   ld1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeER..   ld1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER ..   ld1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeER..   ld1	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1447,19 +1453,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .  .   ld1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER .  .   ld1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE---R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER  .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,5]     .D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeeER .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,7]     . D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D==eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,9]     .  D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER .  .   ld1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE---R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER  .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
+# CHECK-NEXT: [0,5]     .DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeeeER .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,7]     . DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DP=eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,9]     .  DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1493,19 +1500,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.   .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,3]     .D=eE----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,7]     .  D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,7]     .  DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1539,19 +1547,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.   .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1585,19 +1594,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.   .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,7]     .  DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1631,19 +1641,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE----R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.    ..   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eE----R.    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeER  ..   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,5]     . D===eE----R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeER ..   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D===eE----R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D====eeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE----R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeER ..   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,7]     .  DPPPeE----R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP==eeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,9]     .   DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1677,19 +1688,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eE----R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.    ..   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeER  ..   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE----R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeER ..   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D===eE----R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D====eeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE----R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeER ..   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPeE----R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP==eeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1723,19 +1735,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
 # CHECK:      [0,0]     DeeeeeeER .    .    .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .    .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.    .    .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.    .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeER  .    .   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE----R  .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeER .    .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D===eE----R .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=======eeeeeeeER   ld1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,9]     .   D========eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE----R  .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeER .    .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPeE----R .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1769,19 +1782,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=======eeeeeeeER   .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D========eE-----R   .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=============eeeeeeeER .    .    . .   ld1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,5]     .D==============eE-----R .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D====================eeeeeeeER    . .   ld1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .D=====================eE-----R    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==========================eeeeeeeER   ld1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,9]     . D===========================eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeeeeER   .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPeE-----R   .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPeeeeeeeER .    .    . .   ld1	{ v1.b }[8], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPeE-----R .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPeE-----R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1815,19 +1829,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=======eeeeeeeER   .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,3]     D========eE-----R   .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=============eeeeeeeER .    .    . .   ld1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .D==============eE-----R .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D====================eeeeeeeER    . .   ld1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D=====================eE-----R    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==========================eeeeeeeER   ld1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,9]     . D===========================eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeeeeER   .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPeE-----R   .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPeeeeeeeER .    .    . .   ld1	{ v1.s }[0], [x27], #4
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPeE-----R .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPeE-----R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1861,19 +1876,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.  .   ld1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeER  .   ld1r	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,3]     D==eE-----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
-# CHECK-NEXT: [0,7]     .D===eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeER   ld1r	{ v1.4h }, [x27], #2
-# CHECK-NEXT: [0,9]     . D===eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeER  .   ld1r	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPeE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
+# CHECK-NEXT: [0,7]     .DPPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeER   ld1r	{ v1.4h }, [x27], #2
+# CHECK-NEXT: [0,9]     . DPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1907,19 +1923,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.  .   ld1r	{ v1.4s }, [x27], #4
-# CHECK-NEXT: [0,1]     D=eE-----R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeER  .   ld1r	{ v1.8b }, [x27], #1
-# CHECK-NEXT: [0,3]     D==eE-----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
-# CHECK-NEXT: [0,5]     .D==eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
-# CHECK-NEXT: [0,7]     .D===eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeER   ld1r	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeER  .   ld1r	{ v1.8b }, [x27], #1
+# CHECK-NEXT: [0,3]     DPPeE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
+# CHECK-NEXT: [0,5]     .DPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
+# CHECK-NEXT: [0,7]     .DPPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeER   ld1r	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1953,19 +1970,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.  .   ld1r	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeER  .   ld1r	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE-----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeER   ld1r	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeER  .   ld1r	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeER   ld1r	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1999,19 +2017,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.  .   ld1r	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeER  .   ld1r	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE-----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     . D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D=eeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     .  D==eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeER  .   ld1r	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7]     . DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     .  DPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2045,19 +2064,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.  .   ld2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE-----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     . D=eE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D=eE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE-----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2091,19 +2111,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.  .   ld2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE-----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2137,19 +2158,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D======eeeeeeeER   .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,3]     .D=======eE-----R   .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D============eeeeeeeER .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,5]     . D=============eE-----R .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==================eeeeeeeER    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D===================eE-----R    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D========================eeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=========================eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPeeeeeeeER   .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,3]     .DPPPPPPPeE-----R   .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPeeeeeeeER .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPeE-----R .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPeE-----R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2183,19 +2205,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D======eeeeeeeER   .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,3]     .D=======eE-----R   .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D============eeeeeeeER .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D=============eE-----R .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==================eeeeeeeER    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .  D===================eE-----R    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D========================eeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .   D=========================eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPeeeeeeeER   .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,3]     .DPPPPPPPeE-----R   .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPeeeeeeeER .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPeE-----R .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPeE-----R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2229,19 +2252,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .   ld2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D======eeeeeeeER   .    .   ld2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,3]     .D=======eE-----R   .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D============eeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D=============eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D============eeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,7]     .  D=============eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============eeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     .   D=============eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPeeeeeeeER   .    .   ld2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,3]     .DPPPPPPPeE-----R   .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2275,19 +2299,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.  .   ld2r	{ v1.2s, v2.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE-----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER  .   ld2r	{ v1.4h, v2.4h }, [x27], #4
-# CHECK-NEXT: [0,3]     .D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
-# CHECK-NEXT: [0,5]     . D=eE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
-# CHECK-NEXT: [0,7]     .  D=eE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE-----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
-# CHECK-NEXT: [0,9]     .   D=eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2321,19 +2346,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.  .   ld2r	{ v1.16b, v2.16b }, [x27], #2
-# CHECK-NEXT: [0,1]     D=eE-----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER  .   ld2r	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE-----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2367,19 +2393,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   .   ld2r	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER   .   ld2r	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER  .   ld2r	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeER .   ld2r	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE-----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,9]     .   D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2413,19 +2440,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER ..   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,5]     . D==eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER..   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,7]     .  D==eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER..   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,7]     .  DPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2459,19 +2487,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER ..   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER..   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER..   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2505,19 +2534,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    . .   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   .    .    . .   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   .    .    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER .    .    . .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE------R .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D========eeeeeeeER    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,7]     .  D=========eE-----R    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==============eeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,9]     .   D===============eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPeeeeeeeER    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPeE-----R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2551,19 +2581,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D======eeeeeeeER   .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     .D=======eE-----R   .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D============eeeeeeeER .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,5]     . D=============eE-----R .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==================eeeeeeeER    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,7]     .  D===================eE-----R    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D========================eeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=========================eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPeeeeeeeER   .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPeE-----R   .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPeeeeeeeER .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPeE-----R .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPeE-----R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2597,19 +2628,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .    .    .    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D======eeeeeeeER   .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,3]     .D=======eE-----R   .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D============eeeeeeeER .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D=============eE-----R .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==================eeeeeeeER    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,7]     .  D===================eE-----R    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D========================eeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=========================eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPeeeeeeeER   .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,3]     .DPPPPPPPeE-----R   .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPeeeeeeeER .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPeE-----R .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPeE-----R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2643,19 +2675,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE-----R.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER    .   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE-----R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeER  .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
-# CHECK-NEXT: [0,5]     . D==eE-----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeER .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
-# CHECK-NEXT: [0,7]     .  D==eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
-# CHECK-NEXT: [0,9]     .   D===eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeER .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
+# CHECK-NEXT: [0,7]     .  DPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
+# CHECK-NEXT: [0,9]     .   DPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2689,19 +2722,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], #3
-# CHECK-NEXT: [0,1]     D=eE-----R.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER    .   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
-# CHECK-NEXT: [0,3]     .D=eE-----R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeER  .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
-# CHECK-NEXT: [0,5]     . D==eE-----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeER .   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeER .   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2735,19 +2769,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER    .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeER  .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE-----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeER .   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeER .   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2781,11 +2816,12 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .   .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeeER .   .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
 # CHECK-NEXT: [0,3]     . DeE--------R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  DeeeeeeeeER .   .   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
@@ -2827,6 +2863,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -2873,6 +2910,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -2919,19 +2957,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
 # CHECK-NEXT: [0,1]     .DeE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,3]     .  D======eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D============eeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .    D============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D==================eeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,7]     .    . D==================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D========================eeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .    .   D========================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,3]     .  DPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2965,19 +3004,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
 # CHECK-NEXT: [0,1]     .DeE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .  D======eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D============eeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,5]     .    D============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D==================eeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .    . D==================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D========================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .    .   D========================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,5]     .    DPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3011,19 +3051,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
 # CHECK-NEXT: [0,1]     .DeE------R    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     . D======eeeeeeeeER .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .  D======eE------R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .   D=====eeeeeeeeER.  .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,5]     .    D=====eE------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    .D======eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: [0,7]     .    . D======eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .  D=====eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
-# CHECK-NEXT: [0,9]     .    .   D=====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     . DPPPPPPeeeeeeeeER .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPeE------R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .   DPPPPPeeeeeeeeER.  .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,5]     .    DPPPPPeE------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    .DPPPP==eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: [0,7]     .    . DPPPPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .  DPPPPPeeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: [0,9]     .    .   DPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3057,6 +3098,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -3103,6 +3145,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
@@ -3149,6 +3192,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -3159,9 +3203,9 @@ add x0, x27, 1
 # CHECK-NEXT: [0,4]     .   DeeeeeeeeER.   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
 # CHECK-NEXT: [0,5]     .    DeE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .    D=eeeeeE-R.   ldp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,7]     .    D==eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .D==eeeeeER   ldp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,9]     .    .D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    DPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .DP=eeeeeER   ldp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,9]     .    .DPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3195,19 +3239,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER. .   ldp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D=eE-----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeE-R. .   ldp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeER. .   ldp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D==eE---R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeER   ldp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,7]     .D===eE-----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeE--R   ldp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeE-R. .   ldp	s1, s2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeER. .   ldp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPeE---R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeER   ldp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,7]     .DPPPeE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeE--R   ldp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3241,19 +3286,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   ldp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eE--R   ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  ..   ldp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eE--R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER ..   ldp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D==eE--R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ldpsw	x1, x2, [x27], #248
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeER   ldpsw	x1, x2, [x27, #248]!
-# CHECK-NEXT: [0,9]     . D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  ..   ldp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER ..   ldp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPeE--R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ldpsw	x1, x2, [x27], #248
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeER   ldpsw	x1, x2, [x27, #248]!
+# CHECK-NEXT: [0,9]     . DPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3287,19 +3333,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ldr	b1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER ..   ldr	h1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeER..   ldr	s1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ldr	d1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeER   ldr	q1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER ..   ldr	h1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeER..   ldr	s1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ldr	d1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeER   ldr	q1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3333,19 +3380,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   ldr	b1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeER ..   ldr	h1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeER..   ldr	s1, [x27, #254]!
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER.   ldr	d1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeER   ldr	q1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeER ..   ldr	h1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeER..   ldr	s1, [x27, #254]!
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER.   ldr	d1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeER   ldr	q1, [x27, #254]!
+# CHECK-NEXT: [0,9]     .DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3379,19 +3427,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	w1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldr	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldr	x1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrb	w1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldr	x1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldr	w1, [x27, #254]!
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldr	x1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrb	w1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3425,19 +3474,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldrh	w1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldrh	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldrsb	w1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrsb	x1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldrh	w1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldrh	w1, [x27, #254]!
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldrsb	w1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrsb	x1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3471,19 +3521,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrsb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldrsb	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldrsh	w1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldrsh	x1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrsh	w1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldrsb	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldrsh	w1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldrsh	x1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrsh	w1, [x27, #254]!
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3517,18 +3568,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   ldrsh	x1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER.   ldrsw	x1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER   ldrsw	x1, [x27, #254]!
-# CHECK-NEXT: [0,5]     .D==eE--R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeE-R   st1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eE-R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER.   ldrsw	x1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER   ldrsw	x1, [x27, #254]!
+# CHECK-NEXT: [0,5]     .DPPeE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeE-R   st1	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3562,18 +3614,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.8b }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3607,18 +3660,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3652,18 +3706,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3697,18 +3752,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3742,18 +3798,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3787,18 +3844,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3832,19 +3890,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    . .   st1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE-R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-R    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  . .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,3]     .D=eE--R  . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeER . .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,5]     . D==eE-R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeER. .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,7]     .  D==eE-R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,9]     .   D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE-R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeER. .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,7]     .  DPPeE-R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,9]     .   DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3878,19 +3937,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    . .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE-R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-R    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  . .   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,3]     .D=eE--R  . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeER. .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,5]     . D==eE--R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeER. .   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE-R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeER. .   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE-R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3924,19 +3984,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    . .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-R    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeER   . .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-R   . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-R   . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeER. .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE--R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeER. .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE-R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeER. .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE-R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3970,19 +4031,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeE-R   .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eE-R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeER   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,5]     .  D=eE---R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeE--R   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D==eE--R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,9]     .   D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .  DPeE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeE--R   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,7]     .  DPPeE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,9]     .   DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4016,19 +4078,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,1]     .DeE---R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeE--R  ..   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeER.   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,5]     .  D=eE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .  DPeE---R.   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .   DeeeeeER   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
 # CHECK-NEXT: [0,7]     .    DeE---R   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    D==eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .    D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4062,19 +4125,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeE---R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeE--R  ..   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeER  ..   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eER  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeER   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .   D=eE---R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeE--R   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeER  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeER   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .   DPeE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeE--R   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4108,6 +4172,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
@@ -4116,11 +4181,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . DeeeeeER. .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
 # CHECK-NEXT: [0,3]     .  DeE---R. .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  D=eeeeER .   st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,5]     .  D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .   D=eeeeER.   st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,7]     .   D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeER   st1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .  DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .   DPeeeeER.   st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: [0,7]     .   DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPeeeeER   st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4154,19 +4219,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st1	{ v1.h }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4200,19 +4266,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   st1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE--R   ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  ..   st1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER ..   st1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE--R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER..   st1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,9]     . D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  ..   st1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER ..   st1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeE--R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER..   st1	{ v1.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,9]     . DPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4246,19 +4313,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   st2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eE--R   ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  ..   st2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE--R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeER..   st2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE---R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeER..   st2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,7]     . D==eE--R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D=eeeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,9]     .  D==eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  ..   st2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeER..   st2	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE---R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeER..   st2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,7]     . DPPeE--R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPeeeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,9]     .  DPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4292,19 +4360,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER ..   st2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeER ..   st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE--R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeER..   st2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     . D==eE--R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D=eeeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .  D==eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE--R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeER..   st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     . DPPeE--R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPeeeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .  DPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4338,19 +4407,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .   st2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE---R .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeER.   st2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE---R.   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .  D=eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D=eeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,9]     .  D==eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPeeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,9]     .  DPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4384,19 +4454,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4430,19 +4501,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4476,15 +4548,16 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE---R .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,5]     . D==eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4514,19 +4587,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .   .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE---R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,7]     .  D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,7]     .  DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4560,19 +4634,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .  .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .  .   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE---R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeER  .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeER  .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE---R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE---R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   D=eeeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4606,19 +4681,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeE-R . .   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,3]     .D=eE---R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeER. .   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,5]     . D==eE--R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeER .   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeER .   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4652,19 +4728,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   . .   st3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,1]     D=eE--R   . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  . .   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,3]     .D=eE--R  . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeER. .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE--R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeER .   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,9]     .   D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeER .   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,9]     .   DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4698,19 +4775,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    .   st3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .    .   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE---R .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeER    .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE---R    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER  .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,7]     .   D=eE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE---R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER  .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,7]     .   DPeE----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    D=eeeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,9]     .    D==eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    DPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4744,19 +4822,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    .  .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE-----R.    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeER  .  .   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,3]     . DeE-------R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  DeeeeeeeER  .  .   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,5]     .  D=eE-----R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .  DPeE-----R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .   D==eeeeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,7]     .    D==eE-------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .D=eeeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,9]     .    . D=eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    DPPeE-------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .DPeeeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,9]     .    . DPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4790,19 +4869,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeE----R .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     . DeeeeeeeER   ..   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     . D=eE-----R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     . DPeE-----R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  D=eeeeeeeER ..   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .  D==eE-----R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .   D=eeeeeeeeeER   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .    D=eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .  DPPeE-----R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .   DPeeeeeeeeeER   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .    DPeE-------R   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .    .D=eeeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .    .D==eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .    .DPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4836,6 +4916,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
@@ -4844,11 +4925,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . DeeeeeeeeeER ..   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
 # CHECK-NEXT: [0,3]     .  DeE-------R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D==eeeeeER ..   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .   D===eE---R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    D===eeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,7]     .    D====eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .D===eeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .    .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .   DPPPeE---R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    DPP=eeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,7]     .    DPPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .DPPPeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .    .DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4882,19 +4963,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .  .   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .  .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,3]     .D=eE---R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeER  .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,5]     . D==eE---R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE---R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE---R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE---R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4928,17 +5010,18 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,1]     D=eE---R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE---R .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,5]     . D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4970,12 +5053,13 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DeeER.   stp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,1]     D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER   stp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,3]     .D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5003,18 +5087,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER   .   stp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D=eE-R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER   .   stp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     .D=eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER  .   stp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     . D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeER   stp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,7]     .  D==eE-R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eE-R   stp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     .   D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeE-R   stp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     .   DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5048,18 +5133,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   stp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeER.  .   stp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeER  .   stp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeER.   str	b1, [x27], #254
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D=eeER   str	h1, [x27], #254
-# CHECK-NEXT: [0,9]     .  D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeER.   str	b1, [x27], #254
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPeeER   str	h1, [x27], #254
+# CHECK-NEXT: [0,9]     .  DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5093,18 +5179,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   str	s1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   str	d1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   str	q1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeER.   str	b1, [x27, #254]!
-# CHECK-NEXT: [0,7]     . D==eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   str	h1, [x27, #254]!
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   str	d1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   str	q1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeER.   str	b1, [x27, #254]!
+# CHECK-NEXT: [0,7]     . DPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   str	h1, [x27, #254]!
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5138,18 +5225,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   str	s1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   str	d1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   str	q1, [x27, #254]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eER .   str	w1, [x27], #254
-# CHECK-NEXT: [0,7]     . D==eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   str	x1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   str	d1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   str	q1, [x27, #254]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeER .   str	w1, [x27], #254
+# CHECK-NEXT: [0,7]     . DPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   str	x1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5183,18 +5271,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   str	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   str	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   strb	w1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eER .   strb	w1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   strh	w1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   str	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   strb	w1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeER .   strb	w1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   strh	w1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5228,10 +5317,11 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 0.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   strh	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5257,13 +5347,14 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D====eeeeER   ldr	x2, [x1], #254
-# CHECK-NEXT: [0,3]     D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPeeeeER   ldr	x2, [x1], #254
+# CHECK-NEXT: [0,3]     DPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/N2-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/N2-writeback.s
index 5ffaf9138d482..618d103b4fd74 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/N2-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/N2-writeback.s
@@ -1191,19 +1191,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.2s }, [x27], #8
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1237,19 +1238,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.16b }, [x27], #16
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1283,19 +1285,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1329,19 +1332,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1375,19 +1379,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1421,19 +1426,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1467,19 +1473,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1513,19 +1520,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1559,19 +1567,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1605,19 +1614,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .  .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeER.   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,7]     . D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,9]     . D===eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER.  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeER.   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,7]     . DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,9]     . DPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1651,19 +1661,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   .   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE-----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER   .   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eE-----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER  .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,5]     . D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeeeeeER.   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D==eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,9]     .   DPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1697,19 +1708,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eE-----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER   .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER  .   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeeeeeER.   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1743,19 +1755,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    ..   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER    .    ..   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER   .    ..   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE-----R   .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R   .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeeeeeER .    ..   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE-----R .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D========eeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,9]     .  D=========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeE-----R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPPPPPPPPeeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,9]     .  DPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1789,19 +1802,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1835,19 +1849,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.s }[0], [x27], #4
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1881,19 +1896,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld1r	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld1r	{ v1.4h }, [x27], #2
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld1r	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld1r	{ v1.4h }, [x27], #2
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1927,19 +1943,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.4s }, [x27], #4
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld1r	{ v1.8b }, [x27], #1
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld1r	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld1r	{ v1.8b }, [x27], #1
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld1r	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1973,19 +1990,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld1r	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld1r	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld1r	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld1r	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2019,19 +2037,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld1r	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     . D==eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld1r	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7]     . DPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2065,19 +2084,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     . D==eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D=eeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .  D==eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,3]     .DPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,7]     . DPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPeeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .  DPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2111,19 +2131,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     . D==eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     . DPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2157,19 +2178,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     . D=======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     . DPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2203,19 +2225,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2249,19 +2272,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .  .   ld2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .  .   ld2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,3]     D=========eE------R .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D================eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D================eeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,7]     .D=================eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D================eeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     . D=================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .  .   ld2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPeeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPeeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2295,19 +2319,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.2s, v2.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2r	{ v1.4h, v2.4h }, [x27], #4
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2r	{ v1.4h, v2.4h }, [x27], #4
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2341,19 +2366,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.16b, v2.16b }, [x27], #2
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2r	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2r	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2387,19 +2413,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2r	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2r	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2r	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2r	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2r	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2433,19 +2460,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER ..   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,5]     . D==eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER..   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,7]     .  D==eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER..   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,7]     .  DPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2479,19 +2507,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER ..   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER..   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER..   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2525,19 +2554,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .   .   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   .    .    .   .   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R   .    .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   .    .    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER .    .    .   .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE------R .    .    .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D========eeeeeeeeER   .   .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,7]     .  D=========eE------R   .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D===============eeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,9]     .   D================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R .    .    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPeeeeeeeeER   .   .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPeE------R   .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2571,19 +2601,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2617,19 +2648,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2663,19 +2695,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER ..   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
-# CHECK-NEXT: [0,5]     . D==eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER..   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
-# CHECK-NEXT: [0,7]     .  D==eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER..   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
+# CHECK-NEXT: [0,7]     .  DPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2709,19 +2742,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], #3
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER ..   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
-# CHECK-NEXT: [0,5]     . D==eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER..   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER..   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2755,19 +2789,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER ..   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER..   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER..   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2801,19 +2836,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .  .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeER  .  .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE-------R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-------R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER .  .   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,5]     . D==eE------R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeeER  .   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D===eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D===eeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D====eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DP=eeeeeeeeER  .   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,7]     .  DPPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP=eeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,9]     .   DPPPPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2847,19 +2883,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .  .   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeER  .  .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE-------R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-------R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeeeeER  .   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,5]     . D===eE-------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeeeER .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D===eE-------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D====eeeeeeeeER   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE-------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeeeeER .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPeE-------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP==eeeeeeeeER   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2893,19 +2930,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .   .   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeER  .   .   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-------R  .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-------R  .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeeeER.   .   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE------R.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeeeER  .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D===eE-------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D====eeeeeeeeeER   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=====eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE------R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeeeeER  .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPeE-------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP==eeeeeeeeeER   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2939,19 +2977,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2985,19 +3024,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3031,19 +3071,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D=======eeeeeeeeER.  .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,5]     . D========eE------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=========eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D==========eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=========eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
-# CHECK-NEXT: [0,9]     .   D==========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPeeeeeeeeER.  .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,5]     . DPPPPPPPPeE------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPP==eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPeeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3077,19 +3118,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .  .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   .  .   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE------R   .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeeeER.  .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #4
-# CHECK-NEXT: [0,5]     . D===eE------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeeER  .   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
-# CHECK-NEXT: [0,7]     .  D===eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D====eeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
-# CHECK-NEXT: [0,9]     .   D=====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeeeER  .   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
+# CHECK-NEXT: [0,7]     .  DPPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP==eeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
+# CHECK-NEXT: [0,9]     .   DPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3123,19 +3165,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .  .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   .  .   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R   .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeeeER.  .   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeeER  .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D===eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D====eeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeeeER  .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP==eeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3169,19 +3212,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER  .   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE------R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeE-R   ldp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,7]     .  D===eE-----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D===eeeeeeER   ldp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,9]     .  D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeE-R   ldp	s1, s2, [x27], #248
+# CHECK-NEXT: [0,7]     .  DPPPeE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPPPeeeeeeER   ldp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,9]     .  DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3215,19 +3259,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D=eE----R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER..   ldp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     .D=eE----R..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER.   ldp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D==eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeeER   ldp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,7]     . D==eE----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeE-R   ldp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     .  D==eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER.   ldp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeeeER   ldp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,7]     . DPPeE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeE-R   ldp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     .  DPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3261,19 +3306,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    .   ldp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eE--R   .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .    .   ldp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eE--R  .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .    .   ldp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D==eE--R .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeER    .   ldpsw	x1, x2, [x27], #248
-# CHECK-NEXT: [0,7]     .D===eE---R    .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D======eeeeeER   ldpsw	x1, x2, [x27, #248]!
-# CHECK-NEXT: [0,9]     . D=======eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .    .   ldp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeE--R  .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .    .   ldp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPeE--R .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeER    .   ldpsw	x1, x2, [x27], #248
+# CHECK-NEXT: [0,7]     .DPPPeE---R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPP====eeeeeER   ldpsw	x1, x2, [x27, #248]!
+# CHECK-NEXT: [0,9]     . DPPPPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3307,19 +3353,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ldr	b1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ldr	h1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ldr	s1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ldr	d1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ldr	q1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ldr	h1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ldr	s1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ldr	d1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ldr	q1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3353,19 +3400,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ldr	b1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ldr	h1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ldr	s1, [x27, #254]!
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ldr	d1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ldr	q1, [x27, #254]!
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ldr	h1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ldr	s1, [x27, #254]!
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ldr	d1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ldr	q1, [x27, #254]!
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3399,19 +3447,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	w1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldr	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldr	x1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrb	w1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldr	x1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldr	w1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldr	x1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrb	w1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3445,19 +3494,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldrh	w1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldrh	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldrsb	w1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrsb	x1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldrh	w1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldrh	w1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldrsb	w1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrsb	x1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3491,19 +3541,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrsb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldrsb	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldrsh	w1, [x27], #254
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldrsh	x1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrsh	w1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldrsb	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldrsh	w1, [x27], #254
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldrsh	x1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrsh	w1, [x27, #254]!
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3537,18 +3588,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   ldrsh	x1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER.   ldrsw	x1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER   ldrsw	x1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeE-R   st1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eE-R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER.   ldrsw	x1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER   ldrsw	x1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeE-R   st1	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3582,18 +3634,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.8b }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3627,18 +3680,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3672,18 +3726,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3717,18 +3772,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3762,18 +3818,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeER.   st1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     . D==eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeER.   st1	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,7]     . DPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3807,18 +3864,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3852,18 +3910,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER   .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,3]     .D=eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,5]     . D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,7]     .  D==eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,9]     .   D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,9]     .   DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3897,18 +3956,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER   .   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,3]     .D=eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,5]     . D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3942,18 +4002,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER   .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER  .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   D=eeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3987,19 +4048,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER    .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eER    .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeER  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,5]     . D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeER .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,9]     .   D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeER .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,7]     .  DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,9]     .   DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4033,19 +4095,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    ..   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eER.    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER    ..   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eER    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeER  ..   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,5]     . D==eER  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeER ..   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,7]     .  D==eER ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D===eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeER  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeER ..   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,7]     .  DPPeER ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP==eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4079,18 +4142,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER   .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4124,19 +4188,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    . .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER    . .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeER .   st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,5]     . D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D===eeeeER.   st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,7]     . D====eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D===eeeeER   st1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .  D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPPPeeeeER.   st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: [0,7]     . DPPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPPPeeeeER   st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .  DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4170,19 +4235,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st1	{ v1.h }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4216,19 +4282,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st1	{ v1.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4262,19 +4329,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st2	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4308,19 +4376,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  .   st2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     . D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     . DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4354,19 +4423,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st2	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4400,19 +4470,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4446,19 +4517,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4492,19 +4564,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    . .   st2g	x26, [x27], #4064
-# CHECK-NEXT: [0,1]     D=eER.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.    . .   st2g	x26, [x27, #4064]!
-# CHECK-NEXT: [0,3]     D==eER    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeER .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,7]     . D==eE---R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D==eeeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,9]     .  D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.    . .   st2g	x26, [x27, #4064]!
+# CHECK-NEXT: [0,3]     DPPeER    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeeER .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,7]     . DPPeE---R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DP=eeeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,9]     .  DPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4538,19 +4611,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .   .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE---R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,7]     .  D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,7]     .  DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4584,19 +4658,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .  .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeER .  .   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE---R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE---R .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeER  .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeER  .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE---R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE---R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   D=eeeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4630,19 +4705,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.   .   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,3]     .D=eE----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER .   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER .   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4676,19 +4752,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   st3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.   .   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,3]     .D=eE----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER .   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER .   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4722,19 +4799,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   st3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.   .   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeER  .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,7]     .  D==eE---R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeER  .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,7]     .  DPPeE---R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4768,19 +4846,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE----R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER    ..   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,3]     . DeE-----R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .  DeeeeeeER   ..   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,5]     .  D=eE----R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .  DPeE----R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .   D==eeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,7]     .    D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .D=eeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,9]     .    . D=eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .    DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .DPeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,9]     .    . DPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4814,19 +4893,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.    .   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeER  .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeER.   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .   D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    D==eeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .    D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeeER.   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .   DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    DP=eeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .    DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4860,6 +4940,7 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -4868,11 +4949,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     . DeeeeeeeER   . .   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
 # CHECK-NEXT: [0,3]     .  DeE-----R   . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     .   D==eeeeeeER. .   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .   D===eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .    D===eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,7]     .    D====eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .    .D===eeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .    .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     .   DPPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .    DPP=eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,7]     .    DPPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .    .DPPPeeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .    .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4906,19 +4987,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.   .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,3]     .D=eE----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER  .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,5]     . D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4952,19 +5034,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,1]     D=eE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,5]     . D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE--R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eE-R   stg	x26, [x27], #4064
-# CHECK-NEXT: [0,9]     .   D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eE-R   stg	x26, [x27], #4064
+# CHECK-NEXT: [0,9]     .   DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4998,18 +5081,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   stg	x26, [x27, #4064]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   stgp	x1, x2, [x27], #992
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   stgp	x1, x2, [x27, #992]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   stp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   stp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   stgp	x1, x2, [x27], #992
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   stgp	x1, x2, [x27, #992]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   stp	s1, s2, [x27], #248
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   stp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5043,19 +5127,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   stp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D==eER    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D==eeER   .   stp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D===eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeER  .   stp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D===eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeER .   stp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,7]     . D====eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D====eER.   stp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     . D=====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPPeER    .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPeeER   .   stp	s1, s2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPPeER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPeeER  .   stp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPeeER .   stp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,7]     . DPPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPeER.   stp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     . DPPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5089,18 +5174,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   stp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   stp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   stp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   str	b1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   str	h1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   stp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   stp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   str	b1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   str	h1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5134,18 +5220,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   str	s1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   str	d1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   str	q1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   str	b1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   str	h1, [x27, #254]!
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   str	d1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   str	q1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   str	b1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   str	h1, [x27, #254]!
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5179,18 +5266,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   str	s1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   str	d1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   str	q1, [x27, #254]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eER .   str	w1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   str	x1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   str	d1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   str	q1, [x27, #254]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeER .   str	w1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   str	x1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5224,18 +5312,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   str	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   str	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   strb	w1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eER .   strb	w1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   strh	w1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   str	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   strb	w1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeER .   strb	w1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   strh	w1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5269,18 +5358,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   strh	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   stz2g	x26, [x27], #4064
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   stz2g	x26, [x27, #4064]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eER .   stzg	x26, [x27], #4064
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   stzg	x26, [x27, #4064]!
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   stz2g	x26, [x27], #4064
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   stz2g	x26, [x27, #4064]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeER .   stzg	x26, [x27], #4064
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   stzg	x26, [x27, #4064]!
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5314,13 +5404,14 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D====eeeeER   ldr	x2, [x1], #254
-# CHECK-NEXT: [0,3]     D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPeeeeER   ldr	x2, [x1], #254
+# CHECK-NEXT: [0,3]     DPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/N3-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/N3-writeback.s
index 46bea36d38eb8..3887d2659f595 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/N3-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/N3-writeback.s
@@ -1191,19 +1191,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.2s }, [x27], #8
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1237,19 +1238,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.16b }, [x27], #16
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1283,19 +1285,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1329,19 +1332,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1375,19 +1379,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1421,19 +1426,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1467,19 +1473,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1513,19 +1520,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1559,19 +1567,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1605,19 +1614,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .  .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeER.   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,7]     . D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,9]     . D===eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER.  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeER.   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,7]     . DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,9]     . DPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1651,19 +1661,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   .   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE-----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER   .   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eE-----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER  .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,5]     . D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeeeeeER.   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D==eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,9]     .   DPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1697,19 +1708,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eE-----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER   .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER  .   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE-----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeeeeeER.   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1743,19 +1755,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    ..   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER    .    ..   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeER   .    ..   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE-----R   .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-----R   .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeeeeeER .    ..   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE-----R .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D========eeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,9]     .  D=========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeE-----R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPPPPPPPPeeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,9]     .  DPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1789,19 +1802,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1835,19 +1849,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.s }[0], [x27], #4
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1881,19 +1896,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER .   ld1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeE-R .   ld1r	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,3]     D==eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1r	{ v1.2d }, [x27], #8
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1r	{ v1.2s }, [x27], #4
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1r	{ v1.4h }, [x27], #2
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeE-R .   ld1r	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1r	{ v1.4h }, [x27], #2
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1927,19 +1943,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1r	{ v1.4s }, [x27], #4
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1r	{ v1.8b }, [x27], #1
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1r	{ v1.8h }, [x27], #2
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1r	{ v1.16b }, [x27], #1
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1r	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1r	{ v1.8b }, [x27], #1
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1r	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1973,19 +1990,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1r	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1r	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1r	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1r	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1r	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1r	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1r	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2019,19 +2037,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   ld1r	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.   .   ld1r	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER.   .   ld1r	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2065,19 +2084,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2111,19 +2131,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2157,19 +2178,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2203,19 +2225,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2249,19 +2272,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    ..   ld2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    ..   ld2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,3]     D=========eE------R .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   ld2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D================eE------R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D================eeeeeeE-R   ld2r	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,7]     .D=================eE-----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D================eeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     . D=================eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    ..   ld2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPeeeeeeE-R   ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPeE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2295,19 +2319,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld2r	{ v1.2s, v2.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld2r	{ v1.4h, v2.4h }, [x27], #4
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld2r	{ v1.4h, v2.4h }, [x27], #4
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2341,19 +2366,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld2r	{ v1.16b, v2.16b }, [x27], #2
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld2r	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld2r	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2387,19 +2413,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   ld2r	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.    ..   ld2r	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R.    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER    ..   ld2r	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER   ..   ld2r	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R   ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,9]     . D===eE--------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER.    ..   ld2r	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R.    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER    ..   ld2r	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER   ..   ld2r	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,9]     . DPPPeE--------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2433,19 +2460,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .  .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   .  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE------R   .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeeeER  .   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,5]     . D==eE--------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeE-R  .   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,7]     .  D==eE-------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,9]     .   D===eE--------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeE-R  .   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,7]     .  DPPeE-------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,9]     .   DPPPeE--------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2479,19 +2507,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeeER  .  .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE--------R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--------R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeeER .  .   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE--------R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--------R .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER .  .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE------R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER.  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eE------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eE--------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER.  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeE------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeE--------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2525,19 +2554,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    ..   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeeER .    .    .    ..   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE--------R .    .    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--------R .    .    .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeeeER    .    .    ..   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE--------R    .    .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==========eeeeeeeeER .    ..   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,7]     .  D===========eE------R .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=================eeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,9]     .   D==================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--------R    .    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPeeeeeeeeER .    ..   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPeE------R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2571,19 +2601,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2617,19 +2648,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2663,19 +2695,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2709,19 +2742,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], #3
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2755,19 +2789,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2801,19 +2836,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeeER  ..   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,5]     . D=eE------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE------R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D==eeeeeeeeER.   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2847,19 +2883,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .  .   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   .  .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE------R   .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeeeER.  .   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,5]     . D===eE------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeeER  .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D===eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D====eeeeeeeeER   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeeeER  .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP==eeeeeeeeER   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2893,19 +2930,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .  .   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   .  .   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R   .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeeeER.  .   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeeER  .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D===eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D====eeeeeeeeER   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeeeER  .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP==eeeeeeeeER   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2939,19 +2977,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2985,19 +3024,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3031,19 +3071,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D=======eeeeeeeeER.  .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,5]     . D========eE------R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=========eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D==========eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=========eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
-# CHECK-NEXT: [0,9]     .   D==========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .  .   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPeeeeeeeeER.  .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,5]     . DPPPPPPPPeE------R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPP==eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPeeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3077,19 +3118,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   ..   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE------R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER ..   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #4
-# CHECK-NEXT: [0,5]     . D==eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeeeER..   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
-# CHECK-NEXT: [0,7]     .  D==eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
-# CHECK-NEXT: [0,9]     .   D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeeeER..   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
+# CHECK-NEXT: [0,7]     .  DPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
+# CHECK-NEXT: [0,9]     .   DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3123,19 +3165,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    . .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER   . .   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R   . .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R   . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeeeeeeeER. .   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE------R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeeeeeeeER .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D===eeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeE------R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeeeeeeeER .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPP=eeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3169,19 +3212,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER  .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER .   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D==eE------R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeeeE-R   ldp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,7]     .  D==eE-----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeeER   ldp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,9]     .   D==eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeeeE-R   ldp	s1, s2, [x27], #248
+# CHECK-NEXT: [0,7]     .  DPPeE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeeeeeER   ldp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,9]     .   DPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3215,19 +3259,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D=eE----R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER..   ldp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     .D=eE----R..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeER.   ldp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     . D=eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeER   ldp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,7]     .  D=eE----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D=eeeeE-R   ldp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     .  D==eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPeeeeE-R   ldp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     .  DPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3261,19 +3306,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldpsw	x1, x2, [x27], #248
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldpsw	x1, x2, [x27, #248]!
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldpsw	x1, x2, [x27], #248
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldpsw	x1, x2, [x27, #248]!
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3307,19 +3353,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ldr	b1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ldr	h1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ldr	s1, [x27], #254
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ldr	d1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ldr	q1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ldr	h1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ldr	s1, [x27], #254
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ldr	d1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ldr	q1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3353,19 +3400,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ldr	b1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ldr	h1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ldr	s1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ldr	d1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ldr	q1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ldr	h1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ldr	s1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ldr	d1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ldr	q1, [x27, #254]!
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3399,19 +3447,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	w1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldr	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldr	x1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrb	w1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldr	x1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldr	w1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldr	x1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrb	w1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3445,19 +3494,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldrh	w1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldrh	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldrsb	w1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrsb	x1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldrh	w1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldrh	w1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldrsb	w1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrsb	x1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3491,19 +3541,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrsb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldrsb	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldrsh	w1, [x27], #254
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   ldrsh	x1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   ldrsh	w1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldrsb	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldrsh	w1, [x27], #254
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   ldrsh	x1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   ldrsh	w1, [x27, #254]!
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3537,18 +3588,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   ldrsh	x1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER.   ldrsw	x1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER   ldrsw	x1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeE-R   st1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eE-R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER.   ldrsw	x1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER   ldrsw	x1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeE-R   st1	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3582,18 +3634,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.8b }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3627,18 +3680,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3672,18 +3726,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3717,18 +3772,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3762,18 +3818,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3807,18 +3864,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3852,18 +3910,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3897,18 +3956,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3942,18 +4002,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3987,18 +4048,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4032,18 +4094,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4077,18 +4140,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4122,18 +4186,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeER.   st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,7]     . D==eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeER.   st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: [0,7]     . DPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4167,18 +4232,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.h }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4212,18 +4278,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4257,18 +4324,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st2	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4302,18 +4370,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4347,18 +4416,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st2	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4392,18 +4462,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4437,18 +4508,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   st2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   st2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   st2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4482,19 +4554,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    ..   st2g	x26, [x27], #4064
-# CHECK-NEXT: [0,1]     D=eER.    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.    ..   st2g	x26, [x27, #4064]!
-# CHECK-NEXT: [0,3]     D==eER    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER   ..   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,5]     .D==eER   ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeER..   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,7]     . D==eE--R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D==eeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,9]     .  D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.    ..   st2g	x26, [x27, #4064]!
+# CHECK-NEXT: [0,3]     DPPeER    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER   ..   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,5]     .DPPeER   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeER..   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,7]     . DPPeE--R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DP=eeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,9]     .  DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4528,19 +4601,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,3]     .D=eE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeER.   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,5]     . D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeeeER   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,7]     .  D==eE--R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeeeER   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,7]     .  DPPeE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DP=eeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4574,19 +4648,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   st3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  ..   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeER ..   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE--R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE--R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeER..   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE--R..   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE--R..   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   D=eeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4620,18 +4695,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeE-R  .   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,3]     .D=eE-R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeER .   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,5]     . D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=eeER.   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D==eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPeeER.   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4665,18 +4741,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4710,19 +4787,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   st3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER    .   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,3]     .D=eER    .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER   .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D=eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER   .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER  .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,7]     .  D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,9]     .   D=eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4756,19 +4834,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE--R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  ..   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeER ..   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,5]     . D=eE--R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE--R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  D=eeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,7]     .  D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D==eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,9]     .   DPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4802,19 +4881,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  .   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeER .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE--R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeER.   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE--R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4848,19 +4928,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeER  .   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D==eeER .   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,5]     . D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D==eeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,7]     .  D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D==eeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,7]     .  DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4894,18 +4975,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4939,18 +5021,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER  .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeER .   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,5]     . D=eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D=eER.   stg	x26, [x27], #4064
-# CHECK-NEXT: [0,9]     .  D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPeER.   stg	x26, [x27], #4064
+# CHECK-NEXT: [0,9]     .  DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4984,18 +5067,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   stg	x26, [x27, #4064]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   stgp	x1, x2, [x27], #992
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   stgp	x1, x2, [x27, #992]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   stp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   stp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   stgp	x1, x2, [x27], #992
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   stgp	x1, x2, [x27, #992]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   stp	s1, s2, [x27], #248
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   stp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5029,18 +5113,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   stp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   stp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   stp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   stp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   stp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   stp	s1, s2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   stp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   stp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   stp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5074,18 +5159,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   stp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   stp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   stp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   str	b1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeER   str	h1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   stp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   stp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   str	b1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeER   str	h1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5119,18 +5205,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   str	s1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER   .   str	d1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER  .   str	q1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeER.   str	b1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eE-R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeER   str	h1, [x27, #254]!
-# CHECK-NEXT: [0,9]     . D===eE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER   .   str	d1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER  .   str	q1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeER.   str	b1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeE-R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeER   str	h1, [x27, #254]!
+# CHECK-NEXT: [0,9]     . DPPPeE-R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5164,18 +5251,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeER  .   str	s1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE-R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeER .   str	d1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE-R .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER .   str	q1, [x27, #254]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eER .   str	w1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   str	x1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeER .   str	d1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE-R .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER .   str	q1, [x27, #254]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeER .   str	w1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   str	x1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5209,18 +5297,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   str	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   str	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   strb	w1, [x27], #254
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eER .   strb	w1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   strh	w1, [x27], #254
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   str	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   strb	w1, [x27], #254
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeER .   strb	w1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   strh	w1, [x27], #254
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5254,18 +5343,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   strh	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   stz2g	x26, [x27], #4064
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eER  .   stz2g	x26, [x27, #4064]!
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eER .   stzg	x26, [x27], #4064
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eER.   stzg	x26, [x27, #4064]!
-# CHECK-NEXT: [0,9]     . D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   stz2g	x26, [x27], #4064
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeER  .   stz2g	x26, [x27, #4064]!
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeER .   stzg	x26, [x27], #4064
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeER.   stzg	x26, [x27, #4064]!
+# CHECK-NEXT: [0,9]     . DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5299,13 +5389,14 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D====eeeeER   ldr	x2, [x1], #254
-# CHECK-NEXT: [0,3]     D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPeeeeER   ldr	x2, [x1], #254
+# CHECK-NEXT: [0,3]     DPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-clear-upper-regs.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-clear-upper-regs.s
index 37ae765148396..b6e0f291cfa8a 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-clear-upper-regs.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-clear-upper-regs.s
@@ -105,16 +105,17 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.22   0.22   0.28   0.28    -      -      -      -     add	x0, x0, x0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   ldr	w0, [sp]
-# CHECK-NEXT: [0,1]     D====eER.   add	x0, x0, x0
+# CHECK-NEXT: [0,1]     DPPPPeER.   add	x0, x0, x0
 # CHECK-NEXT: [1,0]     DeeeeE-R.   ldr	w0, [sp]
-# CHECK-NEXT: [1,1]     D====eER.   add	x0, x0, x0
+# CHECK-NEXT: [1,1]     DPPPPeER.   add	x0, x0, x0
 # CHECK-NEXT: [2,0]     DeeeeE-R.   ldr	w0, [sp]
-# CHECK-NEXT: [2,1]     D====eER.   add	x0, x0, x0
+# CHECK-NEXT: [2,1]     DPPPPeER.   add	x0, x0, x0
 # CHECK-NEXT: [3,0]     D=eeeeER.   ldr	w0, [sp]
-# CHECK-NEXT: [3,1]     D=====eER   add	x0, x0, x0
+# CHECK-NEXT: [3,1]     DPPPPPeER   add	x0, x0, x0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -181,17 +182,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fadd	d0, d0, d0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldr	b0, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ldr	b0, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ldr	b0, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ldr	b0, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   fadd	d0, d0, d0
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   fadd	d0, d0, d0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -258,17 +260,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fadd	d0, d0, d0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldr	h0, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ldr	h0, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ldr	h0, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ldr	h0, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   fadd	d0, d0, d0
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   fadd	d0, d0, d0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -335,17 +338,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fadd	d0, d0, d0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldr	s0, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ldr	s0, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ldr	s0, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   fadd	d0, d0, d0
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   fadd	d0, d0, d0
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ldr	s0, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   fadd	d0, d0, d0
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   fadd	d0, d0, d0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -412,17 +416,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	v0.16b, v0.16b, v0.16b
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ld1	{ v0.8b }, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ld1	{ v0.8b }, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ld1	{ v0.8b }, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ld1	{ v0.8b }, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	v0.16b, v0.16b, v0.16b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -489,17 +494,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	v0.8h, v0.8h, v0.8h
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ld1	{ v0.4h }, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	v0.8h, v0.8h, v0.8h
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	v0.8h, v0.8h, v0.8h
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ld1	{ v0.4h }, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	v0.8h, v0.8h, v0.8h
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	v0.8h, v0.8h, v0.8h
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ld1	{ v0.4h }, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	v0.8h, v0.8h, v0.8h
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	v0.8h, v0.8h, v0.8h
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ld1	{ v0.4h }, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	v0.8h, v0.8h, v0.8h
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	v0.8h, v0.8h, v0.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -566,17 +572,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	v0.4s, v0.4s, v0.4s
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ld1	{ v0.2s }, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ld1	{ v0.2s }, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ld1	{ v0.2s }, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ld1	{ v0.2s }, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	v0.4s, v0.4s, v0.4s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -643,17 +650,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	v0.2d, v0.2d, v0.2d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ld1	{ v0.1d }, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ld1	{ v0.1d }, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ld1	{ v0.1d }, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ld1	{ v0.1d }, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	v0.2d, v0.2d, v0.2d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -720,17 +728,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     add	v0.16b, v0.16b, v0.16b
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .    .  .   mov	v0.b[0], v1.b[1]
-# CHECK-NEXT: [0,1]     D==eeER   .    .  .   add	v0.16b, v0.16b, v0.16b
-# CHECK-NEXT: [1,0]     D====eeER .    .  .   mov	v0.b[0], v1.b[1]
-# CHECK-NEXT: [1,1]     D======eeER    .  .   add	v0.16b, v0.16b, v0.16b
-# CHECK-NEXT: [2,0]     D========eeER  .  .   mov	v0.b[0], v1.b[1]
-# CHECK-NEXT: [2,1]     D==========eeER.  .   add	v0.16b, v0.16b, v0.16b
-# CHECK-NEXT: [3,0]     D============eeER .   mov	v0.b[0], v1.b[1]
-# CHECK-NEXT: [3,1]     D==============eeER   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [0,1]     DPPeeER   .    .  .   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [1,0]     DPPPPeeER .    .  .   mov	v0.b[0], v1.b[1]
+# CHECK-NEXT: [1,1]     DPPPPPPeeER    .  .   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [2,0]     DPPPPPPPPeeER  .  .   mov	v0.b[0], v1.b[1]
+# CHECK-NEXT: [2,1]     DPPPPPPPPPPeeER.  .   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [3,0]     DPPPPPPPPPPPPeeER .   mov	v0.b[0], v1.b[1]
+# CHECK-NEXT: [3,1]     DPPPPPPPPPPPPPPeeER   add	v0.16b, v0.16b, v0.16b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -797,17 +806,18 @@ add v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     add	v0.16b, v0.16b, v0.16b
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v0.b }[0], [sp]
-# CHECK-NEXT: [0,1]     D========eeER  .    .    .    .    .    . .   add	v0.16b, v0.16b, v0.16b
-# CHECK-NEXT: [1,0]     D==========eeeeeeeeER    .    .    .    . .   ld1	{ v0.b }[0], [sp]
-# CHECK-NEXT: [1,1]     D==================eeER  .    .    .    . .   add	v0.16b, v0.16b, v0.16b
-# CHECK-NEXT: [2,0]     D====================eeeeeeeeER    .    . .   ld1	{ v0.b }[0], [sp]
-# CHECK-NEXT: [2,1]     D============================eeER  .    . .   add	v0.16b, v0.16b, v0.16b
-# CHECK-NEXT: [3,0]     D==============================eeeeeeeeER .   ld1	{ v0.b }[0], [sp]
-# CHECK-NEXT: [3,1]     D======================================eeER   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeER  .    .    .    .    .    . .   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPeeeeeeeeER    .    .    .    . .   ld1	{ v0.b }[0], [sp]
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeER  .    .    .    . .   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [2,0]     DPPPPPPPPPPPPPPPPPPPPeeeeeeeeER    .    . .   ld1	{ v0.b }[0], [sp]
+# CHECK-NEXT: [2,1]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER  .    . .   add	v0.16b, v0.16b, v0.16b
+# CHECK-NEXT: [3,0]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER .   ld1	{ v0.b }[0], [sp]
+# CHECK-NEXT: [3,1]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER   add	v0.16b, v0.16b, v0.16b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s
index a720a6bde305b..02397d9071df1 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s
@@ -244,17 +244,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .    ..   mul	x0, x0, x0
-# CHECK-NEXT: [0,1]     D==eeER   .    ..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [0,2]     D===eeER  .    ..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [0,3]     D=====eeER.    ..   madd	x0, x0, x0, x0
-# CHECK-NEXT: [1,0]     D=======eeER   ..   mul	x0, x0, x0
-# CHECK-NEXT: [1,1]     D=========eeER ..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [1,2]     D==========eeER..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [1,3]     D============eeER   madd	x0, x0, x0, x0
+# CHECK-NEXT: [0,1]     DPPeeER   .    ..   madd	x0, x1, x2, x0
+# CHECK-NEXT: [0,2]     DPPPeeER  .    ..   madd	x0, x1, x2, x0
+# CHECK-NEXT: [0,3]     DPPPPPeeER.    ..   madd	x0, x0, x0, x0
+# CHECK-NEXT: [1,0]     DPPPPPPPeeER   ..   mul	x0, x0, x0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPeeER ..   madd	x0, x1, x2, x0
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPeeER..   madd	x0, x1, x2, x0
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPeeER   madd	x0, x0, x0, x0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -282,17 +283,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .    ..   mul	x0, x0, x0
-# CHECK-NEXT: [0,1]     D==eeER   .    ..   smaddl	x0, w1, w2, x0
-# CHECK-NEXT: [0,2]     D===eeER  .    ..   smaddl	x0, w1, w2, x0
-# CHECK-NEXT: [0,3]     D=====eeER.    ..   smaddl	x0, w0, w0, x0
-# CHECK-NEXT: [1,0]     D=======eeER   ..   mul	x0, x0, x0
-# CHECK-NEXT: [1,1]     D=========eeER ..   smaddl	x0, w1, w2, x0
-# CHECK-NEXT: [1,2]     D==========eeER..   smaddl	x0, w1, w2, x0
-# CHECK-NEXT: [1,3]     D============eeER   smaddl	x0, w0, w0, x0
+# CHECK-NEXT: [0,1]     DPPeeER   .    ..   smaddl	x0, w1, w2, x0
+# CHECK-NEXT: [0,2]     DPPPeeER  .    ..   smaddl	x0, w1, w2, x0
+# CHECK-NEXT: [0,3]     DPPPPPeeER.    ..   smaddl	x0, w0, w0, x0
+# CHECK-NEXT: [1,0]     DPPPPPPPeeER   ..   mul	x0, x0, x0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPeeER ..   smaddl	x0, w1, w2, x0
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPeeER..   smaddl	x0, w1, w2, x0
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPeeER   smaddl	x0, w0, w0, x0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -320,21 +322,22 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeER.    .    .    .    .    .    ..   fadd	d0, d0, d0
-# CHECK-NEXT: [0,1]     D==eeeeER .    .    .    .    .    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    .    .    ..   fmul	d0, d0, d0
-# CHECK-NEXT: [0,3]     D=======eeeeER .    .    .    .    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [0,4]     D=========eeeeER    .    .    .    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [0,5]     D=============eeeeER.    .    .    ..   fmadd	d0, d0, d1, d2
-# CHECK-NEXT: [1,0]     D=================eeER   .    .    ..   fadd	d0, d0, d0
-# CHECK-NEXT: [1,1]     D===================eeeeER    .    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [1,2]     D=======================eeeER .    ..   fmul	d0, d0, d0
-# CHECK-NEXT: [1,3]     D========================eeeeER    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [1,4]     D==========================eeeeER  ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [1,5]     D==============================eeeeER   fmadd	d0, d0, d1, d2
+# CHECK-NEXT: [0,1]     DPPeeeeER .    .    .    .    .    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    .    .    ..   fmul	d0, d0, d0
+# CHECK-NEXT: [0,3]     DPPPPPPPeeeeER .    .    .    .    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [0,4]     DPPPPPPPPPeeeeER    .    .    .    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPeeeeER.    .    .    ..   fmadd	d0, d0, d1, d2
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPeeER   .    .    ..   fadd	d0, d0, d0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPeeeER .    ..   fmul	d0, d0, d0
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [1,4]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER  ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [1,5]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmadd	d0, d0, d1, d2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -364,17 +367,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   saba	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   saba	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   saba	v0.4s, v0.4s, v1.4s
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   saba	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   saba	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,3]     D======================eeeeER   saba	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   saba	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   saba	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   saba	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   saba	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   saba	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   saba	v0.4s, v0.4s, v1.4s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -402,17 +406,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   sadalp	v0.2d, v1.4s
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   sadalp	v0.2d, v1.4s
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   sadalp	v0.2d, v0.4s
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   sadalp	v0.2d, v1.4s
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   sadalp	v0.2d, v1.4s
-# CHECK-NEXT: [1,3]     D======================eeeeER   sadalp	v0.2d, v0.4s
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   sadalp	v0.2d, v1.4s
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   sadalp	v0.2d, v1.4s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   sadalp	v0.2d, v0.4s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   sadalp	v0.2d, v1.4s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   sadalp	v0.2d, v1.4s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   sadalp	v0.2d, v0.4s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -440,17 +445,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 0.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
 # CHECK:      [0,0]     DeeeeER   .    .    .   .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeER.    .    .   .   sdot	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [0,2]     D=====eeeER    .    .   .   sdot	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [0,3]     D========eeeER .    .   .   sdot	v0.4s, v0.16b, v1.16b
-# CHECK-NEXT: [1,0]     D===========eeeeER  .   .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D===============eeeER   .   sdot	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [1,2]     D================eeeER  .   sdot	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [1,3]     D===================eeeER   sdot	v0.4s, v0.16b, v1.16b
+# CHECK-NEXT: [0,1]     DPPPPeeeER.    .    .   .   sdot	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [0,2]     DPPPPPeeeER    .    .   .   sdot	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .   .   sdot	v0.4s, v0.16b, v1.16b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPeeeeER  .   .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPeeeER   .   sdot	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPeeeER  .   sdot	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPeeeER   sdot	v0.4s, v0.16b, v1.16b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -478,17 +484,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 0.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
 # CHECK:      [0,0]     DeeeeER   .    .    .   .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeER.    .    .   .   smmla	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [0,2]     D=====eeeER    .    .   .   smmla	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [0,3]     D========eeeER .    .   .   smmla	v0.4s, v0.16b, v1.16b
-# CHECK-NEXT: [1,0]     D===========eeeeER  .   .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D===============eeeER   .   smmla	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [1,2]     D================eeeER  .   smmla	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [1,3]     D===================eeeER   smmla	v0.4s, v0.16b, v1.16b
+# CHECK-NEXT: [0,1]     DPPPPeeeER.    .    .   .   smmla	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [0,2]     DPPPPPeeeER    .    .   .   smmla	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .   .   smmla	v0.4s, v0.16b, v1.16b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPeeeeER  .   .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPeeeER   .   smmla	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPeeeER  .   smmla	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPeeeER   smmla	v0.4s, v0.16b, v1.16b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -516,17 +523,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   mla	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   mla	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   mla	v0.4s, v0.4s, v1.4s
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   mla	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   mla	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,3]     D======================eeeeER   mla	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   mla	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   mla	v0.4s, v0.4s, v1.4s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -554,17 +562,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   smlal2	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   smlal2	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   smlal2	v0.4s, v0.8h, v1.8h
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   smlal2	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   smlal2	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,3]     D======================eeeeER   smlal2	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   smlal2	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   smlal2	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   smlal2	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   smlal2	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   smlal2	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   smlal2	v0.4s, v0.8h, v1.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -592,17 +601,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   ssra	v0.2d, v1.2d, #1
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   ssra	v0.2d, v1.2d, #1
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   ssra	v0.2d, v0.2d, #1
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   ssra	v0.2d, v1.2d, #1
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   ssra	v0.2d, v1.2d, #1
-# CHECK-NEXT: [1,3]     D======================eeeeER   ssra	v0.2d, v0.2d, #1
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   ssra	v0.2d, v1.2d, #1
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   ssra	v0.2d, v1.2d, #1
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   ssra	v0.2d, v0.2d, #1
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   ssra	v0.2d, v1.2d, #1
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   ssra	v0.2d, v1.2d, #1
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   ssra	v0.2d, v0.2d, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -630,17 +640,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   fcmla	v0.2d, v0.2d, v1.2d, #90
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   fcmla	v0.2d, v1.2d, v2.2d, #90
-# CHECK-NEXT: [1,3]     D======================eeeeER   fcmla	v0.2d, v0.2d, v1.2d, #90
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   fcmla	v0.2d, v0.2d, v1.2d, #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   fcmla	v0.2d, v1.2d, v2.2d, #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   fcmla	v0.2d, v0.2d, v1.2d, #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -668,21 +679,22 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    ..   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D=eeeeER  .    .    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [0,2]     D=====eeER.    .    .    .    .    ..   fadd	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,3]     D=======eeeeER .    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [0,4]     D=========eeeeER    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [0,5]     D=============eeeeER.    .    .    ..   fmla	v0.2d, v0.2d, v1.2d
-# CHECK-NEXT: [1,0]     D=================eeeER  .    .    ..   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D==================eeeeER.    .    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [1,2]     D======================eeER   .    ..   fadd	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,3]     D========================eeeeER    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [1,4]     D==========================eeeeER  ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [1,5]     D==============================eeeeER   fmla	v0.2d, v0.2d, v1.2d
+# CHECK-NEXT: [0,1]     DPeeeeER  .    .    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [0,2]     DPPPPPeeER.    .    .    .    .    ..   fadd	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [0,3]     DPPPPPPPeeeeER .    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [0,4]     DPPPPPPPPPeeeeER    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPeeeeER.    .    .    ..   fmla	v0.2d, v0.2d, v1.2d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPeeeER  .    .    ..   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeER.    .    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPeeER   .    ..   fadd	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [1,4]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER  ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [1,5]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmla	v0.2d, v0.2d, v1.2d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -712,21 +724,22 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    .    .    ..   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    .    .    .    ..   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [0,2]     D========eeER  .    .    .    .    .    .    ..   fadd	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,3]     D==========eeeeeER  .    .    .    .    .    ..   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [0,4]     D============eeeeeER.    .    .    .    .    ..   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [0,5]     D=================eeeeeER.    .    .    .    ..   fmlal	v0.4s, v0.4h, v1.4h
-# CHECK-NEXT: [1,0]     D======================eeeER  .    .    .    ..   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D=========================eeeeeER  .    .    ..   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [1,2]     D==============================eeER.    .    ..   fadd	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,3]     D================================eeeeeER.    ..   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [1,4]     D==================================eeeeeER   ..   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [1,5]     D=======================================eeeeeER   fmlal	v0.4s, v0.4h, v1.4h
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    .    .    .    ..   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeER  .    .    .    .    .    .    ..   fadd	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeeER  .    .    .    .    .    ..   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPPeeeeeER.    .    .    .    .    ..   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPPPPPeeeeeER.    .    .    .    ..   fmlal	v0.4s, v0.4h, v1.4h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPPPPPPeeeER  .    .    .    ..   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    ..   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER.    .    ..   fadd	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER.    ..   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [1,4]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   ..   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [1,5]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   fmlal	v0.4s, v0.4h, v1.4h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -756,17 +769,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   bfdot	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   bfdot	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   bfdot	v0.4s, v0.8h, v1.8h
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   bfdot	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   bfdot	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,3]     D======================eeeeER   bfdot	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   bfdot	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   bfdot	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   bfdot	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   bfdot	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   bfdot	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   bfdot	v0.4s, v0.8h, v1.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -794,17 +808,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .   .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    .   .   bfmmla	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,2]     D======eeeeeER .    .    .    .   .   bfmmla	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,3]     D===========eeeeeER .    .    .   .   bfmmla	v0.4s, v0.8h, v1.8h
-# CHECK-NEXT: [1,0]     D================eeeER   .    .   .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D===================eeeeeER   .   .   bfmmla	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,2]     D======================eeeeeER.   .   bfmmla	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,3]     D===========================eeeeeER   bfmmla	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    .   .   bfmmla	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeeER .    .    .    .   .   bfmmla	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPeeeeeER .    .    .   .   bfmmla	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPeeeER   .    .   .   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeeER   .   .   bfmmla	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeER.   .   bfmmla	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   bfmmla	v0.4s, v0.8h, v1.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -832,17 +847,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   bfmlalb	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   bfmlalb	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   bfmlalb	v0.4s, v0.8h, v1.8h
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   bfmlalb	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   bfmlalb	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,3]     D======================eeeeER   bfmlalb	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   bfmlalb	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   bfmlalb	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   bfmlalb	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   bfmlalb	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   bfmlalb	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   bfmlalb	v0.4s, v0.8h, v1.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -870,31 +886,32 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeER.    .    .    .    .    .   mul	w0, w0, w0
-# CHECK-NEXT: [0,1]     D==eeER   .    .    .    .    .   crc32cb	w0, w0, w1
-# CHECK-NEXT: [0,2]     D===eeER  .    .    .    .    .   crc32cb	w0, w0, w1
-# CHECK-NEXT: [0,3]     D=====eeER.    .    .    .    .   crc32cb	w0, w0, w0
-# CHECK-NEXT: [0,4]     D======eeER    .    .    .    .   crc32b	w0, w0, w15
-# CHECK-NEXT: [0,5]     D=======eeER   .    .    .    .   crc32h	w0, w0, w21
-# CHECK-NEXT: [0,6]     D========eeER  .    .    .    .   crc32w	w0, w0, w24
-# CHECK-NEXT: [0,7]     D=========eeER .    .    .    .   crc32x	w0, w0, x25
-# CHECK-NEXT: [0,8]     D==========eeER.    .    .    .   crc32ch	w0, w0, w16
-# CHECK-NEXT: [0,9]     D===========eeER    .    .    .   crc32cw	w0, w0, w23
-# CHECK-NEXT: [0,10]    D============eeER   .    .    .   crc32cx	w0, w0, x5
-# CHECK-NEXT: [1,0]     D==============eeER .    .    .   mul	w0, w0, w0
-# CHECK-NEXT: [1,1]     D================eeER    .    .   crc32cb	w0, w0, w1
-# CHECK-NEXT: [1,2]     D=================eeER   .    .   crc32cb	w0, w0, w1
-# CHECK-NEXT: [1,3]     D===================eeER .    .   crc32cb	w0, w0, w0
-# CHECK-NEXT: [1,4]     .D===================eeER.    .   crc32b	w0, w0, w15
-# CHECK-NEXT: [1,5]     .D====================eeER    .   crc32h	w0, w0, w21
-# CHECK-NEXT: [1,6]     .D=====================eeER   .   crc32w	w0, w0, w24
-# CHECK-NEXT: [1,7]     .D======================eeER  .   crc32x	w0, w0, x25
-# CHECK-NEXT: [1,8]     .D=======================eeER .   crc32ch	w0, w0, w16
-# CHECK-NEXT: [1,9]     .D========================eeER.   crc32cw	w0, w0, w23
-# CHECK-NEXT: [1,10]    .D=========================eeER   crc32cx	w0, w0, x5
+# CHECK-NEXT: [0,1]     DPPeeER   .    .    .    .    .   crc32cb	w0, w0, w1
+# CHECK-NEXT: [0,2]     DPPPeeER  .    .    .    .    .   crc32cb	w0, w0, w1
+# CHECK-NEXT: [0,3]     DPPPPPeeER.    .    .    .    .   crc32cb	w0, w0, w0
+# CHECK-NEXT: [0,4]     DPPPPPPeeER    .    .    .    .   crc32b	w0, w0, w15
+# CHECK-NEXT: [0,5]     DPPPPPPPeeER   .    .    .    .   crc32h	w0, w0, w21
+# CHECK-NEXT: [0,6]     DPPPPPPPPeeER  .    .    .    .   crc32w	w0, w0, w24
+# CHECK-NEXT: [0,7]     DPPPPPPPPPeeER .    .    .    .   crc32x	w0, w0, x25
+# CHECK-NEXT: [0,8]     DPPPPPPPPPPeeER.    .    .    .   crc32ch	w0, w0, w16
+# CHECK-NEXT: [0,9]     DPPPPPPPPPPPeeER    .    .    .   crc32cw	w0, w0, w23
+# CHECK-NEXT: [0,10]    DPPPPPPPPPPPPeeER   .    .    .   crc32cx	w0, w0, x5
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeER .    .    .   mul	w0, w0, w0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeER    .    .   crc32cb	w0, w0, w1
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPeeER   .    .   crc32cb	w0, w0, w1
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPeeER .    .   crc32cb	w0, w0, w0
+# CHECK-NEXT: [1,4]     .DPPPPPPPPPPPPPPPPPPPeeER.    .   crc32b	w0, w0, w15
+# CHECK-NEXT: [1,5]     .DPPPPPPPPPPPPPPPPPPPPeeER    .   crc32h	w0, w0, w21
+# CHECK-NEXT: [1,6]     .DPPPPPPPPPPPPPPPPPPPPPeeER   .   crc32w	w0, w0, w24
+# CHECK-NEXT: [1,7]     .DPPPPPPPPPPPPPPPPPPPPPPeeER  .   crc32x	w0, w0, x25
+# CHECK-NEXT: [1,8]     .DPPPPPPPPPPPPPPPPPPPPPPPeeER .   crc32ch	w0, w0, w16
+# CHECK-NEXT: [1,9]     .DPPPPPPPPPPPPPPPPPPPPPPPPeeER.   crc32cw	w0, w0, w23
+# CHECK-NEXT: [1,10]    .DPPPPPPPPPPPPPPPPPPPPPPPPPeeER   crc32cx	w0, w0, x5
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -929,17 +946,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeER    .    .    ..   sdot	z0.s, z1.b, z2.b
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    ..   sdot	z0.s, z1.b, z2.b
-# CHECK-NEXT: [0,3]     D=========eeeER.    .    ..   sdot	z0.s, z0.b, z1.b
-# CHECK-NEXT: [1,0]     D============eeeeeER.    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=================eeeER  ..   sdot	z0.s, z1.b, z2.b
-# CHECK-NEXT: [1,2]     D==================eeeER ..   sdot	z0.s, z1.b, z2.b
-# CHECK-NEXT: [1,3]     D=====================eeeER   sdot	z0.s, z0.b, z1.b
+# CHECK-NEXT: [0,1]     DPPPPPeeeER    .    .    ..   sdot	z0.s, z1.b, z2.b
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    ..   sdot	z0.s, z1.b, z2.b
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeER.    .    ..   sdot	z0.s, z0.b, z1.b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPeeeeeER.    ..   mul	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeER  ..   sdot	z0.s, z1.b, z2.b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeER ..   sdot	z0.s, z1.b, z2.b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPeeeER   sdot	z0.s, z0.b, z1.b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -967,17 +985,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeER    .    .    ..   sdot	z0.s, z1.b, z2.b[1]
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    ..   sdot	z0.s, z1.b, z2.b[1]
-# CHECK-NEXT: [0,3]     D=========eeeER.    .    ..   sdot	z0.s, z0.b, z1.b[1]
-# CHECK-NEXT: [1,0]     D============eeeeeER.    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=================eeeER  ..   sdot	z0.s, z1.b, z2.b[1]
-# CHECK-NEXT: [1,2]     D==================eeeER ..   sdot	z0.s, z1.b, z2.b[1]
-# CHECK-NEXT: [1,3]     D=====================eeeER   sdot	z0.s, z0.b, z1.b[1]
+# CHECK-NEXT: [0,1]     DPPPPPeeeER    .    .    ..   sdot	z0.s, z1.b, z2.b[1]
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    ..   sdot	z0.s, z1.b, z2.b[1]
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeER.    .    ..   sdot	z0.s, z0.b, z1.b[1]
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPeeeeeER.    ..   mul	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeER  ..   sdot	z0.s, z1.b, z2.b[1]
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeER ..   sdot	z0.s, z1.b, z2.b[1]
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPeeeER   sdot	z0.s, z0.b, z1.b[1]
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1005,17 +1024,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   sdot	z0.d, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   sdot	z0.d, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   sdot	z0.d, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   sdot	z0.d, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   sdot	z0.d, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D========================eeeeER   sdot	z0.d, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   sdot	z0.d, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   sdot	z0.d, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   sdot	z0.d, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   sdot	z0.d, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   sdot	z0.d, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   sdot	z0.d, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1043,17 +1063,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeER    .    .    ..   smmla	z0.s, z1.b, z2.b
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    ..   smmla	z0.s, z1.b, z2.b
-# CHECK-NEXT: [0,3]     D=========eeeER.    .    ..   smmla	z0.s, z0.b, z1.b
-# CHECK-NEXT: [1,0]     D============eeeeeER.    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=================eeeER  ..   smmla	z0.s, z1.b, z2.b
-# CHECK-NEXT: [1,2]     D==================eeeER ..   smmla	z0.s, z1.b, z2.b
-# CHECK-NEXT: [1,3]     D=====================eeeER   smmla	z0.s, z0.b, z1.b
+# CHECK-NEXT: [0,1]     DPPPPPeeeER    .    .    ..   smmla	z0.s, z1.b, z2.b
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    ..   smmla	z0.s, z1.b, z2.b
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeER.    .    ..   smmla	z0.s, z0.b, z1.b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPeeeeeER.    ..   mul	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeER  ..   smmla	z0.s, z1.b, z2.b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeER ..   smmla	z0.s, z1.b, z2.b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPeeeER   smmla	z0.s, z0.b, z1.b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1081,17 +1102,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeeER  .    .    .    .    ..   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,2]     D=======eeeeeER.    .    .    .    ..   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,3]     D============eeeeeER.    .    .    ..   mla	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT: [1,0]     D=================eeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D======================eeeeeER.    ..   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,2]     D========================eeeeeER   ..   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     .D============================eeeeeER   mla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER  .    .    .    .    ..   mla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeeER.    .    .    .    ..   mla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPeeeeeER.    .    .    ..   mla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPeeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeER.    ..   mla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   ..   mla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,3]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   mla	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1119,17 +1141,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeeER  .    .    .    .    ..   mad	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,2]     D=======eeeeeER.    .    .    .    ..   mad	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,3]     D============eeeeeER.    .    .    ..   mad	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT: [1,0]     D=================eeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D======================eeeeeER.    ..   mad	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,2]     D========================eeeeeER   ..   mad	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     .D============================eeeeeER   mad	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER  .    .    .    .    ..   mad	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeeER.    .    .    .    ..   mad	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPeeeeeER.    .    .    ..   mad	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPeeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeER.    ..   mad	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   ..   mad	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,3]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   mad	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1157,17 +1180,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeeER  .    .    .    .    ..   msb	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,2]     D=======eeeeeER.    .    .    .    ..   msb	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,3]     D============eeeeeER.    .    .    ..   msb	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT: [1,0]     D=================eeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D======================eeeeeER.    ..   msb	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,2]     D========================eeeeeER   ..   msb	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     .D============================eeeeeER   msb	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER  .    .    .    .    ..   msb	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeeER.    .    .    .    ..   msb	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPeeeeeER.    .    .    ..   msb	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPeeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeER.    ..   msb	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   ..   msb	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,3]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   msb	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1195,17 +1219,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
-# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
-# CHECK-NEXT: [0,3]     D==========eeeeeER  .    .    . .   fcmla	z0.d, p0/m, z0.d, z1.d, #90
-# CHECK-NEXT: [1,0]     D===============eeeER    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D==================eeeeeER    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
-# CHECK-NEXT: [1,2]     D====================eeeeeER  . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
-# CHECK-NEXT: [1,3]     D=========================eeeeeER   fcmla	z0.d, p0/m, z0.d, z1.d, #90
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
+# CHECK-NEXT: [0,2]     DPPPPPeeeeeER  .    .    .    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeeER  .    .    . .   fcmla	z0.d, p0/m, z0.d, z1.d, #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeER    .    . .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeeER    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeeER  . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   fcmla	z0.d, p0/m, z0.d, z1.d, #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1233,17 +1258,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    . .   fcmla	z0.s, z1.s, z2.s[1], #90
-# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    . .   fcmla	z0.s, z1.s, z2.s[1], #90
-# CHECK-NEXT: [0,3]     D==========eeeeeER  .    .    . .   fcmla	z0.s, z0.s, z1.s[1], #90
-# CHECK-NEXT: [1,0]     D===============eeeER    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D==================eeeeeER    . .   fcmla	z0.s, z1.s, z2.s[1], #90
-# CHECK-NEXT: [1,2]     D====================eeeeeER  . .   fcmla	z0.s, z1.s, z2.s[1], #90
-# CHECK-NEXT: [1,3]     D=========================eeeeeER   fcmla	z0.s, z0.s, z1.s[1], #90
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    . .   fcmla	z0.s, z1.s, z2.s[1], #90
+# CHECK-NEXT: [0,2]     DPPPPPeeeeeER  .    .    .    . .   fcmla	z0.s, z1.s, z2.s[1], #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeeER  .    .    . .   fcmla	z0.s, z0.s, z1.s[1], #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeER    .    . .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeeER    . .   fcmla	z0.s, z1.s, z2.s[1], #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeeER  . .   fcmla	z0.s, z1.s, z2.s[1], #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   fcmla	z0.s, z0.s, z1.s[1], #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1271,17 +1297,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   fmla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   fmla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   fmla	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   fmla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   fmla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     D======================eeeeER   fmla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   fmla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   fmla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   fmla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   fmla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   fmla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmla	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1309,17 +1336,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   fmla	z0.d, z1.d, z2.d[1]
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   fmla	z0.d, z1.d, z2.d[1]
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   fmla	z0.d, z0.d, z1.d[1]
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   fmla	z0.d, z1.d, z2.d[1]
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   fmla	z0.d, z1.d, z2.d[1]
-# CHECK-NEXT: [1,3]     D======================eeeeER   fmla	z0.d, z0.d, z1.d[1]
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   fmla	z0.d, z1.d, z2.d[1]
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   fmla	z0.d, z1.d, z2.d[1]
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   fmla	z0.d, z0.d, z1.d[1]
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   fmla	z0.d, z1.d, z2.d[1]
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   fmla	z0.d, z1.d, z2.d[1]
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmla	z0.d, z0.d, z1.d[1]
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1347,17 +1375,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   bfdot	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   bfdot	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   bfdot	z0.s, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   bfdot	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   bfdot	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D======================eeeeER   bfdot	z0.s, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   bfdot	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   bfdot	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   bfdot	z0.s, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   bfdot	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   bfdot	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   bfdot	z0.s, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1385,17 +1414,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .   .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    .   .   bfmmla	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D======eeeeeER .    .    .    .   .   bfmmla	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D===========eeeeeER .    .    .   .   bfmmla	z0.s, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D================eeeER   .    .   .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeeER   .   .   bfmmla	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D======================eeeeeER.   .   bfmmla	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D===========================eeeeeER   bfmmla	z0.s, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    .   .   bfmmla	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeeER .    .    .    .   .   bfmmla	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPeeeeeER .    .    .   .   bfmmla	z0.s, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPeeeER   .    .   .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeeER   .   .   bfmmla	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeER.   .   bfmmla	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   bfmmla	z0.s, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1423,17 +1453,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    . .   bfmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    . .   bfmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D==========eeeeeER  .    .    . .   bfmlalb	z0.s, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D===============eeeER    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D==================eeeeeER    . .   bfmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D====================eeeeeER  . .   bfmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D=========================eeeeeER   bfmlalb	z0.s, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    . .   bfmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeeER  .    .    .    . .   bfmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeeER  .    .    . .   bfmlalb	z0.s, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeER    .    . .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeeER    . .   bfmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeeER  . .   bfmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   bfmlalb	z0.s, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s
index 264ad8bccc58e..a6fae77cd4f10 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s
@@ -1171,19 +1171,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.2s }, [x27], #8
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER.   ld1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,7]     DPPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     DPPPPeeeeeeER   ld1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,9]     DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1217,19 +1218,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.16b }, [x27], #16
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER.   ld1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     DPPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     DPPPPeeeeeeER   ld1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1263,19 +1265,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER.   ld1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     DPPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     DPPPPeeeeeeER   ld1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1309,19 +1312,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7]     DPPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1355,19 +1359,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1401,19 +1406,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1447,19 +1453,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1493,19 +1500,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1539,19 +1547,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1585,19 +1594,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .  .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,9]     .D====eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER.  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,9]     .DPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1631,19 +1641,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .  .   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE----R .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.  .   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,3]     D==eE----R.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeER .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,5]     D===eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,9]     .D====eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER.  .   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,3]     DPPeE----R.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeER .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,5]     DPPPeE-----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,9]     .DPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1677,19 +1688,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER. .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eE-----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeER.   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1723,19 +1735,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.    .    .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE----R.    .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeER   .    .   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE-----R   .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeER  .    .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE-----R  .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D=========eeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,9]     .D==========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER.    .    .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE----R.    .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeER   .    .   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE-----R   .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeER  .    .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE-----R  .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPPPPPPPeeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,9]     .DPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1769,19 +1782,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D========================eeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,9]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1815,19 +1829,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D========================eeeeeeeeER.    . .   ld1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.s }[0], [x27], #4
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1861,19 +1876,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld1r	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
-# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld1r	{ v1.4h }, [x27], #2
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld1r	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
+# CHECK-NEXT: [0,5]     DPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld1r	{ v1.4h }, [x27], #2
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1907,19 +1923,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.4s }, [x27], #4
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld1r	{ v1.8b }, [x27], #1
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
-# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld1r	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld1r	{ v1.8b }, [x27], #1
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
+# CHECK-NEXT: [0,5]     DPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld1r	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1953,19 +1970,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld1r	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld1r	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld1r	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld1r	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1999,19 +2017,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld1r	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld1r	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5]     DPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2045,19 +2064,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2091,19 +2111,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2137,19 +2158,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2183,19 +2205,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2229,19 +2252,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .  .   ld2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .  .   ld2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,3]     D=========eE------R .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D================eeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     D=================eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D================eeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,7]     .D=================eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D=================eeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     .D==================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .  .   ld2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPPPPPPeeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPPPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPeeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2275,19 +2299,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.2s, v2.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2r	{ v1.4h, v2.4h }, [x27], #4
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
-# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2r	{ v1.4h, v2.4h }, [x27], #4
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
+# CHECK-NEXT: [0,5]     DPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2321,19 +2346,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.16b, v2.16b }, [x27], #2
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2r	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2r	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2367,19 +2393,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2r	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2r	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld2r	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeeeER .   ld2r	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld2r	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,9]     .DPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2413,19 +2440,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2459,19 +2487,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2505,19 +2534,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .  .   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER   .    .    .  .   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R   .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER  .    .    .  .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R  .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=========eeeeeeeeER    .  .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,7]     .D==========eE------R    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D================eeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,9]     . D=================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER   .    .    .  .   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R   .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER  .    .    .  .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R  .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPeeeeeeeeER    .  .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPeE------R    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2551,19 +2581,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2597,19 +2628,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2643,19 +2675,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2689,19 +2722,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], #3
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2735,19 +2769,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeeeER  .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeeeER .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeeeeeER.   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2781,19 +2816,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeER  ..   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE-------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-------R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeeER  ..   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,5]     . D=eE------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE------R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeeER ..   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D=eE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE------R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   D=eeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D==eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2827,19 +2863,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeER  .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE-------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeeeER .   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,5]     . D=eE-------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE-------R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeeeER.   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE-------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE-------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   D=eeeeeeeeER   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2873,19 +2910,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeeER  ..   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-------R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeeER  ..   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE------R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeeeER..   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE-------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE-------R..   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   D=eeeeeeeeeER   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPPeE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2919,19 +2957,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2965,19 +3004,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPeE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3011,19 +3051,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R    .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D=======eeeeeeeeER..   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,5]     . D========eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=======eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D========eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=======eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
-# CHECK-NEXT: [0,9]     .   D========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     .DPPPPPPPeeeeeeeeER ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     . DPPPPPPPeeeeeeeeER..   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,5]     . DPPPPPPPPeE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DPPPPPPPeeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPeE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPPPPPeeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: [0,9]     .   DPPPPPPPPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3057,19 +3098,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER  .   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeeER .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #4
-# CHECK-NEXT: [0,5]     . D=eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE------R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeeER.   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
-# CHECK-NEXT: [0,7]     .  D=eE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
-# CHECK-NEXT: [0,9]     .   D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3103,19 +3145,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER  .   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeeER .   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE------R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     .  DeeeeeeeeER.   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     .  DPeE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .   DeeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,9]     .   DPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3149,19 +3192,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE------R .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeeER.   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE------R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeeE-R   ldp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,7]     . D==eE-----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ldp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeeeE-R   ldp	s1, s2, [x27], #248
+# CHECK-NEXT: [0,7]     . DPPeE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   ldp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3195,19 +3239,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D=eE----R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER..   ldp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eE----R..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER.   ldp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER   ldp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,7]     D====eE----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeE-R   ldp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER..   ldp	s1, s2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeE----R..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER.   ldp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,5]     DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER   ldp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,7]     DPPPPeE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeE-R   ldp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     .DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3241,19 +3286,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   ldp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eE--R   ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  ..   ldp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eE--R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER ..   ldp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     D===eE--R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeER.   ldpsw	x1, x2, [x27], #248
-# CHECK-NEXT: [0,7]     D====eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeER   ldpsw	x1, x2, [x27, #248]!
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  ..   ldp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER ..   ldp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,5]     DPPPeE--R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeER.   ldpsw	x1, x2, [x27], #248
+# CHECK-NEXT: [0,7]     DPPPPeE---R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeeER   ldpsw	x1, x2, [x27, #248]!
+# CHECK-NEXT: [0,9]     .DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3287,19 +3333,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ldr	b1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ldr	h1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ldr	s1, [x27], #254
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER.   ldr	d1, [x27], #254
-# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     D====eeeeeeER   ldr	q1, [x27], #254
-# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ldr	h1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ldr	s1, [x27], #254
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER.   ldr	d1, [x27], #254
+# CHECK-NEXT: [0,7]     DPPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     DPPPPeeeeeeER   ldr	q1, [x27], #254
+# CHECK-NEXT: [0,9]     DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3333,19 +3380,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ldr	b1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   ldr	h1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeeeER .   ldr	s1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeeeER.   ldr	d1, [x27, #254]!
-# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     D====eeeeeeER   ldr	q1, [x27, #254]!
-# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   ldr	h1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeeeER .   ldr	s1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeeeER.   ldr	d1, [x27, #254]!
+# CHECK-NEXT: [0,7]     DPPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     DPPPPeeeeeeER   ldr	q1, [x27, #254]!
+# CHECK-NEXT: [0,9]     DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3379,19 +3427,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	w1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldr	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeER.   ldr	x1, [x27, #254]!
-# CHECK-NEXT: [0,7]     D====eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     D====eeeeER   ldrb	w1, [x27], #254
-# CHECK-NEXT: [0,9]     D=====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldr	x1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldr	w1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeER.   ldr	x1, [x27, #254]!
+# CHECK-NEXT: [0,7]     DPPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     DPPPPeeeeER   ldrb	w1, [x27], #254
+# CHECK-NEXT: [0,9]     DPPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3425,19 +3474,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldrh	w1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldrh	w1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeER.   ldrsb	w1, [x27], #254
-# CHECK-NEXT: [0,7]     D====eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     D====eeeeER   ldrsb	x1, [x27], #254
-# CHECK-NEXT: [0,9]     D=====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldrh	w1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldrh	w1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeER.   ldrsb	w1, [x27], #254
+# CHECK-NEXT: [0,7]     DPPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     DPPPPeeeeER   ldrsb	x1, [x27], #254
+# CHECK-NEXT: [0,9]     DPPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3471,19 +3521,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrsb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   ldrsb	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   ldrsh	w1, [x27], #254
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeER.   ldrsh	x1, [x27], #254
-# CHECK-NEXT: [0,7]     D====eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     D====eeeeER   ldrsh	w1, [x27, #254]!
-# CHECK-NEXT: [0,9]     D=====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   ldrsb	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   ldrsh	w1, [x27], #254
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeER.   ldrsh	x1, [x27], #254
+# CHECK-NEXT: [0,7]     DPPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     DPPPPeeeeER   ldrsh	w1, [x27, #254]!
+# CHECK-NEXT: [0,9]     DPPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3517,18 +3568,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   ldrsh	x1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER.   ldrsw	x1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER   ldrsw	x1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eE--R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeE-R   st1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,7]     D====eE-R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER.   ldrsw	x1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER   ldrsw	x1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeE-R   st1	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,7]     DPPPPeE-R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3562,18 +3614,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeER.   st1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   st1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeER.   st1	{ v1.8b }, [x27], #8
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3607,18 +3660,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeER.   st1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   st1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeER.   st1	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3652,18 +3706,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeER.   st1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   st1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeER.   st1	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3697,18 +3752,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   st1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3742,18 +3798,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   st1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3787,18 +3844,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   st1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   st1	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   st1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3832,18 +3890,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER   .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,3]     D==eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,5]     .D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,7]     .D====eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,9]     . D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER   .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,3]     DPPeER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,5]     .DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPP=eeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,7]     .DPPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,9]     . DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3877,18 +3936,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER   .   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,3]     D==eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,5]     .D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,7]     .D====eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER   .   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,3]     DPPeER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,5]     .DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPP=eeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3922,18 +3982,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER   .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER  .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER   .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeER  .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPP=eeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3967,19 +4028,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER    .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,3]     D==eER    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeER  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,5]     .D===eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeER .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,7]     . D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D====eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,9]     . D=====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER    .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,3]     DPPeER    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP=eeER  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,5]     .DPPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPeeER .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,7]     . DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPP=eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,9]     . DPPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4013,19 +4075,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    ..   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eER.    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER    ..   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eER    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeER  ..   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,5]     .D===eER  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D==eeER ..   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,7]     . D===eER ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D=====eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .  D=====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER    ..   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,3]     .DPeER    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP=eeER  ..   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,5]     .DPPPeER  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPPeeER ..   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,7]     . DPPPeER ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPP==eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     .  DPPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4059,18 +4122,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER   .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D==eeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     . D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .  D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER   .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPeER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP=eeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPPeeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     . DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPeeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .  DPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4104,19 +4168,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    . .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eER.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeER    . .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===eeeeER .   st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,5]     .D====eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D===eeeeER.   st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,7]     . D====eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D====eeeeER   st1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D=====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeER    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP==eeeeER .   st1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,5]     .DPPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPPPeeeeER.   st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: [0,7]     . DPPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPPeeeeER   st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4150,19 +4215,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   st1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeER.   st1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   st1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   st1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeER.   st1	{ v1.h }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   st1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4196,19 +4262,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   st1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeER.   st1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   st1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeER.   st1	{ v1.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4242,19 +4309,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   st2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   st2	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4288,19 +4356,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4334,19 +4403,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   st2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   st2	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4380,19 +4450,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4426,19 +4497,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     DPPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4472,14 +4544,15 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE---R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,3]     D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,5]     .D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,3]     DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP=eeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,5]     .DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4509,19 +4582,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .  .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eE---R  .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .  .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,3]     D==eE--R  .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeeeeER  .   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,5]     .D===eE---R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeeeeER .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,7]     . D===eE---R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D====eeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D=====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .  .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,3]     DPPeE--R  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP=eeeeeER  .   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,5]     .DPPPeE---R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPeeeeeER .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,7]     . DPPPeE---R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPP=eeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4555,19 +4629,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   . .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  . .   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D==eE--R  . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeER. .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE---R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER. .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  . .   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPeE--R  . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeER. .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE---R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER. .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPP=eeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPeE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4601,19 +4676,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   st3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  ..   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,3]     D==eE--R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeeeER..   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,5]     .D===eE--R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeeeER.   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D====eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     . D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE---R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  ..   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,3]     DPPeE--R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP=eeeeER..   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,5]     .DPPPeE--R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPeeeeER.   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPPeeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     . DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4647,19 +4723,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  .   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  .   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,3]     DPPeE--R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER.   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,9]     . DPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4693,19 +4770,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   . .   st3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeER  . .   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,3]     D==eE--R  . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER . .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER. .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,7]     . D==eE--R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeER  . .   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,3]     DPPeE--R  . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeER . .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,5]     .DPPeE--R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeeeER. .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,7]     . DPPeE--R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,9]     . DPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4739,19 +4817,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE----R .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER    ..   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE-----R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . D=eeeeeeER   ..   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,5]     . D==eE----R   ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D===eeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,7]     .  D====eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D===eeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D====eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPPeE----R   ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .  DP==eeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,7]     .  DPPPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .   DPPPeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,9]     .   DPPPPeE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4785,19 +4864,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 9.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeER.    .   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===eeeeeeER  .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D===eeeeeeeER.   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     . D====eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D====eeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .  D=====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE----R.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP==eeeeeeER  .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     . DPPPeE----R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPPPeeeeeeeER.   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     . DPPPPeE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPPP=eeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .  DPPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4831,19 +4911,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   .   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.   .   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE-----R.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     .DeeeeeeeER   .   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     .DPeE-----R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     . DeeeeeeER   .   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,5]     . D=eE----R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D===eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,7]     .  D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D===eeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .  D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     . DPeE----R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DP==eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,7]     .  DPPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .  DPPPeeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .  DPPPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4877,19 +4958,20 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER. .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,3]     .D=eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeeER.   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     . D==eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     .  D==eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER. .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,3]     .DPeE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DPeeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
+# CHECK-NEXT: [0,5]     .DPPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     . DPeeeeeeER.   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,7]     . DPPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     . DPPeeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,9]     .  DPPeE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4923,17 +5005,18 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,1]     D=eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,5]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeeeeeER.   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPeE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     .DP=eeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
+# CHECK-NEXT: [0,5]     .DPPPeE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPPeeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .DPPPPeE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4965,12 +5048,13 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DeeER.   stp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,1]     D=eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER   stp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,3]     D==eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER   stp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,3]     DPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4998,18 +5082,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   stp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   stp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   stp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   stp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eER.   stp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   stp	s1, s2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   stp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     .DPPeeER.   stp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeER.   stp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5043,18 +5128,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   stp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   stp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eER  .   stp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeER.   str	b1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   str	h1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   stp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeER  .   stp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeER.   str	b1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   str	h1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5088,18 +5174,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   str	s1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   str	d1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   str	q1, [x27], #254
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeER.   str	b1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   str	h1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   str	d1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   str	q1, [x27], #254
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeeER.   str	b1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeeER   str	h1, [x27, #254]!
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5133,18 +5220,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   str	s1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   str	d1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   str	q1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eER .   str	w1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eER.   str	x1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeeER  .   str	d1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeeER .   str	q1, [x27, #254]!
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeER .   str	w1, [x27], #254
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeER.   str	x1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5178,18 +5266,19 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   str	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   str	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eER  .   strb	w1, [x27], #254
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eER .   strb	w1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eER.   strh	w1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPeER.  .   str	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPeER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     DPPeER  .   strb	w1, [x27], #254
+# CHECK-NEXT: [0,5]     DPPPeER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     DPPPeER .   strb	w1, [x27, #254]!
+# CHECK-NEXT: [0,7]     .DPPPeER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .DPPPeER.   strh	w1, [x27], #254
+# CHECK-NEXT: [0,9]     .DPPPPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5223,10 +5312,11 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 0.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   strh	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5252,13 +5342,14 @@ add x0, x27, 1
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D====eeeeER   ldr	x2, [x1], #254
-# CHECK-NEXT: [0,3]     D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,1]     DPeE--R   .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     DPPPPeeeeER   ldr	x2, [x1], #254
+# CHECK-NEXT: [0,3]     DPeE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s
index 8b1c8a4e4ca55..16e682cab32c6 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s
@@ -56,16 +56,17 @@ cmp x0, #4
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.34    -      -      -     0.01   0.01   0.49   0.49    -      -      -      -     cmp	x0, #4
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DeER .   mov	x0, x1
-# CHECK-NEXT: [0,1]     D=eER.   cmp	x0, #4
+# CHECK-NEXT: [0,1]     DPeER.   cmp	x0, #4
 # CHECK-NEXT: [1,0]     DeE-R.   mov	x0, x1
-# CHECK-NEXT: [1,1]     D=eER.   cmp	x0, #4
+# CHECK-NEXT: [1,1]     DPeER.   cmp	x0, #4
 # CHECK-NEXT: [2,0]     DeE-R.   mov	x0, x1
-# CHECK-NEXT: [2,1]     D=eER.   cmp	x0, #4
+# CHECK-NEXT: [2,1]     DPeER.   cmp	x0, #4
 # CHECK-NEXT: [3,0]     DeE-R.   mov	x0, x1
-# CHECK-NEXT: [3,1]     D==eER   cmp	x0, #4
+# CHECK-NEXT: [3,1]     DP=eER   cmp	x0, #4
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-clear-upper-regs.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-clear-upper-regs.s
index fbf65e26e99a5..61d92eef64722 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-clear-upper-regs.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-clear-upper-regs.s
@@ -107,17 +107,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldr	b0, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ldr	b0, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ldr	b0, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ldr	b0, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -186,17 +187,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldr	h0, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ldr	h0, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ldr	h0, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ldr	h0, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -265,17 +267,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldr	s0, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ldr	s0, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ldr	s0, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ldr	s0, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -344,17 +347,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldr	d0, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ldr	d0, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ldr	d0, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ldr	d0, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -423,17 +427,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldr	q0, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ldr	q0, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ldr	q0, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ldr	q0, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -502,17 +507,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ld1	{ v0.8b }, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ld1	{ v0.8b }, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ld1	{ v0.8b }, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ld1	{ v0.8b }, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -581,17 +587,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ld1	{ v0.4h }, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ld1	{ v0.4h }, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ld1	{ v0.4h }, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ld1	{ v0.4h }, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -660,17 +667,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ld1	{ v0.2s }, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ld1	{ v0.2s }, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ld1	{ v0.2s }, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ld1	{ v0.2s }, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -739,17 +747,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   add	z0.d, z0.d, z0.d
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ld1	{ v0.1d }, [sp]
-# CHECK-NEXT: [0,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [0,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [1,0]     DeeeeeeE--R.   ld1	{ v0.1d }, [sp]
-# CHECK-NEXT: [1,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [2,0]     DeeeeeeE--R.   ld1	{ v0.1d }, [sp]
-# CHECK-NEXT: [2,1]     D======eeER.   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [2,1]     DPPPPPPeeER.   add	z0.d, z0.d, z0.d
 # CHECK-NEXT: [3,0]     D=eeeeeeE-R.   ld1	{ v0.1d }, [sp]
-# CHECK-NEXT: [3,1]     D=======eeER   add	z0.d, z0.d, z0.d
+# CHECK-NEXT: [3,1]     DPPPPPPPeeER   add	z0.d, z0.d, z0.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -818,17 +827,18 @@ add z0.s, z0.s, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.33    -     0.33   0.34   add	z0.s, z0.s, z0.s
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    .    .    .    .   .   insr	z0.s, w0
-# CHECK-NEXT: [0,1]     D======eeER    .    .    .    .   .   add	z0.s, z0.s, z0.s
-# CHECK-NEXT: [1,0]     D========eeeeeeER   .    .    .   .   insr	z0.s, w0
-# CHECK-NEXT: [1,1]     D==============eeER .    .    .   .   add	z0.s, z0.s, z0.s
-# CHECK-NEXT: [2,0]     D================eeeeeeER.    .   .   insr	z0.s, w0
-# CHECK-NEXT: [2,1]     D======================eeER   .   .   add	z0.s, z0.s, z0.s
-# CHECK-NEXT: [3,0]     D========================eeeeeeER .   insr	z0.s, w0
-# CHECK-NEXT: [3,1]     D==============================eeER   add	z0.s, z0.s, z0.s
+# CHECK-NEXT: [0,1]     DPPPPPPeeER    .    .    .    .   .   add	z0.s, z0.s, z0.s
+# CHECK-NEXT: [1,0]     DPPPPPPPPeeeeeeER   .    .    .   .   insr	z0.s, w0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPeeER .    .    .   .   add	z0.s, z0.s, z0.s
+# CHECK-NEXT: [2,0]     DPPPPPPPPPPPPPPPPeeeeeeER.    .   .   insr	z0.s, w0
+# CHECK-NEXT: [2,1]     DPPPPPPPPPPPPPPPPPPPPPPeeER   .   .   add	z0.s, z0.s, z0.s
+# CHECK-NEXT: [3,0]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER .   insr	z0.s, w0
+# CHECK-NEXT: [3,1]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER   add	z0.s, z0.s, z0.s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-forwarding.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-forwarding.s
index 0f5ab183f5358..3741044c80883 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-forwarding.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-forwarding.s
@@ -321,17 +321,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .    ..   mul	x0, x0, x0
-# CHECK-NEXT: [0,1]     D==eeER   .    ..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [0,2]     D===eeER  .    ..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [0,3]     D=====eeER.    ..   madd	x0, x0, x0, x0
-# CHECK-NEXT: [1,0]     D=======eeER   ..   mul	x0, x0, x0
-# CHECK-NEXT: [1,1]     D=========eeER ..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [1,2]     D==========eeER..   madd	x0, x1, x2, x0
-# CHECK-NEXT: [1,3]     D============eeER   madd	x0, x0, x0, x0
+# CHECK-NEXT: [0,1]     DPPeeER   .    ..   madd	x0, x1, x2, x0
+# CHECK-NEXT: [0,2]     DPPPeeER  .    ..   madd	x0, x1, x2, x0
+# CHECK-NEXT: [0,3]     DPPPPPeeER.    ..   madd	x0, x0, x0, x0
+# CHECK-NEXT: [1,0]     DPPPPPPPeeER   ..   mul	x0, x0, x0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPeeER ..   madd	x0, x1, x2, x0
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPeeER..   madd	x0, x1, x2, x0
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPeeER   madd	x0, x0, x0, x0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -359,17 +360,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .    ..   mul	x0, x0, x0
-# CHECK-NEXT: [0,1]     D==eeER   .    ..   smaddl	x0, w1, w2, x0
-# CHECK-NEXT: [0,2]     D===eeER  .    ..   smaddl	x0, w1, w2, x0
-# CHECK-NEXT: [0,3]     D=====eeER.    ..   smaddl	x0, w0, w0, x0
-# CHECK-NEXT: [1,0]     D=======eeER   ..   mul	x0, x0, x0
-# CHECK-NEXT: [1,1]     D=========eeER ..   smaddl	x0, w1, w2, x0
-# CHECK-NEXT: [1,2]     D==========eeER..   smaddl	x0, w1, w2, x0
-# CHECK-NEXT: [1,3]     D============eeER   smaddl	x0, w0, w0, x0
+# CHECK-NEXT: [0,1]     DPPeeER   .    ..   smaddl	x0, w1, w2, x0
+# CHECK-NEXT: [0,2]     DPPPeeER  .    ..   smaddl	x0, w1, w2, x0
+# CHECK-NEXT: [0,3]     DPPPPPeeER.    ..   smaddl	x0, w0, w0, x0
+# CHECK-NEXT: [1,0]     DPPPPPPPeeER   ..   mul	x0, x0, x0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPeeER ..   smaddl	x0, w1, w2, x0
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPeeER..   smaddl	x0, w1, w2, x0
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPeeER   smaddl	x0, w0, w0, x0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -397,21 +399,22 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeER.    .    .    .    .    .    ..   fadd	d0, d0, d0
-# CHECK-NEXT: [0,1]     D==eeeeER .    .    .    .    .    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    .    .    ..   fmul	d0, d0, d0
-# CHECK-NEXT: [0,3]     D=======eeeeER .    .    .    .    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [0,4]     D=========eeeeER    .    .    .    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [0,5]     D=============eeeeER.    .    .    ..   fmadd	d0, d0, d1, d2
-# CHECK-NEXT: [1,0]     D=================eeER   .    .    ..   fadd	d0, d0, d0
-# CHECK-NEXT: [1,1]     D===================eeeeER    .    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [1,2]     D=======================eeeER .    ..   fmul	d0, d0, d0
-# CHECK-NEXT: [1,3]     D========================eeeeER    ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [1,4]     D==========================eeeeER  ..   fmadd	d0, d1, d2, d0
-# CHECK-NEXT: [1,5]     D==============================eeeeER   fmadd	d0, d0, d1, d2
+# CHECK-NEXT: [0,1]     DPPeeeeER .    .    .    .    .    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    .    .    ..   fmul	d0, d0, d0
+# CHECK-NEXT: [0,3]     DPPPPPPPeeeeER .    .    .    .    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [0,4]     DPPPPPPPPPeeeeER    .    .    .    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPeeeeER.    .    .    ..   fmadd	d0, d0, d1, d2
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPeeER   .    .    ..   fadd	d0, d0, d0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPeeeER .    ..   fmul	d0, d0, d0
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER    ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [1,4]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER  ..   fmadd	d0, d1, d2, d0
+# CHECK-NEXT: [1,5]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmadd	d0, d0, d1, d2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -441,17 +444,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   saba	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   saba	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   saba	v0.4s, v0.4s, v1.4s
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   saba	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   saba	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,3]     D======================eeeeER   saba	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   saba	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   saba	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   saba	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   saba	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   saba	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   saba	v0.4s, v0.4s, v1.4s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -479,17 +483,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 0.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
 # CHECK:      [0,0]     DeeeeER   .    .    .   .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeER.    .    .   .   sdot	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [0,2]     D=====eeeER    .    .   .   sdot	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [0,3]     D========eeeER .    .   .   sdot	v0.4s, v0.16b, v1.16b
-# CHECK-NEXT: [1,0]     D===========eeeeER  .   .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D===============eeeER   .   sdot	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [1,2]     D================eeeER  .   sdot	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [1,3]     D===================eeeER   sdot	v0.4s, v0.16b, v1.16b
+# CHECK-NEXT: [0,1]     DPPPPeeeER.    .    .   .   sdot	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [0,2]     DPPPPPeeeER    .    .   .   sdot	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .   .   sdot	v0.4s, v0.16b, v1.16b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPeeeeER  .   .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPeeeER   .   sdot	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPeeeER  .   sdot	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPeeeER   sdot	v0.4s, v0.16b, v1.16b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -517,17 +522,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 0.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
 # CHECK:      [0,0]     DeeeeER   .    .    .   .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeER.    .    .   .   smmla	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [0,2]     D=====eeeER    .    .   .   smmla	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [0,3]     D========eeeER .    .   .   smmla	v0.4s, v0.16b, v1.16b
-# CHECK-NEXT: [1,0]     D===========eeeeER  .   .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D===============eeeER   .   smmla	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [1,2]     D================eeeER  .   smmla	v0.4s, v1.16b, v2.16b
-# CHECK-NEXT: [1,3]     D===================eeeER   smmla	v0.4s, v0.16b, v1.16b
+# CHECK-NEXT: [0,1]     DPPPPeeeER.    .    .   .   smmla	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [0,2]     DPPPPPeeeER    .    .   .   smmla	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .   .   smmla	v0.4s, v0.16b, v1.16b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPeeeeER  .   .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPeeeER   .   smmla	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPeeeER  .   smmla	v0.4s, v1.16b, v2.16b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPeeeER   smmla	v0.4s, v0.16b, v1.16b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -555,17 +561,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   mla	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   mla	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   mla	v0.4s, v0.4s, v1.4s
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   mla	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   mla	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,3]     D======================eeeeER   mla	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   mla	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   mla	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   mla	v0.4s, v0.4s, v1.4s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -593,17 +600,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .    .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .    .   sqrdmlah	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   sqrdmlah	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   sqrdmlah	v0.4s, v0.4s, v1.4s
-# CHECK-NEXT: [1,0]     D==============eeeeER    .    .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D==================eeeeER.    .   sqrdmlah	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   sqrdmlah	v0.4s, v1.4s, v2.4s
-# CHECK-NEXT: [1,3]     D========================eeeeER   sqrdmlah	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .    .   sqrdmlah	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   sqrdmlah	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   sqrdmlah	v0.4s, v0.4s, v1.4s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeER    .    .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeER.    .   sqrdmlah	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   sqrdmlah	v0.4s, v1.4s, v2.4s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   sqrdmlah	v0.4s, v0.4s, v1.4s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -631,17 +639,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   smlal2	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   smlal2	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   smlal2	v0.4s, v0.8h, v1.8h
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   smlal2	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   smlal2	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,3]     D======================eeeeER   smlal2	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   smlal2	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   smlal2	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   smlal2	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   smlal2	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   smlal2	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   smlal2	v0.4s, v0.8h, v1.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -669,17 +678,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   sadalp	v0.2d, v1.4s
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   sadalp	v0.2d, v1.4s
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   sadalp	v0.2d, v0.4s
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   sadalp	v0.2d, v1.4s
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   sadalp	v0.2d, v1.4s
-# CHECK-NEXT: [1,3]     D======================eeeeER   sadalp	v0.2d, v0.4s
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   sadalp	v0.2d, v1.4s
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   sadalp	v0.2d, v1.4s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   sadalp	v0.2d, v0.4s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   sadalp	v0.2d, v1.4s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   sadalp	v0.2d, v1.4s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   sadalp	v0.2d, v0.4s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -707,17 +717,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D====eeeeER    .    .    .  .   ssra	v0.2d, v1.2d, #1
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   ssra	v0.2d, v1.2d, #1
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   ssra	v0.2d, v0.2d, #1
-# CHECK-NEXT: [1,0]     D=============eeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D=================eeeeER .  .   ssra	v0.2d, v1.2d, #1
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   ssra	v0.2d, v1.2d, #1
-# CHECK-NEXT: [1,3]     D======================eeeeER   ssra	v0.2d, v0.2d, #1
+# CHECK-NEXT: [0,1]     DPPPPeeeeER    .    .    .  .   ssra	v0.2d, v1.2d, #1
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   ssra	v0.2d, v1.2d, #1
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   ssra	v0.2d, v0.2d, #1
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeeER.    .  .   mul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeeER .  .   ssra	v0.2d, v1.2d, #1
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   ssra	v0.2d, v1.2d, #1
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   ssra	v0.2d, v0.2d, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -745,17 +756,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   fcmla	v0.2d, v0.2d, v1.2d, #90
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   fcmla	v0.2d, v1.2d, v2.2d, #90
-# CHECK-NEXT: [1,3]     D======================eeeeER   fcmla	v0.2d, v0.2d, v1.2d, #90
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   fcmla	v0.2d, v0.2d, v1.2d, #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   fcmla	v0.2d, v1.2d, v2.2d, #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   fcmla	v0.2d, v1.2d, v2.2d, #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   fcmla	v0.2d, v0.2d, v1.2d, #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -783,21 +795,22 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    ..   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D=eeeeER  .    .    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [0,2]     D=====eeER.    .    .    .    .    ..   fadd	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,3]     D=======eeeeER .    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [0,4]     D=========eeeeER    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [0,5]     D=============eeeeER.    .    .    ..   fmla	v0.2d, v0.2d, v1.2d
-# CHECK-NEXT: [1,0]     D=================eeeER  .    .    ..   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D==================eeeeER.    .    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [1,2]     D======================eeER   .    ..   fadd	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,3]     D========================eeeeER    ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [1,4]     D==========================eeeeER  ..   fmla	v0.2d, v1.2d, v2.2d
-# CHECK-NEXT: [1,5]     D==============================eeeeER   fmla	v0.2d, v0.2d, v1.2d
+# CHECK-NEXT: [0,1]     DPeeeeER  .    .    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [0,2]     DPPPPPeeER.    .    .    .    .    ..   fadd	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [0,3]     DPPPPPPPeeeeER .    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [0,4]     DPPPPPPPPPeeeeER    .    .    .    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPeeeeER.    .    .    ..   fmla	v0.2d, v0.2d, v1.2d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPeeeER  .    .    ..   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeER.    .    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPeeER   .    ..   fadd	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER    ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [1,4]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER  ..   fmla	v0.2d, v1.2d, v2.2d
+# CHECK-NEXT: [1,5]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmla	v0.2d, v0.2d, v1.2d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -827,21 +840,22 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    .    .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .    .    .    .   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [0,2]     D=======eeER   .    .    .    .    .    .   fadd	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .    .    .    .   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [0,4]     D===========eeeeER  .    .    .    .    .   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [0,5]     D===============eeeeER   .    .    .    .   fmlal	v0.4s, v0.4h, v1.4h
-# CHECK-NEXT: [1,0]     D===================eeeER.    .    .    .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D======================eeeeER .    .    .   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [1,2]     D==========================eeER    .    .   fadd	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,3]     D============================eeeeER.    .   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [1,4]     D==============================eeeeER   .   fmlal	v0.4s, v1.4h, v2.4h
-# CHECK-NEXT: [1,5]     D==================================eeeeER   fmlal	v0.4s, v0.4h, v1.4h
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .    .    .    .   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [0,2]     DPPPPPPPeeER   .    .    .    .    .    .   fadd	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .    .    .    .   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPeeeeER  .    .    .    .    .   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [0,5]     DPPPPPPPPPPPPPPPeeeeER   .    .    .    .   fmlal	v0.4s, v0.4h, v1.4h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPPPeeeER.    .    .    .   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER .    .    .   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeER    .    .   fadd	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER.    .   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [1,4]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   .   fmlal	v0.4s, v1.4h, v2.4h
+# CHECK-NEXT: [1,5]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmlal	v0.4s, v0.4h, v1.4h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -871,17 +885,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .   .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    .   .   bfdot	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,2]     D======eeeeeER .    .    .    .   .   bfdot	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,3]     D===========eeeeeER .    .    .   .   bfdot	v0.4s, v0.8h, v1.8h
-# CHECK-NEXT: [1,0]     D================eeeER   .    .   .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D===================eeeeeER   .   .   bfdot	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,2]     D======================eeeeeER.   .   bfdot	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,3]     D===========================eeeeeER   bfdot	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    .   .   bfdot	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeeER .    .    .    .   .   bfdot	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPeeeeeER .    .    .   .   bfdot	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPeeeER   .    .   .   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeeER   .   .   bfdot	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeER.   .   bfdot	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   bfdot	v0.4s, v0.8h, v1.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -909,17 +924,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    .    .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D===eeeeeeER   .    .    .    .    .    .   bfmmla	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,2]     D=======eeeeeeER    .    .    .    .    .   bfmmla	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,3]     D=============eeeeeeER   .    .    .    .   bfmmla	v0.4s, v0.8h, v1.8h
-# CHECK-NEXT: [1,0]     D===================eeeER.    .    .    .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D======================eeeeeeER    .    .   bfmmla	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,2]     D==========================eeeeeeER.    .   bfmmla	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,3]     D================================eeeeeeER   bfmmla	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [0,1]     DPPPeeeeeeER   .    .    .    .    .    .   bfmmla	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeeeER    .    .    .    .    .   bfmmla	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPeeeeeeER   .    .    .    .   bfmmla	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPPPeeeER.    .    .    .   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeeER    .    .   bfmmla	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER.    .   bfmmla	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER   bfmmla	v0.4s, v0.8h, v1.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -947,17 +963,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    . .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    . .   bfmlalb	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    . .   bfmlalb	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [0,3]     D==========eeeeeER  .    .    . .   bfmlalb	v0.4s, v0.8h, v1.8h
-# CHECK-NEXT: [1,0]     D===============eeeER    .    . .   fmul	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT: [1,1]     D==================eeeeeER    . .   bfmlalb	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,2]     D====================eeeeeER  . .   bfmlalb	v0.4s, v1.8h, v2.8h
-# CHECK-NEXT: [1,3]     D=========================eeeeeER   bfmlalb	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    . .   bfmlalb	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeeER  .    .    .    . .   bfmlalb	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeeER  .    .    . .   bfmlalb	v0.4s, v0.8h, v1.8h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeER    .    . .   fmul	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeeER    . .   bfmlalb	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeeER  . .   bfmlalb	v0.4s, v1.8h, v2.8h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   bfmlalb	v0.4s, v0.8h, v1.8h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -985,17 +1002,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .    ..   mul	w0, w0, w0
-# CHECK-NEXT: [0,1]     D==eeER   .    ..   crc32b	w0, w0, w1
-# CHECK-NEXT: [0,2]     D===eeER  .    ..   crc32b	w0, w0, w1
-# CHECK-NEXT: [0,3]     D=====eeER.    ..   crc32b	w0, w0, w0
-# CHECK-NEXT: [1,0]     D=======eeER   ..   mul	w0, w0, w0
-# CHECK-NEXT: [1,1]     D=========eeER ..   crc32b	w0, w0, w1
-# CHECK-NEXT: [1,2]     D==========eeER..   crc32b	w0, w0, w1
-# CHECK-NEXT: [1,3]     D============eeER   crc32b	w0, w0, w0
+# CHECK-NEXT: [0,1]     DPPeeER   .    ..   crc32b	w0, w0, w1
+# CHECK-NEXT: [0,2]     DPPPeeER  .    ..   crc32b	w0, w0, w1
+# CHECK-NEXT: [0,3]     DPPPPPeeER.    ..   crc32b	w0, w0, w0
+# CHECK-NEXT: [1,0]     DPPPPPPPeeER   ..   mul	w0, w0, w0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPeeER ..   crc32b	w0, w0, w1
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPeeER..   crc32b	w0, w0, w1
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPeeER   crc32b	w0, w0, w0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1023,17 +1041,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   saba	z0.d, z1.d, z2.d
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   saba	z0.d, z1.d, z2.d
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   saba	z0.d, z0.d, z1.d
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   saba	z0.d, z1.d, z2.d
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   saba	z0.d, z1.d, z2.d
-# CHECK-NEXT: [1,3]     D========================eeeeER   saba	z0.d, z0.d, z1.d
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   saba	z0.d, z1.d, z2.d
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   saba	z0.d, z1.d, z2.d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   saba	z0.d, z0.d, z1.d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   saba	z0.d, z1.d, z2.d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   saba	z0.d, z1.d, z2.d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   saba	z0.d, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1061,17 +1080,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   sadalp	z0.d, p0/m, z1.s
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   sadalp	z0.d, p0/m, z1.s
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   sadalp	z0.d, p0/m, z0.s
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   sadalp	z0.d, p0/m, z1.s
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   sadalp	z0.d, p0/m, z1.s
-# CHECK-NEXT: [1,3]     D========================eeeeER   sadalp	z0.d, p0/m, z0.s
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   sadalp	z0.d, p0/m, z1.s
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   sadalp	z0.d, p0/m, z1.s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   sadalp	z0.d, p0/m, z0.s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   sadalp	z0.d, p0/m, z1.s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   sadalp	z0.d, p0/m, z1.s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   sadalp	z0.d, p0/m, z0.s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1099,17 +1119,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   ssra	z0.d, z1.d, #1
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   ssra	z0.d, z1.d, #1
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   ssra	z0.d, z0.d, #1
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   ssra	z0.d, z1.d, #1
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   ssra	z0.d, z1.d, #1
-# CHECK-NEXT: [1,3]     D========================eeeeER   ssra	z0.d, z0.d, #1
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   ssra	z0.d, z1.d, #1
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   ssra	z0.d, z1.d, #1
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   ssra	z0.d, z0.d, #1
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   ssra	z0.d, z1.d, #1
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   ssra	z0.d, z1.d, #1
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   ssra	z0.d, z0.d, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1137,17 +1158,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeER    .    .    ..   cdot	z0.s, z1.b, z2.b, #90
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    ..   cdot	z0.s, z1.b, z2.b, #90
-# CHECK-NEXT: [0,3]     D=========eeeER.    .    ..   cdot	z0.s, z0.b, z1.b, #90
-# CHECK-NEXT: [1,0]     D============eeeeeER.    ..   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=================eeeER  ..   cdot	z0.s, z1.b, z2.b, #90
-# CHECK-NEXT: [1,2]     D==================eeeER ..   cdot	z0.s, z1.b, z2.b, #90
-# CHECK-NEXT: [1,3]     D=====================eeeER   cdot	z0.s, z0.b, z1.b, #90
+# CHECK-NEXT: [0,1]     DPPPPPeeeER    .    .    ..   cdot	z0.s, z1.b, z2.b, #90
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    ..   cdot	z0.s, z1.b, z2.b, #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeER.    .    ..   cdot	z0.s, z0.b, z1.b, #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPeeeeeER.    ..   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeER  ..   cdot	z0.s, z1.b, z2.b, #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeER ..   cdot	z0.s, z1.b, z2.b, #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPeeeER   cdot	z0.s, z0.b, z1.b, #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1175,17 +1197,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   cdot	z0.d, z1.h, z2.h, #90
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   cdot	z0.d, z1.h, z2.h, #90
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   cdot	z0.d, z0.h, z1.h, #90
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   cdot	z0.d, z1.h, z2.h, #90
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   cdot	z0.d, z1.h, z2.h, #90
-# CHECK-NEXT: [1,3]     D========================eeeeER   cdot	z0.d, z0.h, z1.h, #90
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   cdot	z0.d, z1.h, z2.h, #90
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   cdot	z0.d, z1.h, z2.h, #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   cdot	z0.d, z0.h, z1.h, #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   cdot	z0.d, z1.h, z2.h, #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   cdot	z0.d, z1.h, z2.h, #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   cdot	z0.d, z0.h, z1.h, #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1213,17 +1236,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   cmla	z0.b, z1.b, z2.b, #90
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   cmla	z0.b, z1.b, z2.b, #90
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   cmla	z0.b, z0.b, z1.b, #90
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   cmla	z0.b, z1.b, z2.b, #90
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   cmla	z0.b, z1.b, z2.b, #90
-# CHECK-NEXT: [1,3]     D========================eeeeER   cmla	z0.b, z0.b, z1.b, #90
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   cmla	z0.b, z1.b, z2.b, #90
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   cmla	z0.b, z1.b, z2.b, #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   cmla	z0.b, z0.b, z1.b, #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   cmla	z0.b, z1.b, z2.b, #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   cmla	z0.b, z1.b, z2.b, #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   cmla	z0.b, z0.b, z1.b, #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1251,17 +1275,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345678
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .  .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeeER  .    .    .    .    .  .   cmla	z0.d, z1.d, z2.d, #90
-# CHECK-NEXT: [0,2]     D========eeeeeER    .    .    .    .  .   cmla	z0.d, z1.d, z2.d, #90
-# CHECK-NEXT: [0,3]     D=============eeeeeER    .    .    .  .   cmla	z0.d, z0.d, z1.d, #90
-# CHECK-NEXT: [1,0]     D==================eeeeeER    .    .  .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=======================eeeeeER    .  .   cmla	z0.d, z1.d, z2.d, #90
-# CHECK-NEXT: [1,2]     D==========================eeeeeER .  .   cmla	z0.d, z1.d, z2.d, #90
-# CHECK-NEXT: [1,3]     D===============================eeeeeER   cmla	z0.d, z0.d, z1.d, #90
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER  .    .    .    .    .  .   cmla	z0.d, z1.d, z2.d, #90
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeER    .    .    .    .  .   cmla	z0.d, z1.d, z2.d, #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPeeeeeER    .    .    .  .   cmla	z0.d, z0.d, z1.d, #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPPeeeeeER    .    .  .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPPeeeeeER    .  .   cmla	z0.d, z1.d, z2.d, #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER .  .   cmla	z0.d, z1.d, z2.d, #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   cmla	z0.d, z0.d, z1.d, #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1289,17 +1314,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeER    .    .    ..   sdot	z0.s, z1.b, z2.b
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    ..   sdot	z0.s, z1.b, z2.b
-# CHECK-NEXT: [0,3]     D=========eeeER.    .    ..   sdot	z0.s, z0.b, z1.b
-# CHECK-NEXT: [1,0]     D============eeeeeER.    ..   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=================eeeER  ..   sdot	z0.s, z1.b, z2.b
-# CHECK-NEXT: [1,2]     D==================eeeER ..   sdot	z0.s, z1.b, z2.b
-# CHECK-NEXT: [1,3]     D=====================eeeER   sdot	z0.s, z0.b, z1.b
+# CHECK-NEXT: [0,1]     DPPPPPeeeER    .    .    ..   sdot	z0.s, z1.b, z2.b
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    ..   sdot	z0.s, z1.b, z2.b
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeER.    .    ..   sdot	z0.s, z0.b, z1.b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPeeeeeER.    ..   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeER  ..   sdot	z0.s, z1.b, z2.b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeER ..   sdot	z0.s, z1.b, z2.b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPeeeER   sdot	z0.s, z0.b, z1.b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1327,17 +1353,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeER    .    .    ..   sdot	z0.s, z1.b, z2.b[1]
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    ..   sdot	z0.s, z1.b, z2.b[1]
-# CHECK-NEXT: [0,3]     D=========eeeER.    .    ..   sdot	z0.s, z0.b, z1.b[1]
-# CHECK-NEXT: [1,0]     D============eeeeeER.    ..   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=================eeeER  ..   sdot	z0.s, z1.b, z2.b[1]
-# CHECK-NEXT: [1,2]     D==================eeeER ..   sdot	z0.s, z1.b, z2.b[1]
-# CHECK-NEXT: [1,3]     D=====================eeeER   sdot	z0.s, z0.b, z1.b[1]
+# CHECK-NEXT: [0,1]     DPPPPPeeeER    .    .    ..   sdot	z0.s, z1.b, z2.b[1]
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    ..   sdot	z0.s, z1.b, z2.b[1]
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeER.    .    ..   sdot	z0.s, z0.b, z1.b[1]
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPeeeeeER.    ..   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPeeeER  ..   sdot	z0.s, z1.b, z2.b[1]
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeER ..   sdot	z0.s, z1.b, z2.b[1]
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPeeeER   sdot	z0.s, z0.b, z1.b[1]
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1365,17 +1392,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   sdot	z0.d, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   sdot	z0.d, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   sdot	z0.d, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   sdot	z0.d, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   sdot	z0.d, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D========================eeeeER   sdot	z0.d, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   sdot	z0.d, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   sdot	z0.d, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   sdot	z0.d, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   sdot	z0.d, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   sdot	z0.d, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   sdot	z0.d, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1403,17 +1431,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 0.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
 # CHECK:      [0,0]     DeeeeER   .    .    .   .   mul	z0.s, z0.s, z0.s
-# CHECK-NEXT: [0,1]     D====eeeER.    .    .   .   smmla	z0.s, z1.b, z2.b
-# CHECK-NEXT: [0,2]     D=====eeeER    .    .   .   smmla	z0.s, z1.b, z2.b
-# CHECK-NEXT: [0,3]     D========eeeER .    .   .   smmla	z0.s, z0.b, z1.b
-# CHECK-NEXT: [1,0]     D===========eeeeER  .   .   mul	z0.s, z0.s, z0.s
-# CHECK-NEXT: [1,1]     D===============eeeER   .   smmla	z0.s, z1.b, z2.b
-# CHECK-NEXT: [1,2]     D================eeeER  .   smmla	z0.s, z1.b, z2.b
-# CHECK-NEXT: [1,3]     D===================eeeER   smmla	z0.s, z0.b, z1.b
+# CHECK-NEXT: [0,1]     DPPPPeeeER.    .    .   .   smmla	z0.s, z1.b, z2.b
+# CHECK-NEXT: [0,2]     DPPPPPeeeER    .    .   .   smmla	z0.s, z1.b, z2.b
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .   .   smmla	z0.s, z0.b, z1.b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPeeeeER  .   .   mul	z0.s, z0.s, z0.s
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPeeeER   .   smmla	z0.s, z1.b, z2.b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPeeeER  .   smmla	z0.s, z1.b, z2.b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPeeeER   smmla	z0.s, z0.b, z1.b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1441,17 +1470,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   mla	z0.b, p0/m, z1.b, z2.b
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   mla	z0.b, p0/m, z1.b, z2.b
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   mla	z0.b, p0/m, z0.b, z1.b
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   mla	z0.b, p0/m, z1.b, z2.b
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   mla	z0.b, p0/m, z1.b, z2.b
-# CHECK-NEXT: [1,3]     D========================eeeeER   mla	z0.b, p0/m, z0.b, z1.b
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   mla	z0.b, p0/m, z1.b, z2.b
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   mla	z0.b, p0/m, z1.b, z2.b
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   mla	z0.b, p0/m, z0.b, z1.b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   mla	z0.b, p0/m, z1.b, z2.b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   mla	z0.b, p0/m, z1.b, z2.b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   mla	z0.b, p0/m, z0.b, z1.b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1479,17 +1509,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345678
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .  .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeeER  .    .    .    .    .  .   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,2]     D========eeeeeER    .    .    .    .  .   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,3]     D=============eeeeeER    .    .    .  .   mla	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT: [1,0]     D==================eeeeeER    .    .  .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=======================eeeeeER    .  .   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,2]     D==========================eeeeeER .  .   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     D===============================eeeeeER   mla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER  .    .    .    .    .  .   mla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeER    .    .    .    .  .   mla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPeeeeeER    .    .    .  .   mla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPPeeeeeER    .    .  .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPPeeeeeER    .  .   mla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER .  .   mla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   mla	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1517,17 +1548,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    .   smlalb	z0.d, z1.s, z2.s
-# CHECK-NEXT: [0,2]     D======eeeeER  .    .    .    .   smlalb	z0.d, z1.s, z2.s
-# CHECK-NEXT: [0,3]     D==========eeeeER   .    .    .   smlalb	z0.d, z0.s, z1.s
-# CHECK-NEXT: [1,0]     D==============eeeeeER   .    .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeER    .   smlalb	z0.d, z1.s, z2.s
-# CHECK-NEXT: [1,2]     D====================eeeeER   .   smlalb	z0.d, z1.s, z2.s
-# CHECK-NEXT: [1,3]     D========================eeeeER   smlalb	z0.d, z0.s, z1.s
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    .   smlalb	z0.d, z1.s, z2.s
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeER  .    .    .    .   smlalb	z0.d, z1.s, z2.s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeER   .    .    .   smlalb	z0.d, z0.s, z1.s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPeeeeeER   .    .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeER    .   smlalb	z0.d, z1.s, z2.s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeER   .   smlalb	z0.d, z1.s, z2.s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   smlalb	z0.d, z0.s, z1.s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1555,17 +1587,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    . .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    . .   sqdmlalb	z0.d, z1.s, z2.s
-# CHECK-NEXT: [0,2]     D=======eeeeER .    .    .    . .   sqdmlalb	z0.d, z1.s, z2.s
-# CHECK-NEXT: [0,3]     D===========eeeeER  .    .    . .   sqdmlalb	z0.d, z0.s, z1.s
-# CHECK-NEXT: [1,0]     D===============eeeeeER  .    . .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D====================eeeeER   . .   sqdmlalb	z0.d, z1.s, z2.s
-# CHECK-NEXT: [1,2]     D======================eeeeER . .   sqdmlalb	z0.d, z1.s, z2.s
-# CHECK-NEXT: [1,3]     D==========================eeeeER   sqdmlalb	z0.d, z0.s, z1.s
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    . .   sqdmlalb	z0.d, z1.s, z2.s
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeER .    .    .    . .   sqdmlalb	z0.d, z1.s, z2.s
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPeeeeER  .    .    . .   sqdmlalb	z0.d, z0.s, z1.s
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeeeER  .    . .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPeeeeER   . .   sqdmlalb	z0.d, z1.s, z2.s
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER . .   sqdmlalb	z0.d, z1.s, z2.s
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   sqdmlalb	z0.d, z0.s, z1.s
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1593,17 +1626,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    . .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeER   .    .    .    . .   sqrdmlah	z0.b, z1.b, z2.b
-# CHECK-NEXT: [0,2]     D=======eeeeER .    .    .    . .   sqrdmlah	z0.b, z1.b, z2.b
-# CHECK-NEXT: [0,3]     D===========eeeeER  .    .    . .   sqrdmlah	z0.b, z0.b, z1.b
-# CHECK-NEXT: [1,0]     D===============eeeeeER  .    . .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D====================eeeeER   . .   sqrdmlah	z0.b, z1.b, z2.b
-# CHECK-NEXT: [1,2]     D======================eeeeER . .   sqrdmlah	z0.b, z1.b, z2.b
-# CHECK-NEXT: [1,3]     D==========================eeeeER   sqrdmlah	z0.b, z0.b, z1.b
+# CHECK-NEXT: [0,1]     DPPPPPeeeeER   .    .    .    . .   sqrdmlah	z0.b, z1.b, z2.b
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeER .    .    .    . .   sqrdmlah	z0.b, z1.b, z2.b
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPeeeeER  .    .    . .   sqrdmlah	z0.b, z0.b, z1.b
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeeeER  .    . .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPeeeeER   . .   sqrdmlah	z0.b, z1.b, z2.b
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER . .   sqrdmlah	z0.b, z1.b, z2.b
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   sqrdmlah	z0.b, z0.b, z1.b
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1631,17 +1665,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345678
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .  .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D=====eeeeeER  .    .    .    .    .  .   sqrdmlah	z0.d, z1.d, z2.d
-# CHECK-NEXT: [0,2]     D========eeeeeER    .    .    .    .  .   sqrdmlah	z0.d, z1.d, z2.d
-# CHECK-NEXT: [0,3]     D=============eeeeeER    .    .    .  .   sqrdmlah	z0.d, z0.d, z1.d
-# CHECK-NEXT: [1,0]     D==================eeeeeER    .    .  .   mul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D=======================eeeeeER    .  .   sqrdmlah	z0.d, z1.d, z2.d
-# CHECK-NEXT: [1,2]     D==========================eeeeeER .  .   sqrdmlah	z0.d, z1.d, z2.d
-# CHECK-NEXT: [1,3]     D===============================eeeeeER   sqrdmlah	z0.d, z0.d, z1.d
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER  .    .    .    .    .  .   sqrdmlah	z0.d, z1.d, z2.d
+# CHECK-NEXT: [0,2]     DPPPPPPPPeeeeeER    .    .    .    .  .   sqrdmlah	z0.d, z1.d, z2.d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPeeeeeER    .    .    .  .   sqrdmlah	z0.d, z0.d, z1.d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPPeeeeeER    .    .  .   mul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPPeeeeeER    .  .   sqrdmlah	z0.d, z1.d, z2.d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER .  .   sqrdmlah	z0.d, z1.d, z2.d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   sqrdmlah	z0.d, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1669,17 +1704,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
-# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
-# CHECK-NEXT: [0,3]     D==========eeeeeER  .    .    . .   fcmla	z0.d, p0/m, z0.d, z1.d, #90
-# CHECK-NEXT: [1,0]     D===============eeeER    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D==================eeeeeER    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
-# CHECK-NEXT: [1,2]     D====================eeeeeER  . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
-# CHECK-NEXT: [1,3]     D=========================eeeeeER   fcmla	z0.d, p0/m, z0.d, z1.d, #90
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
+# CHECK-NEXT: [0,2]     DPPPPPeeeeeER  .    .    .    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeeER  .    .    . .   fcmla	z0.d, p0/m, z0.d, z1.d, #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeER    .    . .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeeER    . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeeER  . .   fcmla	z0.d, p0/m, z1.d, z2.d, #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   fcmla	z0.d, p0/m, z0.d, z1.d, #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1707,17 +1743,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    . .   fcmla	z0.s, z1.s, z2.s[1], #90
-# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    . .   fcmla	z0.s, z1.s, z2.s[1], #90
-# CHECK-NEXT: [0,3]     D==========eeeeeER  .    .    . .   fcmla	z0.s, z0.s, z1.s[1], #90
-# CHECK-NEXT: [1,0]     D===============eeeER    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D==================eeeeeER    . .   fcmla	z0.s, z1.s, z2.s[1], #90
-# CHECK-NEXT: [1,2]     D====================eeeeeER  . .   fcmla	z0.s, z1.s, z2.s[1], #90
-# CHECK-NEXT: [1,3]     D=========================eeeeeER   fcmla	z0.s, z0.s, z1.s[1], #90
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    . .   fcmla	z0.s, z1.s, z2.s[1], #90
+# CHECK-NEXT: [0,2]     DPPPPPeeeeeER  .    .    .    . .   fcmla	z0.s, z1.s, z2.s[1], #90
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeeER  .    .    . .   fcmla	z0.s, z0.s, z1.s[1], #90
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeER    .    . .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeeER    . .   fcmla	z0.s, z1.s, z2.s[1], #90
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeeER  . .   fcmla	z0.s, z1.s, z2.s[1], #90
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   fcmla	z0.s, z0.s, z1.s[1], #90
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1745,17 +1782,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   fmla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   fmla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   fmla	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   fmla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   fmla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     D======================eeeeER   fmla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   fmla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   fmla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   fmla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   fmla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   fmla	z0.d, p0/m, z1.d, z2.d
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmla	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1783,17 +1821,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   fmla	z0.d, z1.d, z2.d[1]
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   fmla	z0.d, z1.d, z2.d[1]
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   fmla	z0.d, z0.d, z1.d[1]
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   fmla	z0.d, z1.d, z2.d[1]
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   fmla	z0.d, z1.d, z2.d[1]
-# CHECK-NEXT: [1,3]     D======================eeeeER   fmla	z0.d, z0.d, z1.d[1]
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   fmla	z0.d, z1.d, z2.d[1]
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   fmla	z0.d, z1.d, z2.d[1]
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   fmla	z0.d, z0.d, z1.d[1]
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   fmla	z0.d, z1.d, z2.d[1]
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   fmla	z0.d, z1.d, z2.d[1]
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmla	z0.d, z0.d, z1.d[1]
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1821,17 +1860,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeER.    .    .    .  .   fmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D=====eeeeER   .    .    .  .   fmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D=========eeeeER    .    .  .   fmlalb	z0.s, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D=============eeeER .    .  .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D================eeeeER  .  .   fmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D==================eeeeER.  .   fmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D======================eeeeER   fmlalb	z0.s, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPeeeeER.    .    .    .  .   fmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeER   .    .    .  .   fmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPeeeeER    .    .  .   fmlalb	z0.s, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPeeeER .    .  .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPeeeeER  .  .   fmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPeeeeER.  .   fmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPeeeeER   fmlalb	z0.s, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1859,17 +1899,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .   .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    .   .   bfdot	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D======eeeeeER .    .    .    .   .   bfdot	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D===========eeeeeER .    .    .   .   bfdot	z0.s, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D================eeeER   .    .   .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D===================eeeeeER   .   .   bfdot	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D======================eeeeeER.   .   bfdot	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D===========================eeeeeER   bfdot	z0.s, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    .   .   bfdot	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeeER .    .    .    .   .   bfdot	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPeeeeeER .    .    .   .   bfdot	z0.s, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPeeeER   .    .   .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPeeeeeER   .   .   bfdot	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeER.   .   bfdot	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   bfdot	z0.s, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1897,17 +1938,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    .    .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeeER   .    .    .    .    .    .   bfmmla	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D=======eeeeeeER    .    .    .    .    .   bfmmla	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D=============eeeeeeER   .    .    .    .   bfmmla	z0.s, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D===================eeeER.    .    .    .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D======================eeeeeeER    .    .   bfmmla	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D==========================eeeeeeER.    .   bfmmla	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D================================eeeeeeER   bfmmla	z0.s, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPeeeeeeER   .    .    .    .    .    .   bfmmla	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPPPeeeeeeER    .    .    .    .    .   bfmmla	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPeeeeeeER   .    .    .    .   bfmmla	z0.s, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPPPPPeeeER.    .    .    .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPPPPPeeeeeeER    .    .   bfmmla	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER.    .   bfmmla	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER   bfmmla	z0.s, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1935,17 +1977,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [0,1]     D===eeeeeER    .    .    .    . .   bfmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    . .   bfmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [0,3]     D==========eeeeeER  .    .    . .   bfmlalb	z0.s, z0.h, z1.h
-# CHECK-NEXT: [1,0]     D===============eeeER    .    . .   fmul	z0.d, z0.d, z0.d
-# CHECK-NEXT: [1,1]     D==================eeeeeER    . .   bfmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,2]     D====================eeeeeER  . .   bfmlalb	z0.s, z1.h, z2.h
-# CHECK-NEXT: [1,3]     D=========================eeeeeER   bfmlalb	z0.s, z0.h, z1.h
+# CHECK-NEXT: [0,1]     DPPPeeeeeER    .    .    .    . .   bfmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,2]     DPPPPPeeeeeER  .    .    .    . .   bfmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPeeeeeER  .    .    . .   bfmlalb	z0.s, z0.h, z1.h
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPPPeeeER    .    . .   fmul	z0.d, z0.d, z0.d
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPPPPeeeeeER    . .   bfmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,2]     DPPPPPPPPPPPPPPPPPPPPeeeeeER  . .   bfmlalb	z0.s, z1.h, z2.h
+# CHECK-NEXT: [1,3]     DPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   bfmlalb	z0.s, z0.h, z1.h
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-writeback.s
index 1ef746813966d..1d4d893bc7639 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V2-writeback.s
@@ -739,14 +739,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.2d }, [x27], #16
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,4]     D====eeeeeeER   ld1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.2s }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeER   ld1	{ v1.4s }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -775,14 +776,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.8h }, [x27], #16
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,4]     D====eeeeeeER   ld1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.16b }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeER   ld1	{ v1.2d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -811,14 +813,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,4]     D====eeeeeeER   ld1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeER   ld1	{ v1.8h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -847,14 +850,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,4]     D====eeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -883,14 +887,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,4]     D====eeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -919,14 +924,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,4]     D====eeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -955,14 +961,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,4]     .D===eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -991,14 +998,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,4]     .D===eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1027,14 +1035,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,4]     .D===eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1063,14 +1072,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .  .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER.  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeeeER.   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,4]     .D===eeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,1]     DPeeeeeeER.  .   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeER.   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1099,14 +1109,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   .   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeeeeER   .   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,2]     D==eeeeeeeER  .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,3]     .D===eeeeeeeER.   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,4]     .D====eeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,1]     DPeeeeeeeER   .   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,2]     DPPeeeeeeeER  .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,3]     .DPP=eeeeeeeER.   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,4]     .DPPPPeeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1135,14 +1146,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eeeeeeeER   .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeeER  .   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D===eeeeeeeER.   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,4]     .D====eeeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeER   .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeeER  .   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPP=eeeeeeeER.   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPPeeeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1171,14 +1183,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    ..   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeER    .    ..   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeeER   .    ..   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D===eeeeeeeER .    ..   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,4]     .D==========eeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,1]     DPeeeeeeeER    .    ..   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeeER   .    ..   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPP=eeeeeeeER .    ..   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPeeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1207,14 +1220,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,2]     D================eeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,3]     D========================eeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,4]     D================================eeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,2]     DPPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.b }[8], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.h }[4], [x27], #2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1243,14 +1257,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
-# CHECK-NEXT: [0,2]     D================eeeeeeeeER   .    .    . .   ld1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,3]     D========================eeeeeeeeER.    . .   ld1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,4]     D================================eeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,2]     DPPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld1	{ v1.s }[0], [x27], #4
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,4]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld1	{ v1.d }[0], [x27], #8
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1279,14 +1294,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld1r	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
-# CHECK-NEXT: [0,3]     D===eeeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
-# CHECK-NEXT: [0,4]     D====eeeeeeeeER   ld1r	{ v1.4h }, [x27], #2
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld1r	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld1r	{ v1.2d }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPPeeeeeeeeER.   ld1r	{ v1.2s }, [x27], #4
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeeeER   ld1r	{ v1.4h }, [x27], #2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1315,14 +1331,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.4s }, [x27], #4
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld1r	{ v1.8b }, [x27], #1
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
-# CHECK-NEXT: [0,3]     D===eeeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
-# CHECK-NEXT: [0,4]     D====eeeeeeeeER   ld1r	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld1r	{ v1.8b }, [x27], #1
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld1r	{ v1.8h }, [x27], #2
+# CHECK-NEXT: [0,3]     DPPPeeeeeeeeER.   ld1r	{ v1.16b }, [x27], #1
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeeeER   ld1r	{ v1.1d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1351,14 +1368,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld1r	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,4]     D====eeeeeeeeER   ld1r	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld1r	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld1r	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeeeeeeeER.   ld1r	{ v1.4s }, [x27], x28
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeeeER   ld1r	{ v1.8b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1387,14 +1405,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld1r	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld1r	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,3]     D===eeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,4]     .D===eeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld1r	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,3]     DPPPeeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1423,14 +1442,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,4]     .D===eeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1459,14 +1479,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,4]     .D===eeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1495,14 +1516,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,2]     D================eeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,3]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,4]     .D===============================eeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,2]     DPPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1531,14 +1553,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,2]     D================eeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D========================eeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,4]     .D===============================eeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,2]     DPPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1567,14 +1590,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .  .   ld2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .  .   ld2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,2]     D================eeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D=================eeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: [0,4]     .D=================eeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .  .   ld2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,2]     DPPPPPPPPPPPPPPPPeeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPPPPPPPeeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPPPPPPPeeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1603,14 +1627,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.2s, v2.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld2r	{ v1.4h, v2.4h }, [x27], #4
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
-# CHECK-NEXT: [0,3]     D===eeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
-# CHECK-NEXT: [0,4]     .D===eeeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld2r	{ v1.4h, v2.4h }, [x27], #4
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
+# CHECK-NEXT: [0,3]     DPPPeeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1639,14 +1664,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.16b, v2.16b }, [x27], #2
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld2r	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,4]     .D===eeeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld2r	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1675,14 +1701,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld2r	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld2r	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeeeeeER .   ld2r	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeeeeeeeER.   ld2r	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,4]     .D===eeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld2r	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeeeeeER .   ld2r	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeeeeeeeER.   ld2r	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPeeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1711,14 +1738,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,2]     .D=eeeeeeeeER .   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,4]     . D==eeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,2]     .DPeeeeeeeeER .   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,4]     . DPPeeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1747,14 +1775,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeeeeER .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeeeeER .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1783,14 +1812,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .  .   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER   .    .    .  .   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeeeeER  .    .    .  .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=========eeeeeeeeER    .  .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,4]     . D================eeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER   .    .    .  .   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeeeeER  .    .    .  .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPeeeeeeeeER    .  .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1819,14 +1849,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,2]     .D===============eeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,3]     .D=======================eeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,4]     . D==============================eeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,2]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1855,14 +1886,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,2]     .D===============eeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D=======================eeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,4]     . D==============================eeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,2]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1891,14 +1923,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
-# CHECK-NEXT: [0,2]     .D=eeeeeeeeER .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
-# CHECK-NEXT: [0,4]     . D==eeeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
+# CHECK-NEXT: [0,2]     .DPeeeeeeeeER .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
+# CHECK-NEXT: [0,4]     . DPPeeeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1927,14 +1960,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], #3
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
-# CHECK-NEXT: [0,2]     .D=eeeeeeeeER .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
+# CHECK-NEXT: [0,2]     .DPeeeeeeeeER .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1963,14 +1997,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeeeER  .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeeeeeER .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeeeeeeeER.   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,4]     . D==eeeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeeeER  .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeeeeeER .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeeeeeeeER.   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPeeeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1999,14 +2034,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeeeeeeeeeER  ..   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
 # CHECK-NEXT: [0,2]     . DeeeeeeeeER  ..   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,3]     . D=eeeeeeeeER ..   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,4]     .  D==eeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,3]     . DPeeeeeeeeER ..   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,4]     .  DP=eeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2035,6 +2071,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -2071,6 +2108,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
@@ -2107,14 +2145,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,2]     .D===============eeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D=======================eeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,4]     . D==============================eeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,2]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2143,14 +2182,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,2]     .D===============eeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,3]     .D=======================eeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,4]     . D==============================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,2]     .DPPPPPPPPPPPPPPPeeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2179,14 +2219,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,1]     D========eeeeeeeeER ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,2]     .D========eeeeeeeeER..   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,3]     . D========eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: [0,4]     .  D========eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: [0,1]     DPPPPPPPPeeeeeeeeER ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,2]     .DPPPPPPPPeeeeeeeeER..   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,3]     . DPPPPPPPPeeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: [0,4]     .  DPPPPPPPPeeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2215,6 +2256,7 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -2251,14 +2293,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER    .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeeeeeeeeER   .   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: [0,2]     . DeeeeeeeeER  .   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     . D=eeeeeeeeER .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,4]     .  D==eeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     . DPeeeeeeeeER .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,4]     .  DP=eeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2287,14 +2330,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeeeeeeeeER.   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
 # CHECK-NEXT: [0,2]     . DeeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     . D=eeeeeeE-R   ldp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,4]     .  D=eeeeeeER   ldp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,3]     . DPeeeeeeE-R   ldp	s1, s2, [x27], #248
+# CHECK-NEXT: [0,4]     .  DPeeeeeeER   ldp	d1, d2, [x27], #496
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2323,14 +2367,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER ..   ldp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D=eeeeeeER..   ldp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,2]     D==eeeeeeER.   ldp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,3]     .D==eeeeeeER   ldp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,4]     .D===eeeeE-R   ldp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,1]     DPeeeeeeER..   ldp	s1, s2, [x27, #248]!
+# CHECK-NEXT: [0,2]     DPPeeeeeeER.   ldp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,3]     .DPPeeeeeeER   ldp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,4]     .DPPPeeeeE-R   ldp	w1, w2, [x27], #248
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2359,14 +2404,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   ldp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eeeeER  ..   ldp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,2]     D==eeeeER ..   ldp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,3]     D===eeeeeER.   ldpsw	x1, x2, [x27], #248
-# CHECK-NEXT: [0,4]     .D===eeeeeER   ldpsw	x1, x2, [x27, #248]!
+# CHECK-NEXT: [0,1]     DPeeeeER  ..   ldp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,2]     DPPeeeeER ..   ldp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,3]     DPPPeeeeeER.   ldpsw	x1, x2, [x27], #248
+# CHECK-NEXT: [0,4]     .DPPPeeeeeER   ldpsw	x1, x2, [x27, #248]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2395,14 +2441,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ldr	b1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ldr	h1, [x27], #254
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ldr	s1, [x27], #254
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ldr	d1, [x27], #254
-# CHECK-NEXT: [0,4]     D====eeeeeeER   ldr	q1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ldr	h1, [x27], #254
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ldr	s1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ldr	d1, [x27], #254
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeER   ldr	q1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2431,14 +2478,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER . .   ldr	b1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeeeeeER. .   ldr	h1, [x27, #254]!
-# CHECK-NEXT: [0,2]     D==eeeeeeER .   ldr	s1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D===eeeeeeER.   ldr	d1, [x27, #254]!
-# CHECK-NEXT: [0,4]     D====eeeeeeER   ldr	q1, [x27, #254]!
+# CHECK-NEXT: [0,1]     DPeeeeeeER. .   ldr	h1, [x27, #254]!
+# CHECK-NEXT: [0,2]     DPPeeeeeeER .   ldr	s1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPPeeeeeeER.   ldr	d1, [x27, #254]!
+# CHECK-NEXT: [0,4]     DPPPPeeeeeeER   ldr	q1, [x27, #254]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2467,14 +2515,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	w1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eeeeER  .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,2]     D==eeeeER .   ldr	w1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D===eeeeER.   ldr	x1, [x27, #254]!
-# CHECK-NEXT: [0,4]     D====eeeeER   ldrb	w1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeeeeER  .   ldr	x1, [x27], #254
+# CHECK-NEXT: [0,2]     DPPeeeeER .   ldr	w1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPPeeeeER.   ldr	x1, [x27, #254]!
+# CHECK-NEXT: [0,4]     DPPPPeeeeER   ldrb	w1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2503,14 +2552,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeeeER  .   ldrh	w1, [x27], #254
-# CHECK-NEXT: [0,2]     D==eeeeER .   ldrh	w1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D===eeeeER.   ldrsb	w1, [x27], #254
-# CHECK-NEXT: [0,4]     D====eeeeER   ldrsb	x1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeeeeER  .   ldrh	w1, [x27], #254
+# CHECK-NEXT: [0,2]     DPPeeeeER .   ldrh	w1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPPeeeeER.   ldrsb	w1, [x27], #254
+# CHECK-NEXT: [0,4]     DPPPPeeeeER   ldrsb	x1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2539,14 +2589,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldrsb	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeeeER  .   ldrsb	x1, [x27, #254]!
-# CHECK-NEXT: [0,2]     D==eeeeER .   ldrsh	w1, [x27], #254
-# CHECK-NEXT: [0,3]     D===eeeeER.   ldrsh	x1, [x27], #254
-# CHECK-NEXT: [0,4]     D====eeeeER   ldrsh	w1, [x27, #254]!
+# CHECK-NEXT: [0,1]     DPeeeeER  .   ldrsb	x1, [x27, #254]!
+# CHECK-NEXT: [0,2]     DPPeeeeER .   ldrsh	w1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPPeeeeER.   ldrsh	x1, [x27], #254
+# CHECK-NEXT: [0,4]     DPPPPeeeeER   ldrsh	w1, [x27, #254]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2575,13 +2626,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 1.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   ldrsh	x1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeeeER.   ldrsw	x1, [x27], #254
-# CHECK-NEXT: [0,2]     D==eeeeER   ldrsw	x1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D===eeE-R   st1	{ v1.1d }, [x27], #8
-# CHECK-NEXT: [0,4]     D====eeER   st1	{ v1.2d }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeeeER.   ldrsw	x1, [x27], #254
+# CHECK-NEXT: [0,2]     DPPeeeeER   ldrsw	x1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPPeeE-R   st1	{ v1.1d }, [x27], #8
+# CHECK-NEXT: [0,4]     DPPPPeeER   st1	{ v1.2d }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2610,13 +2662,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2s }, [x27], #8
-# CHECK-NEXT: [0,1]     D=eeER  .   st1	{ v1.4h }, [x27], #8
-# CHECK-NEXT: [0,2]     D==eeER .   st1	{ v1.4s }, [x27], #16
-# CHECK-NEXT: [0,3]     D===eeER.   st1	{ v1.8b }, [x27], #8
-# CHECK-NEXT: [0,4]     D====eeER   st1	{ v1.8h }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeER  .   st1	{ v1.4h }, [x27], #8
+# CHECK-NEXT: [0,2]     DPPeeER .   st1	{ v1.4s }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPPeeER.   st1	{ v1.8b }, [x27], #8
+# CHECK-NEXT: [0,4]     DPPPPeeER   st1	{ v1.8h }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2645,13 +2698,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.16b }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eeER  .   st1	{ v1.1d }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeER .   st1	{ v1.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeER.   st1	{ v1.2s }, [x27], x28
-# CHECK-NEXT: [0,4]     D====eeER   st1	{ v1.4h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeER  .   st1	{ v1.1d }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeER .   st1	{ v1.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeER.   st1	{ v1.2s }, [x27], x28
+# CHECK-NEXT: [0,4]     DPPPPeeER   st1	{ v1.4h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2680,13 +2734,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeER  .   st1	{ v1.8b }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeER .   st1	{ v1.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeER.   st1	{ v1.16b }, [x27], x28
-# CHECK-NEXT: [0,4]     D====eeER   st1	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeER  .   st1	{ v1.8b }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeER .   st1	{ v1.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeER.   st1	{ v1.16b }, [x27], x28
+# CHECK-NEXT: [0,4]     DPPPPeeER   st1	{ v1.1d, v2.1d }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2715,13 +2770,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,2]     D==eeER .   st1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,3]     D===eeER.   st1	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,4]     .D===eeER   st1	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,1]     DPeeER  .   st1	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,2]     DPPeeER .   st1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,3]     DPPPeeER.   st1	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,4]     .DPPPeeER   st1	{ v1.8b, v2.8b }, [x27], #16
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2750,13 +2806,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,2]     D==eeER .   st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeER.   st1	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,4]     .D===eeER   st1	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,2]     DPPeeER .   st1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeER.   st1	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPeeER   st1	{ v1.2s, v2.2s }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2785,13 +2842,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   st1	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,2]     D==eeER .   st1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,3]     D===eeER.   st1	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,4]     .D===eeER   st1	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeER  .   st1	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeER .   st1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeER.   st1	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPeeER   st1	{ v1.16b, v2.16b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2820,13 +2878,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eeER   .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,2]     .D=eeER  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,3]     .D===eeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,4]     . D===eeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,1]     DPeeER   .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,2]     .DPeeER  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,3]     .DPP=eeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,4]     . DPPPeeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2855,13 +2914,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
-# CHECK-NEXT: [0,1]     D=eeER   .   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,2]     .D=eeER  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,3]     .D===eeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
-# CHECK-NEXT: [0,4]     . D===eeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeER   .   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,2]     .DPeeER  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,3]     .DPP=eeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPPeeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2890,13 +2950,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeER   .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeER  .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D==eeER .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,4]     . D===eeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeER   .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeER  .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPeeER .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPP=eeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2925,14 +2986,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeER    .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,2]     .D==eeER  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,3]     .D===eeER .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,4]     . D====eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,1]     DPeeER    .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,2]     .DP=eeER  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,3]     .DPPPeeER .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,4]     . DPPP=eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2961,14 +3023,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    ..   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,1]     D=eeER    ..   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,2]     .D==eeER  ..   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,3]     . D==eeER ..   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,4]     . D=====eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeER    ..   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,2]     .DP=eeER  ..   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,3]     . DPPeeER ..   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,4]     . DPPP==eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2997,13 +3060,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeER   .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,2]     .D==eeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D===eeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,4]     . D===eeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeER   .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,2]     .DP=eeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPeeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,4]     . DPPPeeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3032,14 +3096,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    . .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeeER    . .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,2]     .D===eeeeER .   st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,3]     . D===eeeeER.   st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,4]     . D====eeeeER   st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,2]     .DP==eeeeER .   st1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,3]     . DPPPeeeeER.   st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: [0,4]     . DPPPPeeeeER   st1	{ v1.b }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3068,14 +3133,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st1	{ v1.h }[0], [x27], #2
-# CHECK-NEXT: [0,2]     D==eeeeER .   st1	{ v1.h }[4], [x27], #2
-# CHECK-NEXT: [0,3]     D===eeeeER.   st1	{ v1.h }[0], [x27], x28
-# CHECK-NEXT: [0,4]     .D===eeeeER   st1	{ v1.h }[4], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st1	{ v1.h }[0], [x27], #2
+# CHECK-NEXT: [0,2]     DPPeeeeER .   st1	{ v1.h }[4], [x27], #2
+# CHECK-NEXT: [0,3]     DPPPeeeeER.   st1	{ v1.h }[0], [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPeeeeER   st1	{ v1.h }[4], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3104,14 +3170,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 6.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st1	{ v1.s }[0], [x27], #4
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st1	{ v1.s }[0], [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeER .   st1	{ v1.d }[0], [x27], #8
-# CHECK-NEXT: [0,3]     D===eeeeER.   st1	{ v1.d }[0], [x27], x28
-# CHECK-NEXT: [0,4]     .D===eeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st1	{ v1.s }[0], [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeER .   st1	{ v1.d }[0], [x27], #8
+# CHECK-NEXT: [0,3]     DPPPeeeeER.   st1	{ v1.d }[0], [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPeeeeER   st2	{ v1.2d, v2.2d }, [x27], #32
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3140,14 +3207,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   st2	{ v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: [0,1]     D=eeeeER  ..   st2	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,2]     D==eeeeER ..   st2	{ v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: [0,3]     .D==eeeeER..   st2	{ v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: [0,4]     .D====eeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,1]     DPeeeeER  ..   st2	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,2]     DPPeeeeER ..   st2	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,3]     .DPPeeeeER..   st2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,4]     .DPPP=eeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3176,14 +3244,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   . .   st2	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eeeeER  . .   st2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,2]     .D===eeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D====eeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
-# CHECK-NEXT: [0,4]     .D=====eeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  . .   st2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,2]     .DP==eeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPeeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPPPeeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3212,14 +3281,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   . .   st2	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeER  . .   st2	{ v1.8h, v2.8h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D=eeeeER . .   st2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D====eeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
-# CHECK-NEXT: [0,4]     .D=====eeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
+# CHECK-NEXT: [0,1]     DPeeeeER  . .   st2	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DPeeeeER . .   st2	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     .DPP==eeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,4]     .DPPPPPeeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3248,14 +3318,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.b, v2.b }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
-# CHECK-NEXT: [0,2]     D==eeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
-# CHECK-NEXT: [0,3]     D===eeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
-# CHECK-NEXT: [0,4]     .D===eeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st2	{ v1.b, v2.b }[8], [x27], x28
+# CHECK-NEXT: [0,2]     DPPeeeeER .   st2	{ v1.h, v2.h }[0], [x27], #4
+# CHECK-NEXT: [0,3]     DPPPeeeeER.   st2	{ v1.h, v2.h }[4], [x27], #4
+# CHECK-NEXT: [0,4]     .DPPPeeeeER   st2	{ v1.h, v2.h }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3284,14 +3355,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   st2	{ v1.h, v2.h }[4], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
-# CHECK-NEXT: [0,2]     D==eeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     D===eeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
-# CHECK-NEXT: [0,4]     .D===eeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeER  .   st2	{ v1.s, v2.s }[0], [x27], #8
+# CHECK-NEXT: [0,2]     DPPeeeeER .   st2	{ v1.s, v2.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     DPPPeeeeER.   st2	{ v1.d, v2.d }[0], [x27], #16
+# CHECK-NEXT: [0,4]     .DPPPeeeeER   st2	{ v1.d, v2.d }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3320,14 +3392,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    .   .   st2g	x26, [x27], #4064
-# CHECK-NEXT: [0,1]     D=eER.    .   .   st2g	x26, [x27, #4064]!
-# CHECK-NEXT: [0,2]     D==eeeeeeER   .   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,3]     .D==eeeeeER   .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,4]     .D======eeeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,1]     DPeER.    .   .   st2g	x26, [x27, #4064]!
+# CHECK-NEXT: [0,2]     DPPeeeeeeER   .   st3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,3]     .DPPeeeeeER   .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,4]     .DPPP===eeeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3356,14 +3429,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 14.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    .   .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
 # CHECK-NEXT: [0,1]     .DeeeeeER .    .   .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
 # CHECK-NEXT: [0,2]     . D===eeeeeeER .   .   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,3]     .  D===eeeeeeER.   .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,4]     .   D=======eeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPeeeeeeER.   .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,4]     .   DPPP====eeeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3392,14 +3466,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 12.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    . .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER .    . .   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,2]     .D===eeeeeeER  . .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     . D===eeeeeER  . .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
-# CHECK-NEXT: [0,4]     .  D======eeeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeER .    . .   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,2]     .DP==eeeeeeER  . .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     . DPPPeeeeeER  . .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     .  DPPP===eeeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3428,14 +3503,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 11.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   st3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeeeeeER .    ..   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
-# CHECK-NEXT: [0,2]     .D====eeeeeER  ..   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,3]     . D====eeeeeER ..   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
-# CHECK-NEXT: [0,4]     . D=======eeeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,2]     .DP===eeeeeER  ..   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,3]     . DPPPPeeeeeER ..   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPPPP==eeeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3464,14 +3540,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .   st3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,1]     D=eeeeeER .    .   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
-# CHECK-NEXT: [0,2]     .D===eeeeeER   .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D====eeeeeER  .   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
-# CHECK-NEXT: [0,4]     . D======eeeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,1]     DPeeeeeER .    .   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,2]     .DP==eeeeeER   .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .DPPPPeeeeeER  .   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPPP==eeeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3500,14 +3577,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 13.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    ..   st3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeER .    ..   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
-# CHECK-NEXT: [0,2]     .D===eeeeeER   ..   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     . D===eeeeeER  ..   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,4]     .  D=====eeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,1]     DPeeeeeER .    ..   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,2]     .DP==eeeeeER   ..   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     . DPPPeeeeeER  ..   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,4]     .  DPPP==eeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3536,14 +3614,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 24.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeER .    .    . .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
 # CHECK-NEXT: [0,1]     .DeeeeeeeER    .    . .   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,2]     . D====eeeeeeER.    . .   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,3]     .  D=========eeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,4]     .    D========eeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,3]     .  DPPPP=====eeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,4]     .    DPPPPPPPPeeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3572,14 +3651,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 19.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
 # CHECK:      [0,0]     DeeeeeER  .    .    ..   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: [0,1]     .DeeeeeeER.    .    ..   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
 # CHECK-NEXT: [0,2]     . D=====eeeeeeER    ..   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,3]     .  D=====eeeeeeeER  ..   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,4]     .   D=========eeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPeeeeeeeER  ..   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,4]     .   DPPPPP====eeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3608,14 +3688,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 16.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
 # CHECK:      [0,0]     DeeeeeeeER.    .    .  .   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
 # CHECK-NEXT: [0,1]     . DeeeeeeeER   .    .  .   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
 # CHECK-NEXT: [0,2]     .  D=========eeeeeeER  .   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,3]     .  D===========eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,4]     .  D============eeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,3]     .  DPPPPPPPPPP=eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,4]     .  DPPPPPPPPPPPPeeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3644,14 +3725,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   .   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,1]     D=eeeeeeER.   .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,2]     D===eeeeeeER  .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,3]     .D===eeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,4]     .D=====eeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,1]     DPeeeeeeER.   .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,2]     DPP=eeeeeeER  .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
+# CHECK-NEXT: [0,3]     .DPPPeeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,4]     .DPPPP=eeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3680,14 +3762,15 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,1]     D=eeeeeeER.   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,2]     .D==eeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,3]     .D===eeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,4]     . D===eE--R   stg	x26, [x27], #4064
+# CHECK-NEXT: [0,1]     DPeeeeeeER.   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,2]     .DP=eeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
+# CHECK-NEXT: [0,3]     .DPPPeeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,4]     . DPPPeE--R   stg	x26, [x27], #4064
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3716,13 +3799,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   stg	x26, [x27, #4064]!
-# CHECK-NEXT: [0,1]     D=eER.  .   stgp	x1, x2, [x27], #992
-# CHECK-NEXT: [0,2]     D==eER  .   stgp	x1, x2, [x27, #992]!
-# CHECK-NEXT: [0,3]     D===eeER.   stp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,4]     .D===eeER   stp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,1]     DPeER.  .   stgp	x1, x2, [x27], #992
+# CHECK-NEXT: [0,2]     DPPeER  .   stgp	x1, x2, [x27, #992]!
+# CHECK-NEXT: [0,3]     DPPPeeER.   stp	s1, s2, [x27], #248
+# CHECK-NEXT: [0,4]     .DPPPeeER   stp	d1, d2, [x27], #496
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3751,13 +3835,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 3.0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.   .   stp	q1, q2, [x27], #992
-# CHECK-NEXT: [0,1]     D==eeER  .   stp	s1, s2, [x27, #248]!
-# CHECK-NEXT: [0,2]     D===eeER .   stp	d1, d2, [x27, #496]!
-# CHECK-NEXT: [0,3]     .D===eeER.   stp	q1, q2, [x27, #992]!
-# CHECK-NEXT: [0,4]     .D=====eER   stp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,1]     DPPeeER  .   stp	s1, s2, [x27, #248]!
+# CHECK-NEXT: [0,2]     DPPPeeER .   stp	d1, d2, [x27, #496]!
+# CHECK-NEXT: [0,3]     .DPPPeeER.   stp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,4]     .DPPPPPeER   stp	w1, w2, [x27], #248
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3786,13 +3871,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   stp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eER.  .   stp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,2]     D==eER  .   stp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,3]     D===eeER.   str	b1, [x27], #254
-# CHECK-NEXT: [0,4]     .D===eeER   str	h1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeER.  .   stp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,2]     DPPeER  .   stp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,3]     DPPPeeER.   str	b1, [x27], #254
+# CHECK-NEXT: [0,4]     .DPPPeeER   str	h1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3821,13 +3907,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   str	s1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eeER  .   str	d1, [x27], #254
-# CHECK-NEXT: [0,2]     D==eeER .   str	q1, [x27], #254
-# CHECK-NEXT: [0,3]     D===eeER.   str	b1, [x27, #254]!
-# CHECK-NEXT: [0,4]     .D===eeER   str	h1, [x27, #254]!
+# CHECK-NEXT: [0,1]     DPeeER  .   str	d1, [x27], #254
+# CHECK-NEXT: [0,2]     DPPeeER .   str	q1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPPeeER.   str	b1, [x27, #254]!
+# CHECK-NEXT: [0,4]     .DPPPeeER   str	h1, [x27, #254]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3856,13 +3943,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeER. .   str	s1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eeER .   str	d1, [x27, #254]!
-# CHECK-NEXT: [0,2]     D==eeER.   str	q1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D===eER.   str	w1, [x27], #254
-# CHECK-NEXT: [0,4]     .D===eER   str	x1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeeER .   str	d1, [x27, #254]!
+# CHECK-NEXT: [0,2]     DPPeeER.   str	q1, [x27, #254]!
+# CHECK-NEXT: [0,3]     DPPPeER.   str	w1, [x27], #254
+# CHECK-NEXT: [0,4]     .DPPPeER   str	x1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3891,13 +3979,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   str	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER. .   str	x1, [x27, #254]!
-# CHECK-NEXT: [0,2]     D==eER .   strb	w1, [x27], #254
-# CHECK-NEXT: [0,3]     D===eER.   strb	w1, [x27, #254]!
-# CHECK-NEXT: [0,4]     D====eER   strh	w1, [x27], #254
+# CHECK-NEXT: [0,1]     DPeER. .   str	x1, [x27, #254]!
+# CHECK-NEXT: [0,2]     DPPeER .   strb	w1, [x27], #254
+# CHECK-NEXT: [0,3]     DPPPeER.   strb	w1, [x27, #254]!
+# CHECK-NEXT: [0,4]     DPPPPeER   strh	w1, [x27], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3926,13 +4015,14 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   strh	w1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER. .   stz2g	x26, [x27], #4064
-# CHECK-NEXT: [0,2]     D==eER .   stz2g	x26, [x27, #4064]!
-# CHECK-NEXT: [0,3]     D===eER.   stzg	x26, [x27], #4064
-# CHECK-NEXT: [0,4]     D====eER   stzg	x26, [x27, #4064]!
+# CHECK-NEXT: [0,1]     DPeER. .   stz2g	x26, [x27], #4064
+# CHECK-NEXT: [0,2]     DPPeER .   stz2g	x26, [x27, #4064]!
+# CHECK-NEXT: [0,3]     DPPPeER.   stzg	x26, [x27], #4064
+# CHECK-NEXT: [0,4]     DPPPPeER   stzg	x26, [x27, #4064]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3961,11 +4051,12 @@ ldr  x2, [x1], #254
 # CHECK-NEXT: Block RThroughput: 0.7
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   ldr	x1, [x27], #254
-# CHECK-NEXT: [0,1]     D====eeeeER   ldr	x2, [x1], #254
+# CHECK-NEXT: [0,1]     DPPPPeeeeER   ldr	x2, [x1], #254
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/AMDGPU/carried-over.s b/llvm/test/tools/llvm-mca/AMDGPU/carried-over.s
index 4378dc979fc72..1246889f0a549 100644
--- a/llvm/test/tools/llvm-mca/AMDGPU/carried-over.s
+++ b/llvm/test/tools/llvm-mca/AMDGPU/carried-over.s
@@ -60,6 +60,7 @@ v_sub_u32 v5, v1, v2
 # CHECK-NEXT:  -      -      -      -     1.00    -      -     v_sub_u32_e32 v5, v1, v2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DE   .   .   v_pk_mov_b32 v[0:1], v[2:3], v[4:5]
diff --git a/llvm/test/tools/llvm-mca/AMDGPU/gfx10-add-sequence.s b/llvm/test/tools/llvm-mca/AMDGPU/gfx10-add-sequence.s
index 84289299cf192..4634b5a952cd0 100644
--- a/llvm/test/tools/llvm-mca/AMDGPU/gfx10-add-sequence.s
+++ b/llvm/test/tools/llvm-mca/AMDGPU/gfx10-add-sequence.s
@@ -49,6 +49,7 @@ v_add_f32 v2, v1, v0
 # CHECK-NEXT:  -      -      -     1.00    -      -     1.00    -     v_add_f32_e32 v2, v1, v0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/AMDGPU/gfx10-double.s b/llvm/test/tools/llvm-mca/AMDGPU/gfx10-double.s
index 00b429ef6d67d..dfcbd2c26cd95 100644
--- a/llvm/test/tools/llvm-mca/AMDGPU/gfx10-double.s
+++ b/llvm/test/tools/llvm-mca/AMDGPU/gfx10-double.s
@@ -133,6 +133,7 @@ v_sqrt_f64 v[4:5], v[4:5]
 # CHECK-NEXT:  -      -      -     1.00    -     1.00   1.00    -     v_sqrt_f64_e32 v[4:5], v[4:5]
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          01234
 
diff --git a/llvm/test/tools/llvm-mca/AMDGPU/gfx10-trans.s b/llvm/test/tools/llvm-mca/AMDGPU/gfx10-trans.s
index 571f1ef6c7ec0..0d955920ea195 100644
--- a/llvm/test/tools/llvm-mca/AMDGPU/gfx10-trans.s
+++ b/llvm/test/tools/llvm-mca/AMDGPU/gfx10-trans.s
@@ -75,6 +75,7 @@ v_sqrt_f64 v[2:3], v[0:1]
 # CHECK-NEXT:  -      -      -     1.00    -     1.00   1.00    -     v_sqrt_f64_e32 v[2:3], v[0:1]
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 
 # GFX10-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123
 # GFX10-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789
diff --git a/llvm/test/tools/llvm-mca/AMDGPU/gfx11-double.s b/llvm/test/tools/llvm-mca/AMDGPU/gfx11-double.s
index 7516ee97818a0..b9dc0a992b44f 100644
--- a/llvm/test/tools/llvm-mca/AMDGPU/gfx11-double.s
+++ b/llvm/test/tools/llvm-mca/AMDGPU/gfx11-double.s
@@ -133,6 +133,7 @@ v_sqrt_f64 v[4:5], v[4:5]
 # CHECK-NEXT:  -      -      -     1.00    -     1.00   1.00    -     v_sqrt_f64_e32 v[4:5], v[4:5]
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          012345678
 
diff --git a/llvm/test/tools/llvm-mca/AMDGPU/gfx12-pseudo-scalar-trans.s b/llvm/test/tools/llvm-mca/AMDGPU/gfx12-pseudo-scalar-trans.s
index d11b61919b3ce..bd5bf590e3b3e 100644
--- a/llvm/test/tools/llvm-mca/AMDGPU/gfx12-pseudo-scalar-trans.s
+++ b/llvm/test/tools/llvm-mca/AMDGPU/gfx12-pseudo-scalar-trans.s
@@ -69,6 +69,7 @@ v_s_sqrt_f16 s5, s5
 # CHECK-NEXT:  -      -      -     1.00    -     1.00    -     v_s_sqrt_f16 s5, s5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234
 
diff --git a/llvm/test/tools/llvm-mca/AMDGPU/gfx9-retireooo.s b/llvm/test/tools/llvm-mca/AMDGPU/gfx9-retireooo.s
index 706ed36f9e980..87bb85683aa8b 100644
--- a/llvm/test/tools/llvm-mca/AMDGPU/gfx9-retireooo.s
+++ b/llvm/test/tools/llvm-mca/AMDGPU/gfx9-retireooo.s
@@ -147,6 +147,7 @@ s_waitcnt vmcnt(0) lgkmcnt(0)
 # CHECK-NEXT:  -      -      -     1.00    -      -      -     s_waitcnt vmcnt(0) lgkmcnt(0)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/ARM/cortex-a57-carryover.s b/llvm/test/tools/llvm-mca/ARM/cortex-a57-carryover.s
index ec99d704f0e5e..eb5306bea9b7a 100644
--- a/llvm/test/tools/llvm-mca/ARM/cortex-a57-carryover.s
+++ b/llvm/test/tools/llvm-mca/ARM/cortex-a57-carryover.s
@@ -49,6 +49,7 @@
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     nop
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          012
 
@@ -59,19 +60,19 @@
 # CHECK-NEXT: [2,0]     .    .D==eeeeER.    .    .    .    .    . .   pop	{r3, r4, r5, r6, r7, pc}
 # CHECK-NEXT: [2,1]     .    .  DE----R.    .    .    .    .    . .   nop
 # CHECK-NEXT: [3,0]     .    .   D===eeeeER .    .    .    .    . .   pop	{r3, r4, r5, r6, r7, pc}
-# CHECK-NEXT: [3,1]     .    .    .D=E----R .    .    .    .    . .   nop
-# CHECK-NEXT: [4,0]     .    .    . D====eeeeER  .    .    .    . .   pop	{r3, r4, r5, r6, r7, pc}
-# CHECK-NEXT: [4,1]     .    .    .   D==E----R  .    .    .    . .   nop
-# CHECK-NEXT: [5,0]     .    .    .    D=====eeeeER   .    .    . .   pop	{r3, r4, r5, r6, r7, pc}
-# CHECK-NEXT: [5,1]     .    .    .    . D===E----R   .    .    . .   nop
-# CHECK-NEXT: [6,0]     .    .    .    .  D======eeeeER    .    . .   pop	{r3, r4, r5, r6, r7, pc}
-# CHECK-NEXT: [6,1]     .    .    .    .    D====E----R    .    . .   nop
-# CHECK-NEXT: [7,0]     .    .    .    .    .D=======eeeeER.    . .   pop	{r3, r4, r5, r6, r7, pc}
-# CHECK-NEXT: [7,1]     .    .    .    .    .  D=====E----R.    . .   nop
-# CHECK-NEXT: [8,0]     .    .    .    .    .   D========eeeeER . .   pop	{r3, r4, r5, r6, r7, pc}
-# CHECK-NEXT: [8,1]     .    .    .    .    .    .D======E----R . .   nop
-# CHECK-NEXT: [9,0]     .    .    .    .    .    . D=========eeeeER   pop	{r3, r4, r5, r6, r7, pc}
-# CHECK-NEXT: [9,1]     .    .    .    .    .    .   D=======E----R   nop
+# CHECK-NEXT: [3,1]     .    .    .DPE----R .    .    .    .    . .   nop
+# CHECK-NEXT: [4,0]     .    .    . DP===eeeeER  .    .    .    . .   pop	{r3, r4, r5, r6, r7, pc}
+# CHECK-NEXT: [4,1]     .    .    .   DPPE----R  .    .    .    . .   nop
+# CHECK-NEXT: [5,0]     .    .    .    DPP===eeeeER   .    .    . .   pop	{r3, r4, r5, r6, r7, pc}
+# CHECK-NEXT: [5,1]     .    .    .    . DPPPE----R   .    .    . .   nop
+# CHECK-NEXT: [6,0]     .    .    .    .  DPPP===eeeeER    .    . .   pop	{r3, r4, r5, r6, r7, pc}
+# CHECK-NEXT: [6,1]     .    .    .    .    DPPPPE----R    .    . .   nop
+# CHECK-NEXT: [7,0]     .    .    .    .    .DPPPP===eeeeER.    . .   pop	{r3, r4, r5, r6, r7, pc}
+# CHECK-NEXT: [7,1]     .    .    .    .    .  DPPPPPE----R.    . .   nop
+# CHECK-NEXT: [8,0]     .    .    .    .    .   DPPPPP===eeeeER . .   pop	{r3, r4, r5, r6, r7, pc}
+# CHECK-NEXT: [8,1]     .    .    .    .    .    .DPPPPPPE----R . .   nop
+# CHECK-NEXT: [9,0]     .    .    .    .    .    . DPPPPPP===eeeeER   pop	{r3, r4, r5, r6, r7, pc}
+# CHECK-NEXT: [9,1]     .    .    .    .    .    .   DPPPPPPPE----R   nop
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/ARM/m55-storefwd.s b/llvm/test/tools/llvm-mca/ARM/m55-storefwd.s
index 3a744da93cfbf..073c0f89f2570 100644
--- a/llvm/test/tools/llvm-mca/ARM/m55-storefwd.s
+++ b/llvm/test/tools/llvm-mca/ARM/m55-storefwd.s
@@ -160,6 +160,7 @@ vstrb.8 q0, [r0, #0]
 # CHECK-NEXT:  -     2.00    -      -      -     vstrb.8	q0, [r0]
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/ARM/m7-negative-readadvance.s b/llvm/test/tools/llvm-mca/ARM/m7-negative-readadvance.s
index a63e7486bf600..9f78f890c7431 100644
--- a/llvm/test/tools/llvm-mca/ARM/m7-negative-readadvance.s
+++ b/llvm/test/tools/llvm-mca/ARM/m7-negative-readadvance.s
@@ -56,6 +56,7 @@ vldr d0, [r1]
 # CHECK-NEXT:  -      -      -     1.00   1.00    -      -      -      -      -      -     1.00   1.00   vldr	d0, [r1]
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DE   .   add.w	r1, r1, #1
diff --git a/llvm/test/tools/llvm-mca/ARM/memcpy-ldm-stm.s b/llvm/test/tools/llvm-mca/ARM/memcpy-ldm-stm.s
index 865aa7455125b..071215b1382e4 100644
--- a/llvm/test/tools/llvm-mca/ARM/memcpy-ldm-stm.s
+++ b/llvm/test/tools/llvm-mca/ARM/memcpy-ldm-stm.s
@@ -44,15 +44,16 @@
 # CHECK-NEXT:  -      -      -     2.00   1.37   1.63   stm	r0!, {r3, r4, r5, r6, r12, lr}
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeeeeeER    .  .   ldm	r2!, {r3, r4, r5, r6, r12, lr}
-# CHECK-NEXT: [0,1]     .D=================eER   .  .   stm	r0!, {r3, r4, r5, r6, r12, lr}
+# CHECK-NEXT: [0,1]     .DPPPPPPPPPPPPPPPPPeER   .  .   stm	r0!, {r3, r4, r5, r6, r12, lr}
 # CHECK-NEXT: [1,0]     .  DeeeeeeeeeeeeeeeeeeER .  .   ldm	r2!, {r3, r4, r5, r6, r12, lr}
-# CHECK-NEXT: [1,1]     .   D=================eER.  .   stm	r0!, {r3, r4, r5, r6, r12, lr}
+# CHECK-NEXT: [1,1]     .   DPPPPPPPPPPPPPPPPPeER.  .   stm	r0!, {r3, r4, r5, r6, r12, lr}
 # CHECK-NEXT: [2,0]     .    .DeeeeeeeeeeeeeeeeeeER .   ldm	r2!, {r3, r4, r5, r6, r12, lr}
-# CHECK-NEXT: [2,1]     .    . D==================eER   stm	r0!, {r3, r4, r5, r6, r12, lr}
+# CHECK-NEXT: [2,1]     .    . DPPPPPPPPPPPPPPPPP=eER   stm	r0!, {r3, r4, r5, r6, r12, lr}
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/ARM/vld1-index-update.s b/llvm/test/tools/llvm-mca/ARM/vld1-index-update.s
index 776466cd60077..9c047641823b4 100644
--- a/llvm/test/tools/llvm-mca/ARM/vld1-index-update.s
+++ b/llvm/test/tools/llvm-mca/ARM/vld1-index-update.s
@@ -47,19 +47,20 @@ vld1.32	{d16, d17}, [r1]!
 # CHECK-NEXT:  -      -      -     1.00   1.00    -     vld1.32	{d16, d17}, [r1]!
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    .    .   add	r1, r1, r12
-# CHECK-NEXT: [0,1]     D=eeeeER  .    .   vld1.32	{d16, d17}, [r1]!
-# CHECK-NEXT: [1,0]     .D=eE--R  .    .   add	r1, r1, r12
-# CHECK-NEXT: [1,1]     .D==eeeeER.    .   vld1.32	{d16, d17}, [r1]!
-# CHECK-NEXT: [2,0]     . D==eE--R.    .   add	r1, r1, r12
-# CHECK-NEXT: [2,1]     . D===eeeeER   .   vld1.32	{d16, d17}, [r1]!
-# CHECK-NEXT: [3,0]     .  D===eE--R   .   add	r1, r1, r12
-# CHECK-NEXT: [3,1]     .  D====eeeeER .   vld1.32	{d16, d17}, [r1]!
-# CHECK-NEXT: [4,0]     .   D====eE--R .   add	r1, r1, r12
-# CHECK-NEXT: [4,1]     .   D=====eeeeER   vld1.32	{d16, d17}, [r1]!
+# CHECK-NEXT: [0,1]     DPeeeeER  .    .   vld1.32	{d16, d17}, [r1]!
+# CHECK-NEXT: [1,0]     .DPeE--R  .    .   add	r1, r1, r12
+# CHECK-NEXT: [1,1]     .DPPeeeeER.    .   vld1.32	{d16, d17}, [r1]!
+# CHECK-NEXT: [2,0]     . DPPeE--R.    .   add	r1, r1, r12
+# CHECK-NEXT: [2,1]     . DPPPeeeeER   .   vld1.32	{d16, d17}, [r1]!
+# CHECK-NEXT: [3,0]     .  DPPPeE--R   .   add	r1, r1, r12
+# CHECK-NEXT: [3,1]     .  DPPPPeeeeER .   vld1.32	{d16, d17}, [r1]!
+# CHECK-NEXT: [4,0]     .   DPPPPeE--R .   add	r1, r1, r12
+# CHECK-NEXT: [4,1]     .   DPPPPPeeeeER   vld1.32	{d16, d17}, [r1]!
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s b/llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s
index d93129129a176..b52d2d8a4c9b2 100644
--- a/llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s
+++ b/llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s
@@ -105,18 +105,19 @@
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     nop
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.    ..   div	a0, a1, a2
 # CHECK-NEXT: [0,1]     DeeeeE---R.    ..   mul	a4, a1, a2
 # CHECK-NEXT: [0,2]     DeeeeeE--R.    ..   fmul.s	ft1, ft2, ft3
-# CHECK-NEXT: [0,3]     D=======eeeeER ..   lw	a3, 0(a0)
-# CHECK-NEXT: [0,4]     .D==========eeeER   sw	a3, 0(a1)
+# CHECK-NEXT: [0,3]     DPPPPPPPeeeeER ..   lw	a3, 0(a0)
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPeeeER   sw	a3, 0(a1)
 # CHECK-NEXT: [0,5]     .DeE------------R   add	a5, a1, a2
-# CHECK-NEXT: [0,6]     .D=eE-----------R   ror	a6, a5, a2
+# CHECK-NEXT: [0,6]     .DPeE-----------R   ror	a6, a5, a2
 # CHECK-NEXT: [0,7]     .DeE------------R   j	.Lend
-# CHECK-NEXT: [0,8]     . D=====eE------R   add	a7, a4, a0
+# CHECK-NEXT: [0,8]     . DPPPPPeE------R   add	a7, a4, a0
 # CHECK-NEXT: [0,9]     . DE------------R   nop
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFive7/div-fdiv.s b/llvm/test/tools/llvm-mca/RISCV/SiFive7/div-fdiv.s
index cb60d8ea935ad..07afc7eaec3fd 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFive7/div-fdiv.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFive7/div-fdiv.s
@@ -47,6 +47,7 @@ fdiv.s f1, f2, f3
 # CHECK-NEXT: 26.00   -      -     1.00    -      -      -      -     fdiv.s	ft1, ft2, ft3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFive7/gpr-bypass-c.s b/llvm/test/tools/llvm-mca/RISCV/SiFive7/gpr-bypass-c.s
index c7ff5e6a6b9c4..a463bb8e60910 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFive7/gpr-bypass-c.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFive7/gpr-bypass-c.s
@@ -103,6 +103,7 @@ c.jr a0
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     jr	a0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFive7/gpr-bypass.s b/llvm/test/tools/llvm-mca/RISCV/SiFive7/gpr-bypass.s
index 03f7de2fe9a4c..f2dbfee599058 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFive7/gpr-bypass.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFive7/gpr-bypass.s
@@ -322,6 +322,7 @@ jr a0
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     jr	a0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789          012345678
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFive7/jump.s b/llvm/test/tools/llvm-mca/RISCV/SiFive7/jump.s
index f23a9ccfca3be..779152c23e02f 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFive7/jump.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFive7/jump.s
@@ -58,6 +58,7 @@ ret
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     ret
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   j	.Ltmp0
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/different-lmul-instruments.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/different-lmul-instruments.s
index 0e7284fb550af..1faa8ee41d844 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/different-lmul-instruments.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/different-lmul-instruments.s
@@ -54,6 +54,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     17.00  1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/different-sew-instruments.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/different-sew-instruments.s
index b445855ef3c11..ebc3b1ff86433 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/different-sew-instruments.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/different-sew-instruments.s
@@ -55,6 +55,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     115.00 1.00    -      -     vdiv.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   vsetvli	zero, a0, e8, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/disable-im.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/disable-im.s
index 0cd96701fd8f8..5caa4cec362de 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/disable-im.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/disable-im.s
@@ -61,6 +61,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     17.00  1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-at-start.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-at-start.s
index 53d106a327411..c718254c13782 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-at-start.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-at-start.s
@@ -47,6 +47,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     3.00   1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeE . .   vsetvli	zero, a0, e8, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-in-middle.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-in-middle.s
index 2b0e3fa1b8af4..8170beaf555bd 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-in-middle.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-in-middle.s
@@ -50,6 +50,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     2.00   1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-in-region.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-in-region.s
index 308994116ed26..9fa57df507f81 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-in-region.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-in-region.s
@@ -51,6 +51,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     3.00   1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeE . .   vsetvli	zero, a0, e8, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-straddles-region.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-straddles-region.s
index 7c596b16109fb..c1b9f5d47a159 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-straddles-region.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/lmul-instrument-straddles-region.s
@@ -52,6 +52,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     3.00   1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeE . .   vsetvli	zero, a0, e8, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/multiple-same-lmul-instruments.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/multiple-same-lmul-instruments.s
index 680d84e9dc226..998668d685404 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/multiple-same-lmul-instruments.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/multiple-same-lmul-instruments.s
@@ -67,6 +67,7 @@ vsub.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     9.00   1.00    -      -     vsub.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/multiple-same-sew-instruments.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/multiple-same-sew-instruments.s
index 02e1fd72bceea..15fb3becda893 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/multiple-same-sew-instruments.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/multiple-same-sew-instruments.s
@@ -68,6 +68,7 @@ vdivu.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     113.00 1.00    -      -     vdivu.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   vsetvli	zero, a0, e64, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/needs-sew-but-only-lmul.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/needs-sew-but-only-lmul.s
index 2a58ea7962ae8..54e5915b8ce33 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/needs-sew-but-only-lmul.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/needs-sew-but-only-lmul.s
@@ -52,6 +52,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     241.00 1.00    -      -     vdiv.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   vsetvli	zero, a0, e8, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/no-vsetvli-to-start.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/no-vsetvli-to-start.s
index e16b8f982b9c9..5b20d14e3b33e 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/no-vsetvli-to-start.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/no-vsetvli-to-start.s
@@ -49,6 +49,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     3.00   1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-at-start.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-at-start.s
index e9b0ee562a4ce..2ebe55d650006 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-at-start.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-at-start.s
@@ -48,6 +48,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     241.00 1.00    -      -     vdiv.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   vsetvli	zero, a0, e8, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-in-middle.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-in-middle.s
index dbec706866f63..6ccb3d1a1f346 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-in-middle.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-in-middle.s
@@ -30,7 +30,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT: [6]: HasSideEffects (U)
 
 # CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
-# CHECK-NEXT:  1      1920   1920.00                      vdiv.vv	v8, v8, v12
+# CHECK-NEXT:  1      1920  1920.00                     vdiv.vv	v8, v8, v12
 # CHECK-NEXT:  1      3     1.00                  U     vsetvli	zero, a0, e8, m8, tu, mu
 # CHECK-NEXT:  1      912   912.00                      vdiv.vv	v8, v8, v12
 
@@ -55,6 +55,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     913.00 1.00    -      -     vdiv.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0
 # CHECK-NEXT: Truncated display due to cycle limit
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-in-region.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-in-region.s
index 49e639d8c06fd..9dec9ead51392 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-in-region.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-in-region.s
@@ -52,6 +52,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     115.00 1.00    -      -     vdiv.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   vsetvli	zero, a0, e64, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-straddles-region.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-straddles-region.s
index e1e222f7f035c..352b9213bf2ef 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-straddles-region.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/sew-instrument-straddles-region.s
@@ -53,6 +53,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     115.00 1.00    -      -     vdiv.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   vsetvli	zero, a0, e64, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetivli-lmul-instrument.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetivli-lmul-instrument.s
index f39b33fd70f32..6e78aefd21964 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetivli-lmul-instrument.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetivli-lmul-instrument.s
@@ -52,6 +52,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     17.00  1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetivli-lmul-sew-instrument.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetivli-lmul-sew-instrument.s
index 8dc7cac02c885..4f4c37bd26f4f 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetivli-lmul-sew-instrument.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetivli-lmul-sew-instrument.s
@@ -52,6 +52,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     897.00 1.00    -      -     vdiv.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   vsetivli	zero, 8, e8, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetvli-lmul-instrument.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetvli-lmul-instrument.s
index 130bb19280f20..c534705fb54d0 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetvli-lmul-instrument.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetvli-lmul-instrument.s
@@ -52,6 +52,7 @@ vadd.vv v12, v12, v12
 # CHECK-NEXT:  -      -      -      -     17.00  1.00    -      -     vadd.vv	v12, v12, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetvli-lmul-sew-instrument.s b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetvli-lmul-sew-instrument.s
index fe4d3f6169c93..d4ee2ee7c380b 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetvli-lmul-sew-instrument.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SiFiveX280/vsetvli-lmul-sew-instrument.s
@@ -52,6 +52,7 @@ vdiv.vv v8, v8, v12
 # CHECK-NEXT:  -      -      -      -     897.00 1.00    -      -     vdiv.vv	v8, v8, v12
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DeeE   vsetvli	zero, a0, e8, m1, tu, mu
diff --git a/llvm/test/tools/llvm-mca/RISCV/SyntacoreSCR/SCR4_5-FPU.s b/llvm/test/tools/llvm-mca/RISCV/SyntacoreSCR/SCR4_5-FPU.s
index 90fef749a1c3d..b089f52fb49a4 100644
--- a/llvm/test/tools/llvm-mca/RISCV/SyntacoreSCR/SCR4_5-FPU.s
+++ b/llvm/test/tools/llvm-mca/RISCV/SyntacoreSCR/SCR4_5-FPU.s
@@ -115,6 +115,7 @@ fdiv.d ft7, ft7, ft7
 # CHECK-NEXT:    -      -      -     15.00   -      -      -     fdiv.d	ft7, ft7, ft7
 
 # CHECK:        Timeline view:
+# CHECK-NEXT:   D: Instruction dispatched
 # CHECK-NEXT:                       0123456789          0123456789          0123456789
 # CHECK-NEXT:   Index     0123456789          0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/RISCV/XiangShan/gpr-bypass.s b/llvm/test/tools/llvm-mca/RISCV/XiangShan/gpr-bypass.s
index 677fece1535a0..1a5ae3c2767c6 100644
--- a/llvm/test/tools/llvm-mca/RISCV/XiangShan/gpr-bypass.s
+++ b/llvm/test/tools/llvm-mca/RISCV/XiangShan/gpr-bypass.s
@@ -331,100 +331,101 @@ jr a0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -     jr	a0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789          0123456789          0123
 
 # CHECK:      [0,0]     DeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   lui	a0, 1
 # CHECK-NEXT: [0,1]     DeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   auipc	a1, 1
-# CHECK-NEXT: [0,2]     D=eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a1
-# CHECK-NEXT: [0,3]     D==eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   addi	a0, a0, 1
-# CHECK-NEXT: [0,4]     D===eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   addw	a0, a0, a0
-# CHECK-NEXT: [0,5]     D====eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   addiw	a0, a0, 1
-# CHECK-NEXT: [0,6]     .D====eER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sub	a0, a0, a0
-# CHECK-NEXT: [0,7]     .D=====eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   subw	a0, a0, a0
-# CHECK-NEXT: [0,8]     .D======eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   and	a0, a0, a0
-# CHECK-NEXT: [0,9]     .D=======eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   andi	a0, a0, 1
-# CHECK-NEXT: [0,10]    .D========eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   or	a0, a0, a0
-# CHECK-NEXT: [0,11]    .D=========eER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   ori	a0, a0, 1
-# CHECK-NEXT: [0,12]    . D=========eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   xor	a0, a0, a0
-# CHECK-NEXT: [0,13]    . D==========eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   xori	a0, a0, 1
-# CHECK-NEXT: [0,14]    . D===========eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sll	a0, a0, a0
-# CHECK-NEXT: [0,15]    . D============eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slli	a0, a0, 1
-# CHECK-NEXT: [0,16]    . D=============eER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sllw	a0, a0, a0
-# CHECK-NEXT: [0,17]    . D==============eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slliw	a0, a0, 1
-# CHECK-NEXT: [0,18]    .  D==============eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srl	a0, a0, a0
-# CHECK-NEXT: [0,19]    .  D===============eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srli	a0, a0, 1
-# CHECK-NEXT: [0,20]    .   D===============eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srlw	a0, a0, a0
-# CHECK-NEXT: [0,21]    .    D===============eER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srliw	a0, a0, 1
-# CHECK-NEXT: [0,22]    .    .D===============eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sra	a0, a0, a0
-# CHECK-NEXT: [0,23]    .    . D===============eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srai	a0, a0, 1
-# CHECK-NEXT: [0,24]    .    .  D===============eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sraw	a0, a0, a0
-# CHECK-NEXT: [0,25]    .    .   D===============eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sraiw	a0, a0, 1
-# CHECK-NEXT: [0,26]    .    .    D===============eER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slt	a0, a0, a0
-# CHECK-NEXT: [0,27]    .    .    .D===============eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slti	a0, a0, 1
-# CHECK-NEXT: [0,28]    .    .    . D===============eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sltu	a0, a0, a0
-# CHECK-NEXT: [0,29]    .    .    .  D===============eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   seqz	a0, a0
-# CHECK-NEXT: [0,30]    .    .    .  D================eeeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   mul	a0, a0, a0
-# CHECK-NEXT: [0,31]    .    .    .   D==================eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,32]    .    .    .   D===================eeeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   mulw	a0, a0, a0
-# CHECK-NEXT: [0,33]    .    .    .    D=====================eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,34]    .    .    .    D======================eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   beq	a0, a0, .Ltmp0
-# CHECK-NEXT: [0,35]    .    .    .    .D=====================eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,36]    .    .    .    .D======================eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   bne	a0, a0, .Ltmp1
-# CHECK-NEXT: [0,37]    .    .    .    . D=====================eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,38]    .    .    .    . D======================eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   blt	a0, a0, .Ltmp2
-# CHECK-NEXT: [0,39]    .    .    .    .  D=====================eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,40]    .    .    .    .  D======================eER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   bltu	a0, a0, .Ltmp3
-# CHECK-NEXT: [0,41]    .    .    .    .   D=====================eER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,42]    .    .    .    .   D======================eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   bge	a0, a0, .Ltmp4
-# CHECK-NEXT: [0,43]    .    .    .    .    D=====================eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,44]    .    .    .    .    D======================eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   bgeu	a0, a0, .Ltmp5
-# CHECK-NEXT: [0,45]    .    .    .    .    .D=====================eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add.uw	a0, a0, a0
-# CHECK-NEXT: [0,46]    .    .    .    .    . D=====================eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slli.uw	a0, a0, 1
-# CHECK-NEXT: [0,47]    .    .    .    .    .  D=====================eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh1add.uw	a0, a0, a0
-# CHECK-NEXT: [0,48]    .    .    .    .    .   D=====================eER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh2add.uw	a0, a0, a0
-# CHECK-NEXT: [0,49]    .    .    .    .    .    D=====================eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh3add.uw	a0, a0, a0
-# CHECK-NEXT: [0,50]    .    .    .    .    .    .D=====================eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh1add	a0, a0, a0
-# CHECK-NEXT: [0,51]    .    .    .    .    .    . D=====================eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh2add	a0, a0, a0
-# CHECK-NEXT: [0,52]    .    .    .    .    .    .  D=====================eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh3add	a0, a0, a0
-# CHECK-NEXT: [0,53]    .    .    .    .    .    .   D=====================eER .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   andn	a0, a0, a0
-# CHECK-NEXT: [0,54]    .    .    .    .    .    .    .  D==================eER.    .    .    .    .    .    .    .    .    .    .    .    .    .  .   orn	a0, a0, a0
-# CHECK-NEXT: [0,55]    .    .    .    .    .    .    .    . D===============eER    .    .    .    .    .    .    .    .    .    .    .    .    .  .   xnor	a0, a0, a0
-# CHECK-NEXT: [0,56]    .    .    .    .    .    .    .    .  D===============eER   .    .    .    .    .    .    .    .    .    .    .    .    .  .   sext.b	a0, a0
-# CHECK-NEXT: [0,57]    .    .    .    .    .    .    .    .   D===============eER  .    .    .    .    .    .    .    .    .    .    .    .    .  .   sext.h	a0, a0
-# CHECK-NEXT: [0,58]    .    .    .    .    .    .    .    .    D===============eER .    .    .    .    .    .    .    .    .    .    .    .    .  .   zext.h	a0, a0
-# CHECK-NEXT: [0,59]    .    .    .    .    .    .    .    .    .D===============eER.    .    .    .    .    .    .    .    .    .    .    .    .  .   min	a0, a0, a0
-# CHECK-NEXT: [0,60]    .    .    .    .    .    .    .    .    . D===============eER    .    .    .    .    .    .    .    .    .    .    .    .  .   minu	a0, a0, a0
-# CHECK-NEXT: [0,61]    .    .    .    .    .    .    .    .    .  D===============eER   .    .    .    .    .    .    .    .    .    .    .    .  .   max	a0, a0, a0
-# CHECK-NEXT: [0,62]    .    .    .    .    .    .    .    .    .   D===============eER  .    .    .    .    .    .    .    .    .    .    .    .  .   maxu	a0, a0, a0
-# CHECK-NEXT: [0,63]    .    .    .    .    .    .    .    .    .    D===============eER .    .    .    .    .    .    .    .    .    .    .    .  .   rol	a0, a0, a0
-# CHECK-NEXT: [0,64]    .    .    .    .    .    .    .    .    .    .D===============eER.    .    .    .    .    .    .    .    .    .    .    .  .   ror	a0, a0, a0
-# CHECK-NEXT: [0,65]    .    .    .    .    .    .    .    .    .    . D===============eER    .    .    .    .    .    .    .    .    .    .    .  .   rori	a0, a0, 1
-# CHECK-NEXT: [0,66]    .    .    .    .    .    .    .    .    .    . D================eeeER .    .    .    .    .    .    .    .    .    .    .  .   clz	a0, a0
-# CHECK-NEXT: [0,67]    .    .    .    .    .    .    .    .    .    . D===================eeeER   .    .    .    .    .    .    .    .    .    .  .   clzw	a0, a0
-# CHECK-NEXT: [0,68]    .    .    .    .    .    .    .    .    .    . D======================eeeER.    .    .    .    .    .    .    .    .    .  .   ctz	a0, a0
-# CHECK-NEXT: [0,69]    .    .    .    .    .    .    .    .    .    . D=========================eeeER  .    .    .    .    .    .    .    .    .  .   ctzw	a0, a0
-# CHECK-NEXT: [0,70]    .    .    .    .    .    .    .    .    .    . D============================eeeER    .    .    .    .    .    .    .    .  .   cpop	a0, a0
-# CHECK-NEXT: [0,71]    .    .    .    .    .    .    .    .    .    .  D==============================eER   .    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,72]    .    .    .    .    .    .    .    .    .    .  D===============================eeeER.    .    .    .    .    .    .    .  .   cpopw	a0, a0
-# CHECK-NEXT: [0,73]    .    .    .    .    .    .    .    .    .    .   D=================================eER    .    .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,74]    .    .    .    .    .    .    .    .    .    .    D=================================eER   .    .    .    .    .    .    .  .   rev8	a0, a0
-# CHECK-NEXT: [0,75]    .    .    .    .    .    .    .    .    .    .    .D=================================eER  .    .    .    .    .    .    .  .   orc.b	a0, a0
-# CHECK-NEXT: [0,76]    .    .    .    .    .    .    .    .    .    .    .D==================================eeeeeER  .    .    .    .    .    .  .   lb	a0, 0(a0)
-# CHECK-NEXT: [0,77]    .    .    .    .    .    .    .    .    .    .    . D=====================================eER  .    .    .    .    .    .  .   add	a0, a0, a0
-# CHECK-NEXT: [0,78]    .    .    .    .    .    .    .    .    .    .    . D======================================eeeeeER  .    .    .    .    .  .   lh	a0, 0(a0)
-# CHECK-NEXT: [0,79]    .    .    .    .    .    .    .    .    .    .    .  D=========================================eER  .    .    .    .    .  .   and	a0, a0, a0
-# CHECK-NEXT: [0,80]    .    .    .    .    .    .    .    .    .    .    .  D==========================================eeeeeER  .    .    .    .  .   lw	a0, 0(a0)
-# CHECK-NEXT: [0,81]    .    .    .    .    .    .    .    .    .    .    .   D=============================================eER  .    .    .    .  .   or	a0, a0, a0
-# CHECK-NEXT: [0,82]    .    .    .    .    .    .    .    .    .    .    .   D==============================================eeeeeER  .    .    .  .   ld	a0, 0(a0)
-# CHECK-NEXT: [0,83]    .    .    .    .    .    .    .    .    .    .    .    D=================================================eER  .    .    .  .   xor	a0, a0, a0
-# CHECK-NEXT: [0,84]    .    .    .    .    .    .    .    .    .    .    .    D==================================================eeeeeER  .    .  .   lbu	a0, 0(a0)
-# CHECK-NEXT: [0,85]    .    .    .    .    .    .    .    .    .    .    .    .D=====================================================eER  .    .  .   addi	a0, a0, 1
-# CHECK-NEXT: [0,86]    .    .    .    .    .    .    .    .    .    .    .    .D======================================================eeeeeER  .  .   lhu	a0, 0(a0)
-# CHECK-NEXT: [0,87]    .    .    .    .    .    .    .    .    .    .    .    . D=========================================================eER  .  .   sub	a0, a0, a0
-# CHECK-NEXT: [0,88]    .    .    .    .    .    .    .    .    .    .    .    . D==========================================================eeeeeER.   lwu	a0, 0(a0)
-# CHECK-NEXT: [0,89]    .    .    .    .    .    .    .    .    .    .    .    .  D=============================================================eER.   addw	a0, a0, a0
-# CHECK-NEXT: [0,90]    .    .    .    .    .    .    .    .    .    .    .    .  D==============================================================eER   jr	a0
+# CHECK-NEXT: [0,2]     DPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a1
+# CHECK-NEXT: [0,3]     DPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   addi	a0, a0, 1
+# CHECK-NEXT: [0,4]     DPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   addw	a0, a0, a0
+# CHECK-NEXT: [0,5]     DPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   addiw	a0, a0, 1
+# CHECK-NEXT: [0,6]     .DPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sub	a0, a0, a0
+# CHECK-NEXT: [0,7]     .DPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   subw	a0, a0, a0
+# CHECK-NEXT: [0,8]     .DPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   and	a0, a0, a0
+# CHECK-NEXT: [0,9]     .DPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   andi	a0, a0, 1
+# CHECK-NEXT: [0,10]    .DPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   or	a0, a0, a0
+# CHECK-NEXT: [0,11]    .DPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   ori	a0, a0, 1
+# CHECK-NEXT: [0,12]    . DPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   xor	a0, a0, a0
+# CHECK-NEXT: [0,13]    . DPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   xori	a0, a0, 1
+# CHECK-NEXT: [0,14]    . DPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sll	a0, a0, a0
+# CHECK-NEXT: [0,15]    . DPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slli	a0, a0, 1
+# CHECK-NEXT: [0,16]    . DPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sllw	a0, a0, a0
+# CHECK-NEXT: [0,17]    . DPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slliw	a0, a0, 1
+# CHECK-NEXT: [0,18]    .  DPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srl	a0, a0, a0
+# CHECK-NEXT: [0,19]    .  DPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srli	a0, a0, 1
+# CHECK-NEXT: [0,20]    .   DPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srlw	a0, a0, a0
+# CHECK-NEXT: [0,21]    .    DPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srliw	a0, a0, 1
+# CHECK-NEXT: [0,22]    .    .DPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sra	a0, a0, a0
+# CHECK-NEXT: [0,23]    .    . DPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   srai	a0, a0, 1
+# CHECK-NEXT: [0,24]    .    .  DPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sraw	a0, a0, a0
+# CHECK-NEXT: [0,25]    .    .   DPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sraiw	a0, a0, 1
+# CHECK-NEXT: [0,26]    .    .    DPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slt	a0, a0, a0
+# CHECK-NEXT: [0,27]    .    .    .DPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slti	a0, a0, 1
+# CHECK-NEXT: [0,28]    .    .    . DPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sltu	a0, a0, a0
+# CHECK-NEXT: [0,29]    .    .    .  DPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   seqz	a0, a0
+# CHECK-NEXT: [0,30]    .    .    .  DPPPPPPPPPPPPPPPPeeeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   mul	a0, a0, a0
+# CHECK-NEXT: [0,31]    .    .    .   DPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,32]    .    .    .   DPPPPPPPPPPPPPPPPPPPeeeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   mulw	a0, a0, a0
+# CHECK-NEXT: [0,33]    .    .    .    DPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,34]    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   beq	a0, a0, .Ltmp0
+# CHECK-NEXT: [0,35]    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,36]    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   bne	a0, a0, .Ltmp1
+# CHECK-NEXT: [0,37]    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,38]    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   blt	a0, a0, .Ltmp2
+# CHECK-NEXT: [0,39]    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,40]    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   bltu	a0, a0, .Ltmp3
+# CHECK-NEXT: [0,41]    .    .    .    .   DPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,42]    .    .    .    .   DPPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   bge	a0, a0, .Ltmp4
+# CHECK-NEXT: [0,43]    .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,44]    .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   bgeu	a0, a0, .Ltmp5
+# CHECK-NEXT: [0,45]    .    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   add.uw	a0, a0, a0
+# CHECK-NEXT: [0,46]    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   slli.uw	a0, a0, 1
+# CHECK-NEXT: [0,47]    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh1add.uw	a0, a0, a0
+# CHECK-NEXT: [0,48]    .    .    .    .    .   DPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh2add.uw	a0, a0, a0
+# CHECK-NEXT: [0,49]    .    .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh3add.uw	a0, a0, a0
+# CHECK-NEXT: [0,50]    .    .    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh1add	a0, a0, a0
+# CHECK-NEXT: [0,51]    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh2add	a0, a0, a0
+# CHECK-NEXT: [0,52]    .    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   sh3add	a0, a0, a0
+# CHECK-NEXT: [0,53]    .    .    .    .    .    .   DPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .  .   andn	a0, a0, a0
+# CHECK-NEXT: [0,54]    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .  .   orn	a0, a0, a0
+# CHECK-NEXT: [0,55]    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .  .   xnor	a0, a0, a0
+# CHECK-NEXT: [0,56]    .    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .  .   sext.b	a0, a0
+# CHECK-NEXT: [0,57]    .    .    .    .    .    .    .    .   DPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .  .   sext.h	a0, a0
+# CHECK-NEXT: [0,58]    .    .    .    .    .    .    .    .    DPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .  .   zext.h	a0, a0
+# CHECK-NEXT: [0,59]    .    .    .    .    .    .    .    .    .DPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .  .   min	a0, a0, a0
+# CHECK-NEXT: [0,60]    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .  .   minu	a0, a0, a0
+# CHECK-NEXT: [0,61]    .    .    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .  .   max	a0, a0, a0
+# CHECK-NEXT: [0,62]    .    .    .    .    .    .    .    .    .   DPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .  .   maxu	a0, a0, a0
+# CHECK-NEXT: [0,63]    .    .    .    .    .    .    .    .    .    DPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .  .   rol	a0, a0, a0
+# CHECK-NEXT: [0,64]    .    .    .    .    .    .    .    .    .    .DPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .  .   ror	a0, a0, a0
+# CHECK-NEXT: [0,65]    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .  .   rori	a0, a0, 1
+# CHECK-NEXT: [0,66]    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPeeeER .    .    .    .    .    .    .    .    .    .    .  .   clz	a0, a0
+# CHECK-NEXT: [0,67]    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPeeeER   .    .    .    .    .    .    .    .    .    .  .   clzw	a0, a0
+# CHECK-NEXT: [0,68]    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPeeeER.    .    .    .    .    .    .    .    .    .  .   ctz	a0, a0
+# CHECK-NEXT: [0,69]    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPeeeER  .    .    .    .    .    .    .    .    .  .   ctzw	a0, a0
+# CHECK-NEXT: [0,70]    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeER    .    .    .    .    .    .    .    .  .   cpop	a0, a0
+# CHECK-NEXT: [0,71]    .    .    .    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,72]    .    .    .    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeER.    .    .    .    .    .    .    .  .   cpopw	a0, a0
+# CHECK-NEXT: [0,73]    .    .    .    .    .    .    .    .    .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,74]    .    .    .    .    .    .    .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .  .   rev8	a0, a0
+# CHECK-NEXT: [0,75]    .    .    .    .    .    .    .    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .  .   orc.b	a0, a0
+# CHECK-NEXT: [0,76]    .    .    .    .    .    .    .    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    .    .    .    .  .   lb	a0, 0(a0)
+# CHECK-NEXT: [0,77]    .    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .  .   add	a0, a0, a0
+# CHECK-NEXT: [0,78]    .    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    .    .    .  .   lh	a0, 0(a0)
+# CHECK-NEXT: [0,79]    .    .    .    .    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .  .   and	a0, a0, a0
+# CHECK-NEXT: [0,80]    .    .    .    .    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    .    .  .   lw	a0, 0(a0)
+# CHECK-NEXT: [0,81]    .    .    .    .    .    .    .    .    .    .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .  .   or	a0, a0, a0
+# CHECK-NEXT: [0,82]    .    .    .    .    .    .    .    .    .    .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    .  .   ld	a0, 0(a0)
+# CHECK-NEXT: [0,83]    .    .    .    .    .    .    .    .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .  .   xor	a0, a0, a0
+# CHECK-NEXT: [0,84]    .    .    .    .    .    .    .    .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    .  .   lbu	a0, 0(a0)
+# CHECK-NEXT: [0,85]    .    .    .    .    .    .    .    .    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .  .   addi	a0, a0, 1
+# CHECK-NEXT: [0,86]    .    .    .    .    .    .    .    .    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .  .   lhu	a0, 0(a0)
+# CHECK-NEXT: [0,87]    .    .    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .  .   sub	a0, a0, a0
+# CHECK-NEXT: [0,88]    .    .    .    .    .    .    .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER.   lwu	a0, 0(a0)
+# CHECK-NEXT: [0,89]    .    .    .    .    .    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.   addw	a0, a0, a0
+# CHECK-NEXT: [0,90]    .    .    .    .    .    .    .    .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   jr	a0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/RISCV/XiangShan/load-to-alu.s b/llvm/test/tools/llvm-mca/RISCV/XiangShan/load-to-alu.s
index e1925e7647e33..479500c03886b 100644
--- a/llvm/test/tools/llvm-mca/RISCV/XiangShan/load-to-alu.s
+++ b/llvm/test/tools/llvm-mca/RISCV/XiangShan/load-to-alu.s
@@ -56,10 +56,11 @@ addi a2, a1, 1
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -     addi	a2, a1, 1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeeeER   ld	a1, 0(a0)
-# CHECK-NEXT: [0,1]     D====eER   addi	a2, a1, 1
+# CHECK-NEXT: [0,1]     DPPPPeER   addi	a2, a1, 1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/SystemZ/stm-lm.s b/llvm/test/tools/llvm-mca/SystemZ/stm-lm.s
index a4b5190c32ec7..31940fe0626f2 100644
--- a/llvm/test/tools/llvm-mca/SystemZ/stm-lm.s
+++ b/llvm/test/tools/llvm-mca/SystemZ/stm-lm.s
@@ -51,15 +51,16 @@ lmg	%r6, %r15, 48(%r15)
 # CHECK-NEXT:  -      -      -      -     0.10   4.90    -      -      -      -      -      -      -     lmg	%r6, %r15, 48(%r15)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeER .    .    .    .    .    .  .   stmg	%r6, %r15, 48(%r15)
 # CHECK-NEXT: [0,1]     .DeeeeeeeeeeER .    .    .    .  .   lmg	%r6, %r15, 48(%r15)
-# CHECK-NEXT: [1,0]     . D=========eER.    .    .    .  .   stmg	%r6, %r15, 48(%r15)
-# CHECK-NEXT: [1,1]     .  D========eeeeeeeeeeER .    .  .   lmg	%r6, %r15, 48(%r15)
-# CHECK-NEXT: [2,0]     .   D=================eER.    .  .   stmg	%r6, %r15, 48(%r15)
-# CHECK-NEXT: [2,1]     .    D================eeeeeeeeeeER   lmg	%r6, %r15, 48(%r15)
+# CHECK-NEXT: [1,0]     . DPPPPPPPPPeER.    .    .    .  .   stmg	%r6, %r15, 48(%r15)
+# CHECK-NEXT: [1,1]     .  DPPPPPPPPeeeeeeeeeeER .    .  .   lmg	%r6, %r15, 48(%r15)
+# CHECK-NEXT: [2,0]     .   DPPPPPPPPPPPPPPPPPeER.    .  .   stmg	%r6, %r15, 48(%r15)
+# CHECK-NEXT: [2,1]     .    DPPPPPPPPPPPPPPPPeeeeeeeeeeER   lmg	%r6, %r15, 48(%r15)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/AlderlakeP/independent-load-stores.s b/llvm/test/tools/llvm-mca/X86/AlderlakeP/independent-load-stores.s
index f70ce42d115f2..5ce0f5179b49f 100644
--- a/llvm/test/tools/llvm-mca/X86/AlderlakeP/independent-load-stores.s
+++ b/llvm/test/tools/llvm-mca/X86/AlderlakeP/independent-load-stores.s
@@ -84,6 +84,7 @@
 # ALL-NEXT:      1.00    -     0.33   0.33   1.00    -      -     1.00    -      -     0.34    -      -     addq	$44, 640(%r14)
 
 # ALL:           Timeline view:
+# ALL-NEXT:      D: Instruction dispatched
 
 # NOALIAS-NEXT:                      0123456789
 # NOALIAS-NEXT:  Index     0123456789          0123
@@ -103,11 +104,11 @@
 # NOALIAS-NEXT:  [0,9]     .    .   DeeeeeeeeeeeeER   addq	$44, 640(%r14)
 
 # YESALIAS:      [0,0]     DeeeeeeeeeeeeER.    .    .    .    .    .    .    .    .    .    .    .   .   addq	$44, 64(%r14)
-# YESALIAS-NEXT: [0,1]     .D===========eeeeeeeeeeeeER   .    .    .    .    .    .    .    .    .   .   addq	$44, 128(%r14)
-# YESALIAS-NEXT: [0,2]     . D======================eeeeeeeeeeeeER .    .    .    .    .    .    .   .   addq	$44, 192(%r14)
-# YESALIAS-NEXT: [0,3]     .  D=================================eeeeeeeeeeeeER    .    .    .    .   .   addq	$44, 256(%r14)
-# YESALIAS-NEXT: [0,4]     .   D============================================eeeeeeeeeeeeER  .    .   .   addq	$44, 320(%r14)
-# YESALIAS-NEXT: [0,5]     .    D=======================================================eeeeeeeeeeeeER   addq	$44, 384(%r14)
+# YESALIAS-NEXT: [0,1]     .DPPPPPPPPPPPeeeeeeeeeeeeER   .    .    .    .    .    .    .    .    .   .   addq	$44, 128(%r14)
+# YESALIAS-NEXT: [0,2]     . DPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeER .    .    .    .    .    .    .   .   addq	$44, 192(%r14)
+# YESALIAS-NEXT: [0,3]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeER    .    .    .    .   .   addq	$44, 256(%r14)
+# YESALIAS-NEXT: [0,4]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeER  .    .   .   addq	$44, 320(%r14)
+# YESALIAS-NEXT: [0,5]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeER   addq	$44, 384(%r14)
 # YESALIAS-NEXT: Truncated display due to cycle limit
 
 # ALL:           Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/AlderlakeP/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/AlderlakeP/zero-idioms.s
index 66f647b1978f0..1e3430755f83f 100644
--- a/llvm/test/tools/llvm-mca/X86/AlderlakeP/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/AlderlakeP/zero-idioms.s
@@ -316,92 +316,93 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT:  -     1.00    -      -      -      -      -      -      -      -      -      -      -     vpxor	%ymm3, %ymm3, %ymm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeER .    .    .    .    .    .  .   subl	%eax, %eax
-# CHECK-NEXT: [0,1]     D=eER.    .    .    .    .    .  .   subq	%rax, %rax
-# CHECK-NEXT: [0,2]     D==eeER   .    .    .    .    .  .   xorl	%eax, %eax
-# CHECK-NEXT: [0,3]     D====eeER .    .    .    .    .  .   xorq	%rax, %rax
+# CHECK-NEXT: [0,1]     DPeER.    .    .    .    .    .  .   subq	%rax, %rax
+# CHECK-NEXT: [0,2]     DPPeeER   .    .    .    .    .  .   xorl	%eax, %eax
+# CHECK-NEXT: [0,3]     DPPPPeeER .    .    .    .    .  .   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     DeE-----R .    .    .    .    .  .   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     D=eE----R .    .    .    .    .  .   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D=eE---R .    .    .    .    .  .   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     DPeE----R .    .    .    .    .  .   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPeE---R .    .    .    .    .  .   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .DeE----R .    .    .    .    .  .   pcmpgtb	%xmm2, %xmm2
-# CHECK-NEXT: [0,8]     .D=eE---R .    .    .    .    .  .   pcmpgtd	%xmm2, %xmm2
-# CHECK-NEXT: [0,9]     .D==eeeER .    .    .    .    .  .   pcmpgtq	%xmm2, %xmm2
-# CHECK-NEXT: [0,10]    .D=====eER.    .    .    .    .  .   pcmpgtw	%xmm2, %xmm2
+# CHECK-NEXT: [0,8]     .DPeE---R .    .    .    .    .  .   pcmpgtd	%xmm2, %xmm2
+# CHECK-NEXT: [0,9]     .DPPeeeER .    .    .    .    .  .   pcmpgtq	%xmm2, %xmm2
+# CHECK-NEXT: [0,10]    .DPPPPPeER.    .    .    .    .  .   pcmpgtw	%xmm2, %xmm2
 # CHECK-NEXT: [0,11]    .D==eE---R.    .    .    .    .  .   vpcmpgtb	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,12]    . D==eE--R.    .    .    .    .  .   vpcmpgtd	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,13]    . D===eeeER    .    .    .    .  .   vpcmpgtq	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,14]    . D======eER   .    .    .    .  .   vpcmpgtw	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,15]    . D=======eER  .    .    .    .  .   vpcmpgtb	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,16]    . D=======eER  .    .    .    .  .   vpcmpgtd	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,17]    . D=======eeeER.    .    .    .  .   vpcmpgtq	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,18]    .  D=======eE-R.    .    .    .  .   vpcmpgtw	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,19]    .  D=======eE-R.    .    .    .  .   vpcmpgtb	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,20]    .  D========eER.    .    .    .  .   vpcmpgtd	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,21]    .  D=========eeeER  .    .    .  .   vpcmpgtq	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,22]    .  D============eER .    .    .  .   vpcmpgtw	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,23]    .  D=============eER.    .    .  .   vpcmpgtb	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,24]    .   D============eER.    .    .  .   vpcmpgtd	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,25]    .   D============eeeER   .    .  .   vpcmpgtq	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,26]    .   D=============eE-R   .    .  .   vpcmpgtw	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,12]    . DPPeE--R.    .    .    .    .  .   vpcmpgtd	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,13]    . DPPPeeeER    .    .    .    .  .   vpcmpgtq	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,14]    . DPPPPPPeER   .    .    .    .  .   vpcmpgtw	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,15]    . DPPPPPPPeER  .    .    .    .  .   vpcmpgtb	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,16]    . DPPPPPPPeER  .    .    .    .  .   vpcmpgtd	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,17]    . DPPPPPPPeeeER.    .    .    .  .   vpcmpgtq	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,18]    .  DPPPPPP=eE-R.    .    .    .  .   vpcmpgtw	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,19]    .  DPPPPPP=eE-R.    .    .    .  .   vpcmpgtb	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,20]    .  DPPPPPPPPeER.    .    .    .  .   vpcmpgtd	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,21]    .  DPPPPPPPPPeeeER  .    .    .  .   vpcmpgtq	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,22]    .  DPPPPPPPPPPPPeER .    .    .  .   vpcmpgtw	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,23]    .  DPPPPPPPPPPPPPeER.    .    .  .   vpcmpgtb	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,24]    .   DPPPPPPPPPPPPeER.    .    .  .   vpcmpgtd	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,25]    .   DPPPPPPPPPPPPeeeER   .    .  .   vpcmpgtq	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,26]    .   DPPPPPPPPPPPP=eE-R   .    .  .   vpcmpgtw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,27]    .   DeE--------------R   .    .  .   psubb	%mm2, %mm2
-# CHECK-NEXT: [0,28]    .   D=eE-------------R   .    .  .   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,29]    .   D==eE------------R   .    .  .   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    D==eE-----------R   .    .  .   psubw	%mm2, %mm2
-# CHECK-NEXT: [0,31]    .    D==eE-----------R   .    .  .   psubb	%xmm2, %xmm2
-# CHECK-NEXT: [0,32]    .    D===eE----------R   .    .  .   psubd	%xmm2, %xmm2
-# CHECK-NEXT: [0,33]    .    D=====eE--------R   .    .  .   psubq	%xmm2, %xmm2
-# CHECK-NEXT: [0,34]    .    D======eE-------R   .    .  .   psubw	%xmm2, %xmm2
-# CHECK-NEXT: [0,35]    .    D============eE-R   .    .  .   vpsubb	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,36]    .    .D============eER   .    .  .   vpsubd	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,37]    .    .D=============eER  .    .  .   vpsubq	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,38]    .    .D==============eER .    .  .   vpsubw	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,39]    .    .D===============eER.    .  .   vpsubb	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,40]    .    .D================eER    .  .   vpsubd	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,41]    .    .D=================eER   .  .   vpsubq	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,42]    .    . D=================eER  .  .   vpsubw	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,43]    .    . D==================eER .  .   vpsubb	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,44]    .    . D==================eER .  .   vpsubd	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,45]    .    . D==================eER .  .   vpsubq	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,46]    .    . D===================eER.  .   vpsubw	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,47]    .    . D===================eER.  .   vpsubb	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,48]    .    .  D==================eER.  .   vpsubd	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,49]    .    .  D===================eER  .   vpsubq	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,50]    .    .  D===================eER  .   vpsubw	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,28]    .   DPeE-------------R   .    .  .   psubd	%mm2, %mm2
+# CHECK-NEXT: [0,29]    .   DPPeE------------R   .    .  .   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    DPPeE-----------R   .    .  .   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,31]    .    DPPeE-----------R   .    .  .   psubb	%xmm2, %xmm2
+# CHECK-NEXT: [0,32]    .    DPPPeE----------R   .    .  .   psubd	%xmm2, %xmm2
+# CHECK-NEXT: [0,33]    .    DPPPP=eE--------R   .    .  .   psubq	%xmm2, %xmm2
+# CHECK-NEXT: [0,34]    .    DPPPPPPeE-------R   .    .  .   psubw	%xmm2, %xmm2
+# CHECK-NEXT: [0,35]    .    DPPPPPPPPPPP=eE-R   .    .  .   vpsubb	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,36]    .    .DPPPPPPPPPPPPeER   .    .  .   vpsubd	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,37]    .    .DPPPPPPPPPPPPPeER  .    .  .   vpsubq	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,38]    .    .DPPPPPPPPPPPPPPeER .    .  .   vpsubw	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,39]    .    .DPPPPPPPPPPPPPPPeER.    .  .   vpsubb	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,40]    .    .DPPPPPPPPPPPPPPPPeER    .  .   vpsubd	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,41]    .    .DPPPPPPPPPPPPPPPPPeER   .  .   vpsubq	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,42]    .    . DPPPPPPPPPPPPPPPPPeER  .  .   vpsubw	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,43]    .    . DPPPPPPPPPPPPPPPPPPeER .  .   vpsubb	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,44]    .    . DPPPPPPPPPPPPPPPPPPeER .  .   vpsubd	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,45]    .    . DPPPPPPPPPPPPPPPPPPeER .  .   vpsubq	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,46]    .    . DPPPPPPPPPPPPPPPPPP=eER.  .   vpsubw	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,47]    .    . DPPPPPPPPPPPPPPPPPP=eER.  .   vpsubb	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,48]    .    .  DPPPPPPPPPPPPPPPPP=eER.  .   vpsubd	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,49]    .    .  DPPPPPPPPPPPPPPPPP==eER  .   vpsubq	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,50]    .    .  DPPPPPPPPPPPPPPPPP==eER  .   vpsubw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,51]    .    .  DeE-------------------R  .   andnps	%xmm0, %xmm0
 # CHECK-NEXT: [0,52]    .    .  D===eE----------------R  .   andnpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,53]    .    .  D====eE---------------R  .   vandnps	%xmm2, %xmm2, %xmm2
-# CHECK-NEXT: [0,54]    .    .   D===eE---------------R  .   vandnpd	%xmm1, %xmm1, %xmm1
-# CHECK-NEXT: [0,55]    .    .   D====eE--------------R  .   vandnps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,56]    .    .   D====eE--------------R  .   vandnpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,53]    .    .  DPPPPeE---------------R  .   vandnps	%xmm2, %xmm2, %xmm2
+# CHECK-NEXT: [0,54]    .    .   DPPPeE---------------R  .   vandnpd	%xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,55]    .    .   DPPPPeE--------------R  .   vandnps	%ymm2, %ymm2, %ymm2
+# CHECK-NEXT: [0,56]    .    .   DPPPPeE--------------R  .   vandnpd	%ymm1, %ymm1, %ymm1
 # CHECK-NEXT: [0,57]    .    .   D====eE--------------R  .   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,58]    .    .   D=====eE-------------R  .   pandn	%xmm2, %xmm2
-# CHECK-NEXT: [0,59]    .    .   D==================eER  .   vpandn	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,60]    .    .    D==================eER .   vpandn	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,61]    .    .    D=====eE-------------R .   vandnps	%xmm2, %xmm2, %xmm5
-# CHECK-NEXT: [0,62]    .    .    D====eE--------------R .   vandnpd	%xmm1, %xmm1, %xmm5
-# CHECK-NEXT: [0,63]    .    .    D===================eER.   vpandn	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,64]    .    .    D=====eE--------------R.   vandnps	%ymm2, %ymm2, %ymm5
-# CHECK-NEXT: [0,65]    .    .    D====eE---------------R.   vandnpd	%ymm1, %ymm1, %ymm5
-# CHECK-NEXT: [0,66]    .    .    .D==================eER.   vpandn	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,58]    .    .   DPPPPPeE-------------R  .   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,59]    .    .   DPPPPPPPPPPPPPPPP==eER  .   vpandn	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,60]    .    .    DPPPPPPPPPPPPPPPPPPeER .   vpandn	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,61]    .    .    DPPPPPeE-------------R .   vandnps	%xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,62]    .    .    DPPPPeE--------------R .   vandnpd	%xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,63]    .    .    DPPPPPPPPPPPPPPPPPPPeER.   vpandn	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,64]    .    .    DPPPPPeE--------------R.   vandnps	%ymm2, %ymm2, %ymm5
+# CHECK-NEXT: [0,65]    .    .    DPPPPeE---------------R.   vandnpd	%ymm1, %ymm1, %ymm5
+# CHECK-NEXT: [0,66]    .    .    .DPPPPPPPPPPPPPPPPPPeER.   vpandn	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,67]    .    .    .D=======eE-----------R.   xorps	%xmm0, %xmm0
-# CHECK-NEXT: [0,68]    .    .    .D======eE------------R.   xorpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,69]    .    .    .D=======eE-----------R.   vxorps	%xmm2, %xmm2, %xmm2
-# CHECK-NEXT: [0,70]    .    .    .D========eE----------R.   vxorpd	%xmm1, %xmm1, %xmm1
-# CHECK-NEXT: [0,71]    .    .    .D========eE----------R.   vxorps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,72]    .    .    . D========eE---------R.   vxorpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,73]    .    .    . D========eE---------R.   pxor	%mm2, %mm2
-# CHECK-NEXT: [0,74]    .    .    . D=========eE--------R.   pxor	%xmm2, %xmm2
-# CHECK-NEXT: [0,75]    .    .    . D=================eER.   vpxor	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,76]    .    .    . D==================eER   vpxor	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,68]    .    .    .DPPP===eE------------R.   xorpd	%xmm1, %xmm1
+# CHECK-NEXT: [0,69]    .    .    .DPPPP===eE-----------R.   vxorps	%xmm2, %xmm2, %xmm2
+# CHECK-NEXT: [0,70]    .    .    .DPPPPPPP=eE----------R.   vxorpd	%xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,71]    .    .    .DPPPPPPPPeE----------R.   vxorps	%ymm2, %ymm2, %ymm2
+# CHECK-NEXT: [0,72]    .    .    . DPPPPPPPPeE---------R.   vxorpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,73]    .    .    . DPP======eE---------R.   pxor	%mm2, %mm2
+# CHECK-NEXT: [0,74]    .    .    . DPPPPPPPP=eE--------R.   pxor	%xmm2, %xmm2
+# CHECK-NEXT: [0,75]    .    .    . DPPPPPPPPPPPPPPPPPeER.   vpxor	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,76]    .    .    . DPPPPPPPPPPPPPPPPPPeER   vpxor	%ymm3, %ymm3, %ymm3
 # CHECK-NEXT: [0,77]    .    .    . D==========eE--------R   vxorps	%xmm4, %xmm4, %xmm5
-# CHECK-NEXT: [0,78]    .    .    .  D=========eE--------R   vxorpd	%xmm1, %xmm1, %xmm3
+# CHECK-NEXT: [0,78]    .    .    .  DPPPPPPPP=eE--------R   vxorpd	%xmm1, %xmm1, %xmm3
 # CHECK-NEXT: [0,79]    .    .    .  D==========eE-------R   vxorps	%ymm4, %ymm4, %ymm5
-# CHECK-NEXT: [0,80]    .    .    .  D========eE---------R   vxorpd	%ymm1, %ymm1, %ymm3
-# CHECK-NEXT: [0,81]    .    .    .  D==========eE-------R   vpxor	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,82]    .    .    .  D===========eE------R   vpxor	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,80]    .    .    .  DPPPPPPPPeE---------R   vxorpd	%ymm1, %ymm1, %ymm3
+# CHECK-NEXT: [0,81]    .    .    .  DPPPPPPPPP=eE-------R   vpxor	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,82]    .    .    .  DPPPPPPPPP==eE------R   vpxor	%ymm3, %ymm3, %ymm5
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Atom/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/Atom/zero-idioms.s
index 905e1aeaca7ed..2732a6e5169a9 100644
--- a/llvm/test/tools/llvm-mca/X86/Atom/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/Atom/zero-idioms.s
@@ -154,6 +154,7 @@ pxor   %xmm2, %xmm2
 # CHECK-NEXT: 1.00    -     pxor	%xmm2, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/clear-super-register-1.s b/llvm/test/tools/llvm-mca/X86/Barcelona/clear-super-register-1.s
index 99b9e0ce6e46a..8c3b92bf9e345 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/clear-super-register-1.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/clear-super-register-1.s
@@ -38,17 +38,18 @@ bsf   %rax, %rcx
 # CHECK-NEXT:  1      3     1.00                        bsfq	%rax, %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .  .   imulq	$5, %rcx, %rax
 # CHECK-NEXT: [0,1]     D=eeeER   .    .  .   lzcntl	%ecx, %eax
-# CHECK-NEXT: [0,2]     D====eER  .    .  .   andq	%rcx, %rax
-# CHECK-NEXT: [0,3]     D=====eeeER    .  .   bsfq	%rax, %rcx
-# CHECK-NEXT: [1,0]     .D=======eeeER .  .   imulq	$5, %rcx, %rax
-# CHECK-NEXT: [1,1]     .D========eeeER.  .   lzcntl	%ecx, %eax
-# CHECK-NEXT: [1,2]     .D===========eER  .   andq	%rcx, %rax
-# CHECK-NEXT: [1,3]     .D============eeeER   bsfq	%rax, %rcx
+# CHECK-NEXT: [0,2]     DPPPPeER  .    .  .   andq	%rcx, %rax
+# CHECK-NEXT: [0,3]     DPPPPPeeeER    .  .   bsfq	%rax, %rcx
+# CHECK-NEXT: [1,0]     .DPPPPPPPeeeER .  .   imulq	$5, %rcx, %rax
+# CHECK-NEXT: [1,1]     .DPPPPPPP=eeeER.  .   lzcntl	%ecx, %eax
+# CHECK-NEXT: [1,2]     .DPPPPPPPPPPPeER  .   andq	%rcx, %rax
+# CHECK-NEXT: [1,3]     .DPPPPPPPPPPPPeeeER   bsfq	%rax, %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/clear-super-register-2.s b/llvm/test/tools/llvm-mca/X86/Barcelona/clear-super-register-2.s
index da943dc3f1bba..4ec2b67e1df75 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/clear-super-register-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/clear-super-register-2.s
@@ -43,18 +43,19 @@ addps  %xmm0, %xmm0
 # CHECK-NEXT:  1      3     1.00                        addps	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeER   .    .    .    .    .   .   sqrtss	%xmm0, %xmm0
 # CHECK-NEXT: [0,1]     DeeeeeeE--------R   .    .    .    .    .   .   movss	(%eax), %xmm0
-# CHECK-NEXT: [0,2]     D======eeeE-----R   .    .    .    .    .   .   addps	%xmm0, %xmm0
-# CHECK-NEXT: [1,0]     D==============eeeeeeeeeeeeeeER    .    .   .   sqrtss	%xmm0, %xmm0
+# CHECK-NEXT: [0,2]     DPPPPPPeeeE-----R   .    .    .    .    .   .   addps	%xmm0, %xmm0
+# CHECK-NEXT: [1,0]     DPPPPPPPPP=====eeeeeeeeeeeeeeER    .    .   .   sqrtss	%xmm0, %xmm0
 # CHECK-NEXT: [1,1]     .DeeeeeeE---------------------R    .    .   .   movss	(%eax), %xmm0
-# CHECK-NEXT: [1,2]     .D======eeeE------------------R    .    .   .   addps	%xmm0, %xmm0
-# CHECK-NEXT: [2,0]     .D===========================eeeeeeeeeeeeeeER   sqrtss	%xmm0, %xmm0
+# CHECK-NEXT: [1,2]     .DPPPPPPeeeE------------------R    .    .   .   addps	%xmm0, %xmm0
+# CHECK-NEXT: [2,0]     .DPPPPPPPPP==================eeeeeeeeeeeeeeER   sqrtss	%xmm0, %xmm0
 # CHECK-NEXT: [2,1]     .DeeeeeeE-----------------------------------R   movss	(%eax), %xmm0
-# CHECK-NEXT: [2,2]     . D======eeeE-------------------------------R   addps	%xmm0, %xmm0
+# CHECK-NEXT: [2,2]     . DPPPPP=eeeE-------------------------------R   addps	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -94,18 +95,19 @@ addps  %xmm0, %xmm0
 # CHECK-NEXT:  1      3     1.00                        addps	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          012345
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeeeeeeeeER .    .    .    .    .    .    .    .    .   sqrtsd	%xmm0, %xmm0
 # CHECK-NEXT: [0,1]     DeeeeeeE---------------R .    .    .    .    .    .    .    .    .   movsd	(%eax), %xmm0
-# CHECK-NEXT: [0,2]     D======eeeE------------R .    .    .    .    .    .    .    .    .   addps	%xmm0, %xmm0
-# CHECK-NEXT: [1,0]     D=====================eeeeeeeeeeeeeeeeeeeeeER.    .    .    .    .   sqrtsd	%xmm0, %xmm0
+# CHECK-NEXT: [0,2]     DPPPPPPeeeE------------R .    .    .    .    .    .    .    .    .   addps	%xmm0, %xmm0
+# CHECK-NEXT: [1,0]     DPPPPPPPPP============eeeeeeeeeeeeeeeeeeeeeER.    .    .    .    .   sqrtsd	%xmm0, %xmm0
 # CHECK-NEXT: [1,1]     .DeeeeeeE-----------------------------------R.    .    .    .    .   movsd	(%eax), %xmm0
-# CHECK-NEXT: [1,2]     .D======eeeE--------------------------------R.    .    .    .    .   addps	%xmm0, %xmm0
-# CHECK-NEXT: [2,0]     .D=========================================eeeeeeeeeeeeeeeeeeeeeER   sqrtsd	%xmm0, %xmm0
+# CHECK-NEXT: [1,2]     .DPPPPPPeeeE--------------------------------R.    .    .    .    .   addps	%xmm0, %xmm0
+# CHECK-NEXT: [2,0]     .DPPPPPPPPP================================eeeeeeeeeeeeeeeeeeeeeER   sqrtsd	%xmm0, %xmm0
 # CHECK-NEXT: [2,1]     .DeeeeeeE--------------------------------------------------------R   movsd	(%eax), %xmm0
-# CHECK-NEXT: [2,2]     . D======eeeE----------------------------------------------------R   addps	%xmm0, %xmm0
+# CHECK-NEXT: [2,2]     . DPPPPP=eeeE----------------------------------------------------R   addps	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-cmp.s b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-cmp.s
index d42a49b4b862d..c34ad3de63dba 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-cmp.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-cmp.s
@@ -49,15 +49,16 @@ cmovae %ebx, %eax
 # CHECK-NEXT:  -      -     1.00   1.00    -      -      -      -     cmovael	%ebx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    ..   cmpl	%eax, %eax
-# CHECK-NEXT: [0,1]     D=eeER    ..   cmovael	%ebx, %eax
-# CHECK-NEXT: [1,0]     D===eER   ..   cmpl	%eax, %eax
-# CHECK-NEXT: [1,1]     .D===eeER ..   cmovael	%ebx, %eax
-# CHECK-NEXT: [2,0]     .D=====eER..   cmpl	%eax, %eax
-# CHECK-NEXT: [2,1]     . D=====eeER   cmovael	%ebx, %eax
+# CHECK-NEXT: [0,1]     DPeeER    ..   cmovael	%ebx, %eax
+# CHECK-NEXT: [1,0]     DPPPeER   ..   cmpl	%eax, %eax
+# CHECK-NEXT: [1,1]     .DPPPeeER ..   cmovael	%ebx, %eax
+# CHECK-NEXT: [2,0]     .DPPPPPeER..   cmpl	%eax, %eax
+# CHECK-NEXT: [2,1]     . DPPPPPeeER   cmovael	%ebx, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-pcmpeq.s b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-pcmpeq.s
index 94ed93a94e7e3..aa58c9d75d215 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-pcmpeq.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-pcmpeq.s
@@ -66,30 +66,31 @@ pcmpeqw %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -     0.99    -     0.01    -      -     pcmpeqw	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .   .   pcmpeqb	%mm0, %mm0
-# CHECK-NEXT: [0,1]     D===eeeER .    .    .    .   .   pcmpeqd	%mm0, %mm0
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    .   .   pcmpeqw	%mm0, %mm0
+# CHECK-NEXT: [0,1]     DPPPeeeER .    .    .    .   .   pcmpeqd	%mm0, %mm0
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    .   .   pcmpeqw	%mm0, %mm0
 # CHECK-NEXT: [0,3]     DeE--------R   .    .    .   .   pcmpeqb	%xmm0, %xmm0
 # CHECK-NEXT: [0,4]     .DeE-------R   .    .    .   .   pcmpeqd	%xmm0, %xmm0
-# CHECK-NEXT: [0,5]     .D=eE------R   .    .    .   .   pcmpeqq	%xmm0, %xmm0
-# CHECK-NEXT: [0,6]     .D==eE-----R   .    .    .   .   pcmpeqw	%xmm0, %xmm0
-# CHECK-NEXT: [1,0]     .D========eeeER.    .    .   .   pcmpeqb	%mm0, %mm0
-# CHECK-NEXT: [1,1]     . D==========eeeER  .    .   .   pcmpeqd	%mm0, %mm0
-# CHECK-NEXT: [1,2]     . D=============eeeER    .   .   pcmpeqw	%mm0, %mm0
-# CHECK-NEXT: [1,3]     . D==eE-------------R    .   .   pcmpeqb	%xmm0, %xmm0
-# CHECK-NEXT: [1,4]     . D===eE------------R    .   .   pcmpeqd	%xmm0, %xmm0
-# CHECK-NEXT: [1,5]     .  D===eE-----------R    .   .   pcmpeqq	%xmm0, %xmm0
-# CHECK-NEXT: [1,6]     .  D====eE----------R    .   .   pcmpeqw	%xmm0, %xmm0
-# CHECK-NEXT: [2,0]     .  D===============eeeER .   .   pcmpeqb	%mm0, %mm0
-# CHECK-NEXT: [2,1]     .  D==================eeeER  .   pcmpeqd	%mm0, %mm0
-# CHECK-NEXT: [2,2]     .   D====================eeeER   pcmpeqw	%mm0, %mm0
-# CHECK-NEXT: [2,3]     .   D====eE------------------R   pcmpeqb	%xmm0, %xmm0
-# CHECK-NEXT: [2,4]     .   D=====eE-----------------R   pcmpeqd	%xmm0, %xmm0
-# CHECK-NEXT: [2,5]     .   D======eE----------------R   pcmpeqq	%xmm0, %xmm0
-# CHECK-NEXT: [2,6]     .    D======eE---------------R   pcmpeqw	%xmm0, %xmm0
+# CHECK-NEXT: [0,5]     .DPeE------R   .    .    .   .   pcmpeqq	%xmm0, %xmm0
+# CHECK-NEXT: [0,6]     .DPPeE-----R   .    .    .   .   pcmpeqw	%xmm0, %xmm0
+# CHECK-NEXT: [1,0]     .DPPPPPPPPeeeER.    .    .   .   pcmpeqb	%mm0, %mm0
+# CHECK-NEXT: [1,1]     . DPPPPPPPPPPeeeER  .    .   .   pcmpeqd	%mm0, %mm0
+# CHECK-NEXT: [1,2]     . DPPPPPPPPPPPPPeeeER    .   .   pcmpeqw	%mm0, %mm0
+# CHECK-NEXT: [1,3]     . DPPeE-------------R    .   .   pcmpeqb	%xmm0, %xmm0
+# CHECK-NEXT: [1,4]     . DPPPeE------------R    .   .   pcmpeqd	%xmm0, %xmm0
+# CHECK-NEXT: [1,5]     .  DPPPeE-----------R    .   .   pcmpeqq	%xmm0, %xmm0
+# CHECK-NEXT: [1,6]     .  DPPPPeE----------R    .   .   pcmpeqw	%xmm0, %xmm0
+# CHECK-NEXT: [2,0]     .  DPPPPPPPPPPPPPPPeeeER .   .   pcmpeqb	%mm0, %mm0
+# CHECK-NEXT: [2,1]     .  DPPPPPPPPPPPPPPPPPPeeeER  .   pcmpeqd	%mm0, %mm0
+# CHECK-NEXT: [2,2]     .   DPPPPPPPPPPPPPPPPPPPPeeeER   pcmpeqw	%mm0, %mm0
+# CHECK-NEXT: [2,3]     .   DPPPPeE------------------R   pcmpeqb	%xmm0, %xmm0
+# CHECK-NEXT: [2,4]     .   DPPPPPeE-----------------R   pcmpeqd	%xmm0, %xmm0
+# CHECK-NEXT: [2,5]     .   DPPPPPPeE----------------R   pcmpeqq	%xmm0, %xmm0
+# CHECK-NEXT: [2,6]     .    DPPPPPPeE---------------R   pcmpeqw	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-pcmpgt.s b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-pcmpgt.s
index 1e387719a10ab..608781f02d3ec 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-pcmpgt.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-pcmpgt.s
@@ -67,26 +67,27 @@ pcmpgtw %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     pcmpgtw	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .   .   pcmpgtb	%mm0, %mm0
-# CHECK-NEXT: [0,1]     D===eeeER .    .    .    .   .   pcmpgtd	%mm0, %mm0
-# CHECK-NEXT: [0,2]     D======eeeER   .    .    .   .   pcmpgtw	%mm0, %mm0
+# CHECK-NEXT: [0,1]     DPPPeeeER .    .    .    .   .   pcmpgtd	%mm0, %mm0
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   .    .    .   .   pcmpgtw	%mm0, %mm0
 # CHECK-NEXT: [0,3]     D----------R   .    .    .   .   pcmpgtb	%xmm0, %xmm0
 # CHECK-NEXT: [0,4]     .D---------R   .    .    .   .   pcmpgtd	%xmm0, %xmm0
 # CHECK-NEXT: [0,5]     .D---------R   .    .    .   .   pcmpgtq	%xmm0, %xmm0
 # CHECK-NEXT: [0,6]     .D---------R   .    .    .   .   pcmpgtw	%xmm0, %xmm0
-# CHECK-NEXT: [1,0]     .D========eeeER.    .    .   .   pcmpgtb	%mm0, %mm0
-# CHECK-NEXT: [1,1]     . D==========eeeER  .    .   .   pcmpgtd	%mm0, %mm0
-# CHECK-NEXT: [1,2]     . D=============eeeER    .   .   pcmpgtw	%mm0, %mm0
+# CHECK-NEXT: [1,0]     .DPPPPPPPPeeeER.    .    .   .   pcmpgtb	%mm0, %mm0
+# CHECK-NEXT: [1,1]     . DPPPPPPPPPPeeeER  .    .   .   pcmpgtd	%mm0, %mm0
+# CHECK-NEXT: [1,2]     . DPPPPPPPPPPPPPeeeER    .   .   pcmpgtw	%mm0, %mm0
 # CHECK-NEXT: [1,3]     . D-----------------R    .   .   pcmpgtb	%xmm0, %xmm0
 # CHECK-NEXT: [1,4]     . D-----------------R    .   .   pcmpgtd	%xmm0, %xmm0
 # CHECK-NEXT: [1,5]     .  D----------------R    .   .   pcmpgtq	%xmm0, %xmm0
 # CHECK-NEXT: [1,6]     .  D----------------R    .   .   pcmpgtw	%xmm0, %xmm0
-# CHECK-NEXT: [2,0]     .  D===============eeeER .   .   pcmpgtb	%mm0, %mm0
-# CHECK-NEXT: [2,1]     .  D==================eeeER  .   pcmpgtd	%mm0, %mm0
-# CHECK-NEXT: [2,2]     .   D====================eeeER   pcmpgtw	%mm0, %mm0
+# CHECK-NEXT: [2,0]     .  DPPPPPPPPPPPPPPPeeeER .   .   pcmpgtb	%mm0, %mm0
+# CHECK-NEXT: [2,1]     .  DPPPPPPPPPPPPPPPPPPeeeER  .   pcmpgtd	%mm0, %mm0
+# CHECK-NEXT: [2,2]     .   DPPPPPPPPPPPPPPPPPPPPeeeER   pcmpgtw	%mm0, %mm0
 # CHECK-NEXT: [2,3]     .   D------------------------R   pcmpgtb	%xmm0, %xmm0
 # CHECK-NEXT: [2,4]     .   D------------------------R   pcmpgtd	%xmm0, %xmm0
 # CHECK-NEXT: [2,5]     .   D------------------------R   pcmpgtq	%xmm0, %xmm0
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-sbb-1.s b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-sbb-1.s
index b685814b88159..434545a151d21 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-sbb-1.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-sbb-1.s
@@ -50,15 +50,16 @@ sbb %eax, %eax
 # CHECK-NEXT:  -      -     0.67   0.67    -     0.67    -      -     sbbl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   .   sbbl	%edx, %edx
-# CHECK-NEXT: [0,1]     D==eeER   .   .   sbbl	%eax, %eax
-# CHECK-NEXT: [1,0]     .D===eeER .   .   sbbl	%edx, %edx
-# CHECK-NEXT: [1,1]     .D=====eeER   .   sbbl	%eax, %eax
-# CHECK-NEXT: [2,0]     . D======eeER .   sbbl	%edx, %edx
-# CHECK-NEXT: [2,1]     . D========eeER   sbbl	%eax, %eax
+# CHECK-NEXT: [0,1]     DPPeeER   .   .   sbbl	%eax, %eax
+# CHECK-NEXT: [1,0]     .DPPPeeER .   .   sbbl	%edx, %edx
+# CHECK-NEXT: [1,1]     .DPPPPPeeER   .   sbbl	%eax, %eax
+# CHECK-NEXT: [2,0]     . DPPPPPPeeER .   sbbl	%edx, %edx
+# CHECK-NEXT: [2,1]     . DPPPPPPPPeeER   sbbl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-sbb-2.s b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-sbb-2.s
index 6df5e68f0bd21..18eb27bbcd126 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-sbb-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/dependency-breaking-sbb-2.s
@@ -53,18 +53,19 @@ sbb %eax, %eax
 # CHECK-NEXT:  -      -     1.00    -      -     1.00    -      -     sbbl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .    . .   imull	%edx, %eax
 # CHECK-NEXT: [0,1]     DeE--R    .    . .   addl	%edx, %edx
-# CHECK-NEXT: [0,2]     D===eeER  .    . .   sbbl	%eax, %eax
-# CHECK-NEXT: [1,0]     .D====eeeER    . .   imull	%edx, %eax
+# CHECK-NEXT: [0,2]     DPPPeeER  .    . .   sbbl	%eax, %eax
+# CHECK-NEXT: [1,0]     .DPPPPeeeER    . .   imull	%edx, %eax
 # CHECK-NEXT: [1,1]     .DeE------R    . .   addl	%edx, %edx
-# CHECK-NEXT: [1,2]     .D=======eeER  . .   sbbl	%eax, %eax
-# CHECK-NEXT: [2,0]     . D========eeeER .   imull	%edx, %eax
+# CHECK-NEXT: [1,2]     .DPPPPPPPeeER  . .   sbbl	%eax, %eax
+# CHECK-NEXT: [2,0]     . DPPPPPPPPeeeER .   imull	%edx, %eax
 # CHECK-NEXT: [2,1]     . DeE----------R .   addl	%edx, %edx
-# CHECK-NEXT: [2,2]     . D===========eeER   sbbl	%eax, %eax
+# CHECK-NEXT: [2,2]     . DPPPPPPPPPPPeeER   sbbl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/int-to-fpu-forwarding-3.s b/llvm/test/tools/llvm-mca/X86/Barcelona/int-to-fpu-forwarding-3.s
index ccdf431ddc7a2..61739bb40d02f 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/int-to-fpu-forwarding-3.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/int-to-fpu-forwarding-3.s
@@ -49,18 +49,19 @@ pinsrw $1, %eax, %xmm0
 # CHECK-NEXT:  -      -      -     1.00    -     1.00    -      -     pinsrw	$1, %eax, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    .    .   addl	%eax, %eax
-# CHECK-NEXT: [0,1]     D=eeER    .    .   pinsrw	$0, %eax, %xmm0
-# CHECK-NEXT: [0,2]     .D==eeER  .    .   pinsrw	$1, %eax, %xmm0
+# CHECK-NEXT: [0,1]     DPeeER    .    .   pinsrw	$0, %eax, %xmm0
+# CHECK-NEXT: [0,2]     .DPPeeER  .    .   pinsrw	$1, %eax, %xmm0
 # CHECK-NEXT: [1,0]     .DeE---R  .    .   addl	%eax, %eax
-# CHECK-NEXT: [1,1]     . D===eeER.    .   pinsrw	$0, %eax, %xmm0
-# CHECK-NEXT: [1,2]     . D=====eeER   .   pinsrw	$1, %eax, %xmm0
+# CHECK-NEXT: [1,1]     . DPPPeeER.    .   pinsrw	$0, %eax, %xmm0
+# CHECK-NEXT: [1,2]     . DPPPPPeeER   .   pinsrw	$1, %eax, %xmm0
 # CHECK-NEXT: [2,0]     .  DeE-----R   .   addl	%eax, %eax
-# CHECK-NEXT: [2,1]     .  D======eeER .   pinsrw	$0, %eax, %xmm0
-# CHECK-NEXT: [2,2]     .   D=======eeER   pinsrw	$1, %eax, %xmm0
+# CHECK-NEXT: [2,1]     .  DPPPPPPeeER .   pinsrw	$0, %eax, %xmm0
+# CHECK-NEXT: [2,2]     .   DPPPPPPPeeER   pinsrw	$1, %eax, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/load-store-throughput.s b/llvm/test/tools/llvm-mca/X86/Barcelona/load-store-throughput.s
index 97649581c2192..bb089d1eda9a2 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/load-store-throughput.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/load-store-throughput.s
@@ -120,12 +120,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movb	%dil, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movb	%spl, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movb	(%rcx), %bpl
 # CHECK-NEXT: [0,2]     D=eeeeeER   movb	(%rdx), %sil
-# CHECK-NEXT: [0,3]     D=eE----R   movb	%dil, (%rbx)
+# CHECK-NEXT: [0,3]     DPeE----R   movb	%dil, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -217,12 +218,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movw	%di, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movw	%sp, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movw	(%rcx), %bp
 # CHECK-NEXT: [0,2]     D=eeeeeER   movw	(%rdx), %si
-# CHECK-NEXT: [0,3]     D=eE----R   movw	%di, (%rbx)
+# CHECK-NEXT: [0,3]     DPeE----R   movw	%di, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -314,12 +316,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movl	%edi, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movl	%esp, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movl	(%rcx), %ebp
 # CHECK-NEXT: [0,2]     D=eeeeeER   movl	(%rdx), %esi
-# CHECK-NEXT: [0,3]     D=eE----R   movl	%edi, (%rbx)
+# CHECK-NEXT: [0,3]     DPeE----R   movl	%edi, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -411,12 +414,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movq	%rdi, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movq	%rsp, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movq	(%rcx), %rbp
 # CHECK-NEXT: [0,2]     D=eeeeeER   movq	(%rdx), %rsi
-# CHECK-NEXT: [0,3]     D=eE----R   movq	%rdi, (%rbx)
+# CHECK-NEXT: [0,3]     DPeE----R   movq	%rdi, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -508,12 +512,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movd	%mm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movd	%mm0, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movd	(%rcx), %mm1
 # CHECK-NEXT: [0,2]     D=eeeeeER   movd	(%rdx), %mm2
-# CHECK-NEXT: [0,3]     D=eE----R   movd	%mm3, (%rbx)
+# CHECK-NEXT: [0,3]     DPeE----R   movd	%mm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -605,12 +610,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movaps	%xmm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .   .   movaps	%xmm0, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeeER.   movaps	(%rcx), %xmm1
 # CHECK-NEXT: [0,2]     D=eeeeeeER   movaps	(%rdx), %xmm2
-# CHECK-NEXT: [0,3]     D=eE-----R   movaps	%xmm3, (%rbx)
+# CHECK-NEXT: [0,3]     DPeE-----R   movaps	%xmm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/load-throughput.s b/llvm/test/tools/llvm-mca/X86/Barcelona/load-throughput.s
index 1e1bfd5c98ca6..194398d5e519c 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/load-throughput.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/load-throughput.s
@@ -120,6 +120,7 @@ movaps (%rbx), %xmm3
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -     movb	(%rbx), %dil
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeeER.   movb	(%rax), %spl
@@ -217,6 +218,7 @@ movaps (%rbx), %xmm3
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -     movw	(%rbx), %di
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeeER.   movw	(%rax), %sp
@@ -314,6 +316,7 @@ movaps (%rbx), %xmm3
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -     movl	(%rbx), %edi
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeeER.   movl	(%rax), %esp
@@ -411,6 +414,7 @@ movaps (%rbx), %xmm3
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -     movq	(%rbx), %rdi
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeeER.   movq	(%rax), %rsp
@@ -508,6 +512,7 @@ movaps (%rbx), %xmm3
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -     movd	(%rbx), %mm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeeER.   movd	(%rax), %mm0
@@ -605,6 +610,7 @@ movaps (%rbx), %xmm3
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -     movaps	(%rbx), %xmm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER.   movaps	(%rax), %xmm0
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/one-idioms.s b/llvm/test/tools/llvm-mca/X86/Barcelona/one-idioms.s
index 2021863416260..51c2d066d7b78 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/one-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/one-idioms.s
@@ -69,16 +69,17 @@ pcmpeqw %xmm2, %xmm2
 # CHECK-NEXT:  -      -      -     0.79    -     0.21    -      -     pcmpeqw	%xmm2, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    ..   pcmpeqb	%mm2, %mm2
-# CHECK-NEXT: [0,1]     D===eeeER ..   pcmpeqd	%mm2, %mm2
-# CHECK-NEXT: [0,2]     D======eeeER   pcmpeqw	%mm2, %mm2
+# CHECK-NEXT: [0,1]     DPPPeeeER ..   pcmpeqd	%mm2, %mm2
+# CHECK-NEXT: [0,2]     DPPPPPPeeeER   pcmpeqw	%mm2, %mm2
 # CHECK-NEXT: [0,3]     DeE--------R   pcmpeqb	%xmm2, %xmm2
 # CHECK-NEXT: [0,4]     .DeE-------R   pcmpeqd	%xmm2, %xmm2
-# CHECK-NEXT: [0,5]     .D=eE------R   pcmpeqq	%xmm2, %xmm2
-# CHECK-NEXT: [0,6]     .D==eE-----R   pcmpeqw	%xmm2, %xmm2
+# CHECK-NEXT: [0,5]     .DPeE------R   pcmpeqq	%xmm2, %xmm2
+# CHECK-NEXT: [0,6]     .DPPeE-----R   pcmpeqw	%xmm2, %xmm2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-2.s b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-2.s
index 5412821894296..1b94959341f62 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-2.s
@@ -29,11 +29,12 @@ add    %ecx, %ebx
 # CHECK-NEXT:  1      1     0.33                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   imulq	%rax, %rbx
 # CHECK-NEXT: [0,1]     D=eeeER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,2]     DPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-3.s b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-3.s
index 6cf7d93cb748e..0b6f3435ef506 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-3.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-3.s
@@ -52,15 +52,16 @@ xor %bx, %dx
 # CHECK-NEXT:  -      -     0.33   0.33    -     0.33    -      -     xorw	%bx, %dx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   addw	%cx, %dx
 # CHECK-NEXT: [0,1]     DeER ..   movw	%ax, %dx
-# CHECK-NEXT: [0,2]     D=eER..   xorw	%bx, %dx
-# CHECK-NEXT: [1,0]     D==eER.   addw	%cx, %dx
+# CHECK-NEXT: [0,2]     DPeER..   xorw	%bx, %dx
+# CHECK-NEXT: [1,0]     DPPeER.   addw	%cx, %dx
 # CHECK-NEXT: [1,1]     .DeE-R.   movw	%ax, %dx
-# CHECK-NEXT: [1,2]     .D=eER.   xorw	%bx, %dx
-# CHECK-NEXT: [2,0]     .D==eER   addw	%cx, %dx
+# CHECK-NEXT: [1,2]     .DPeER.   xorw	%bx, %dx
+# CHECK-NEXT: [2,0]     .DPPeER   addw	%cx, %dx
 # CHECK-NEXT: [2,1]     .DeE--R   movw	%ax, %dx
 # CHECK-NEXT: [2,2]     . DeE-R   xorw	%bx, %dx
 
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-4.s b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-4.s
index f349c3e0e61ee..0cd6319419668 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-4.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-4.s
@@ -52,18 +52,19 @@ add %cx, %bx
 # CHECK-NEXT:  -      -     0.50    -      -     0.50    -      -     addw	%cx, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    ..   imulw	%ax, %bx
 # CHECK-NEXT: [0,1]     D=eeeER   ..   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D====eER  ..   addw	%cx, %bx
-# CHECK-NEXT: [1,0]     D=====eeeER.   imulw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPeER  ..   addw	%cx, %bx
+# CHECK-NEXT: [1,0]     DPPPPPeeeER.   imulw	%ax, %bx
 # CHECK-NEXT: [1,1]     .D=eeeE---R.   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,2]     .D====eE--R.   addw	%cx, %bx
-# CHECK-NEXT: [2,0]     .D=====eeeER   imulw	%ax, %bx
+# CHECK-NEXT: [1,2]     .DPPPPeE--R.   addw	%cx, %bx
+# CHECK-NEXT: [2,0]     .DPPPPPeeeER   imulw	%ax, %bx
 # CHECK-NEXT: [2,1]     .D==eeeE---R   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,2]     . D====eE--R   addw	%cx, %bx
+# CHECK-NEXT: [2,2]     . DPPPPeE--R   addw	%cx, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-5.s b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-5.s
index fcda63029475a..a2ba311e2dc1b 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-5.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-5.s
@@ -43,6 +43,7 @@ lzcnt %ax, %bx  ## partial register stall.
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     lzcntw	%ax, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   lzcntw	%ax, %bx
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-6.s b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-6.s
index cb7cbda3d82f2..06b49ef832400 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-6.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-6.s
@@ -54,16 +54,17 @@ lzcnt 2(%rsp), %cx
 # CHECK-NEXT:  -      -      -     1.00    -      -     1.00    -     lzcntw	2(%rsp), %cx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .  .   imull	%edx, %ecx
 # CHECK-NEXT: [0,1]     D=eeeeeeeeER   .  .   lzcntw	(%rsp), %cx
 # CHECK-NEXT: [0,2]     .D=eeeeeeeeER  .  .   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [1,0]     .D=========eeeER  .   imull	%edx, %ecx
+# CHECK-NEXT: [1,0]     .DPPPPPPPPPeeeER  .   imull	%edx, %ecx
 # CHECK-NEXT: [1,1]     . D=eeeeeeeeE--R  .   lzcntw	(%rsp), %cx
 # CHECK-NEXT: [1,2]     . D==eeeeeeeeE-R  .   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [2,0]     .  D==========eeeER   imull	%edx, %ecx
+# CHECK-NEXT: [2,0]     .  DPPPPPPPPPPeeeER   imull	%edx, %ecx
 # CHECK-NEXT: [2,1]     .  D==eeeeeeeeE---R   lzcntw	(%rsp), %cx
 # CHECK-NEXT: [2,2]     .   D==eeeeeeeeE--R   lzcntw	2(%rsp), %cx
 
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-7.s b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-7.s
index 58981f9a3a914..2b183235ce24d 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-7.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update-7.s
@@ -55,34 +55,35 @@ cmpl $1025, %eax
 # CHECK-NEXT:  -      -     0.33   0.33    -     0.34    -      -     cmpl	$1025, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeER .    .    .    .    .  .   sete	%r9b
 # CHECK-NEXT: [0,1]     DeER .    .    .    .    .  .   movzbl	%al, %eax
-# CHECK-NEXT: [0,2]     D=eER.    .    .    .    .  .   shll	$2, %eax
-# CHECK-NEXT: [0,3]     D==eeeER  .    .    .    .  .   imull	%ecx, %eax
-# CHECK-NEXT: [0,4]     .D====eER .    .    .    .  .   cmpl	$1025, %eax
-# CHECK-NEXT: [1,0]     .D=====eER.    .    .    .  .   sete	%r9b
-# CHECK-NEXT: [1,1]     .D====eE-R.    .    .    .  .   movzbl	%al, %eax
-# CHECK-NEXT: [1,2]     .D=====eER.    .    .    .  .   shll	$2, %eax
-# CHECK-NEXT: [1,3]     . D=====eeeER  .    .    .  .   imull	%ecx, %eax
-# CHECK-NEXT: [1,4]     . D========eER .    .    .  .   cmpl	$1025, %eax
-# CHECK-NEXT: [2,0]     . D=========eER.    .    .  .   sete	%r9b
-# CHECK-NEXT: [2,1]     . D========eE-R.    .    .  .   movzbl	%al, %eax
-# CHECK-NEXT: [2,2]     .  D========eER.    .    .  .   shll	$2, %eax
-# CHECK-NEXT: [2,3]     .  D=========eeeER  .    .  .   imull	%ecx, %eax
-# CHECK-NEXT: [2,4]     .  D============eER .    .  .   cmpl	$1025, %eax
-# CHECK-NEXT: [3,0]     .  D=============eER.    .  .   sete	%r9b
-# CHECK-NEXT: [3,1]     .   D===========eE-R.    .  .   movzbl	%al, %eax
-# CHECK-NEXT: [3,2]     .   D============eER.    .  .   shll	$2, %eax
-# CHECK-NEXT: [3,3]     .   D=============eeeER  .  .   imull	%ecx, %eax
-# CHECK-NEXT: [3,4]     .   D================eER .  .   cmpl	$1025, %eax
-# CHECK-NEXT: [4,0]     .    D================eER.  .   sete	%r9b
-# CHECK-NEXT: [4,1]     .    D===============eE-R.  .   movzbl	%al, %eax
-# CHECK-NEXT: [4,2]     .    D================eER.  .   shll	$2, %eax
-# CHECK-NEXT: [4,3]     .    D=================eeeER.   imull	%ecx, %eax
-# CHECK-NEXT: [4,4]     .    .D===================eER   cmpl	$1025, %eax
+# CHECK-NEXT: [0,2]     DPeER.    .    .    .    .  .   shll	$2, %eax
+# CHECK-NEXT: [0,3]     DPPeeeER  .    .    .    .  .   imull	%ecx, %eax
+# CHECK-NEXT: [0,4]     .DPPPPeER .    .    .    .  .   cmpl	$1025, %eax
+# CHECK-NEXT: [1,0]     .DPPPPPeER.    .    .    .  .   sete	%r9b
+# CHECK-NEXT: [1,1]     .DPPPPeE-R.    .    .    .  .   movzbl	%al, %eax
+# CHECK-NEXT: [1,2]     .DPPPPPeER.    .    .    .  .   shll	$2, %eax
+# CHECK-NEXT: [1,3]     . DPPPPPeeeER  .    .    .  .   imull	%ecx, %eax
+# CHECK-NEXT: [1,4]     . DPPPPPPPPeER .    .    .  .   cmpl	$1025, %eax
+# CHECK-NEXT: [2,0]     . DPPPPPPPPPeER.    .    .  .   sete	%r9b
+# CHECK-NEXT: [2,1]     . DPPPPPPPPeE-R.    .    .  .   movzbl	%al, %eax
+# CHECK-NEXT: [2,2]     .  DPPPPPPPPeER.    .    .  .   shll	$2, %eax
+# CHECK-NEXT: [2,3]     .  DPPPPPPPPPeeeER  .    .  .   imull	%ecx, %eax
+# CHECK-NEXT: [2,4]     .  DPPPPPPPPPPPPeER .    .  .   cmpl	$1025, %eax
+# CHECK-NEXT: [3,0]     .  DPPPPPPPPPPPPPeER.    .  .   sete	%r9b
+# CHECK-NEXT: [3,1]     .   DPPPPPPPPPPPeE-R.    .  .   movzbl	%al, %eax
+# CHECK-NEXT: [3,2]     .   DPPPPPPPPPPPPeER.    .  .   shll	$2, %eax
+# CHECK-NEXT: [3,3]     .   DPPPPPPPPPPPPPeeeER  .  .   imull	%ecx, %eax
+# CHECK-NEXT: [3,4]     .   DPPPPPPPPPPPPPPPPeER .  .   cmpl	$1025, %eax
+# CHECK-NEXT: [4,0]     .    DPPPPPPPPPPPPPPPPeER.  .   sete	%r9b
+# CHECK-NEXT: [4,1]     .    DPPPPPPPPPPPPPPPeE-R.  .   movzbl	%al, %eax
+# CHECK-NEXT: [4,2]     .    DPPPPPPPPPPPPPPPPeER.  .   shll	$2, %eax
+# CHECK-NEXT: [4,3]     .    DPPPPPPPPPPPPPPPPPeeeER.   imull	%ecx, %eax
+# CHECK-NEXT: [4,4]     .    .DPPPPPPPPPPPPPPPPPPPeER   cmpl	$1025, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update.s b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update.s
index e5cc4bc0f2c40..6f1e5341bb9cc 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/partial-reg-update.s
@@ -29,11 +29,12 @@ add  %ecx, %ebx
 # CHECK-NEXT:  1      1     0.33                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   imulw	%ax, %cx
-# CHECK-NEXT: [0,1]     D===eER.   addb	%al, %cl
-# CHECK-NEXT: [0,2]     D====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPeER.   addb	%al, %cl
+# CHECK-NEXT: [0,2]     DPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-1.s b/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-1.s
index deb69273d7c31..922488e755716 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-1.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-1.s
@@ -31,6 +31,7 @@ mulps  (%rdi), %xmm1
 # CHECK-NEXT:  2      11    1.00    *                   mulps	(%rdi), %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-2.s b/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-2.s
index d57e9fb4a7987..6a5b9339df237 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-2.s
@@ -30,6 +30,7 @@ imull  (%rdi)
 # CHECK-NEXT:  4      9     1.00    *                   imull	(%rdi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-3.s b/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-3.s
index 071207df27e77..9dee6ad2bf6d6 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-3.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/read-advance-3.s
@@ -29,6 +29,7 @@ add %rdx, %r8
 # CHECK-NEXT:  1      1     0.33                        addq	%rdx, %r8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   addq	%rdi, %rsi
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-1.s b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-1.s
index 46852e69dd9a7..49eeaed2c4e48 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-1.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-1.s
@@ -56,17 +56,18 @@ addps %xmm1, %xmm1
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     addps	%xmm1, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DR   .  .   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,1]     DeER .  .   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [0,2]     D=eeeER .   addps	%xmm1, %xmm1
+# CHECK-NEXT: [0,2]     DPeeeER .   addps	%xmm1, %xmm1
 # CHECK-NEXT: [1,0]     D-----R .   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [1,1]     .DeE--R .   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [1,2]     .D=eeeER.   addps	%xmm1, %xmm1
+# CHECK-NEXT: [1,2]     .DPeeeER.   addps	%xmm1, %xmm1
 # CHECK-NEXT: [2,0]     .D-----R.   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [2,1]     .D=eE--R.   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [2,2]     . D=eeeER   addps	%xmm1, %xmm1
+# CHECK-NEXT: [2,2]     . DPeeeER   addps	%xmm1, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-2.s b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-2.s
index 598319ee6b55a..ce45249171702 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-2.s
@@ -72,36 +72,37 @@ movdqu %xmm5, %xmm0
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     movdqu	%xmm5, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    .    . .   pxor	%mm0, %mm0
-# CHECK-NEXT: [0,1]     D=eER.    .    . .   movq	%mm0, %mm1
+# CHECK-NEXT: [0,1]     DPeER.    .    . .   movq	%mm0, %mm1
 # CHECK-NEXT: [0,2]     D---R.    .    . .   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,3]     D=eER.    .    . .   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [0,4]     .D=eER    .    . .   movups	%xmm1, %xmm2
-# CHECK-NEXT: [0,5]     .D==eER   .    . .   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [0,6]     .D===eER  .    . .   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [0,7]     .D====eER .    . .   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [0,8]     . D====eER.    . .   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [0,4]     .DPeER    .    . .   movups	%xmm1, %xmm2
+# CHECK-NEXT: [0,5]     .DPPeER   .    . .   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [0,6]     .DPPPeER  .    . .   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [0,7]     .DPPPPeER .    . .   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [0,8]     . DPPPPeER.    . .   movdqu	%xmm5, %xmm0
 # CHECK-NEXT: [1,0]     . DeE----R.    . .   pxor	%mm0, %mm0
-# CHECK-NEXT: [1,1]     . D=eE---R.    . .   movq	%mm0, %mm1
+# CHECK-NEXT: [1,1]     . DPeE---R.    . .   movq	%mm0, %mm1
 # CHECK-NEXT: [1,2]     . D------R.    . .   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [1,3]     .  D==eE-R.    . .   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [1,4]     .  D===eER.    . .   movups	%xmm1, %xmm2
-# CHECK-NEXT: [1,5]     .  D====eER    . .   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [1,6]     .  D=====eER   . .   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [1,7]     .   D=====eER  . .   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [1,8]     .   D======eER . .   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [1,4]     .  DPPPeER.    . .   movups	%xmm1, %xmm2
+# CHECK-NEXT: [1,5]     .  DPPPPeER    . .   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [1,6]     .  DPPPPPeER   . .   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [1,7]     .   DPPPPPeER  . .   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [1,8]     .   DPPPPPPeER . .   movdqu	%xmm5, %xmm0
 # CHECK-NEXT: [2,0]     .   DeE------R . .   pxor	%mm0, %mm0
-# CHECK-NEXT: [2,1]     .   D=eE-----R . .   movq	%mm0, %mm1
+# CHECK-NEXT: [2,1]     .   DPeE-----R . .   movq	%mm0, %mm1
 # CHECK-NEXT: [2,2]     .    D-------R . .   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [2,3]     .    D====eE-R . .   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [2,4]     .    D=====eER . .   movups	%xmm1, %xmm2
-# CHECK-NEXT: [2,5]     .    D======eER. .   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [2,6]     .    .D======eER .   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [2,7]     .    .D=======eER.   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [2,8]     .    .D========eER   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [2,4]     .    DPPPPPeER . .   movups	%xmm1, %xmm2
+# CHECK-NEXT: [2,5]     .    DPPPPPPeER. .   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [2,6]     .    .DPPPPPPeER .   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [2,7]     .    .DPPPPPPPeER.   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [2,8]     .    .DPPPPPPPPeER   movdqu	%xmm5, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-3.s b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-3.s
index f37d4199514cf..e23709e4f5a1c 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-3.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-3.s
@@ -65,30 +65,31 @@ movdqu %xmm5, %xmm0
 # CHECK-NEXT:  -      -     1.00    -      -      -      -      -     movdqu	%xmm5, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DR   .    .    ..   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [0,1]     DeER .    .    ..   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [0,2]     D=eER.    .    ..   movups	%xmm1, %xmm2
-# CHECK-NEXT: [0,3]     D==eER    .    ..   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [0,4]     .D==eER   .    ..   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [0,5]     .D===eER  .    ..   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [0,6]     .D====eER .    ..   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [0,2]     DPeER.    .    ..   movups	%xmm1, %xmm2
+# CHECK-NEXT: [0,3]     DPPeER    .    ..   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [0,4]     .DPPeER   .    ..   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [0,5]     .DPPPeER  .    ..   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [0,6]     .DPPPPeER .    ..   movdqu	%xmm5, %xmm0
 # CHECK-NEXT: [1,0]     .D------R .    ..   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [1,1]     . D==eE-R .    ..   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [1,2]     . D===eER .    ..   movups	%xmm1, %xmm2
-# CHECK-NEXT: [1,3]     . D====eER.    ..   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [1,4]     . D=====eER    ..   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [1,5]     .  D=====eER   ..   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [1,6]     .  D======eER  ..   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [1,2]     . DPPPeER .    ..   movups	%xmm1, %xmm2
+# CHECK-NEXT: [1,3]     . DPPPPeER.    ..   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [1,4]     . DPPPPPeER    ..   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [1,5]     .  DPPPPPeER   ..   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [1,6]     .  DPPPPPPeER  ..   movdqu	%xmm5, %xmm0
 # CHECK-NEXT: [2,0]     .  D--------R  ..   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [2,1]     .  D=====eE-R  ..   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [2,2]     .   D=====eER  ..   movups	%xmm1, %xmm2
-# CHECK-NEXT: [2,3]     .   D======eER ..   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [2,4]     .   D=======eER..   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [2,5]     .   D========eER.   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [2,6]     .    D========eER   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [2,2]     .   DPPPPPeER  ..   movups	%xmm1, %xmm2
+# CHECK-NEXT: [2,3]     .   DPPPPPPeER ..   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [2,4]     .   DPPPPPPPeER..   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [2,5]     .   DPPPPPPPPeER.   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [2,6]     .    DPPPPPPPPeER   movdqu	%xmm5, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-4.s b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-4.s
index 93c3e4c5fee59..ab66140d6fa5b 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-4.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-4.s
@@ -59,23 +59,24 @@ mov %edx, %eax
 # CHECK-NEXT:  -      -     0.33    -      -     0.67    -      -     movl	%edx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DR   .  .   xorl	%eax, %eax
 # CHECK-NEXT: [0,1]     DeER .  .   movl	%eax, %ebx
-# CHECK-NEXT: [0,2]     D=eER.  .   movl	%ebx, %ecx
-# CHECK-NEXT: [0,3]     D==eER  .   movl	%ecx, %edx
-# CHECK-NEXT: [0,4]     .D==eER .   movl	%edx, %eax
+# CHECK-NEXT: [0,2]     DPeER.  .   movl	%ebx, %ecx
+# CHECK-NEXT: [0,3]     DPPeER  .   movl	%ecx, %edx
+# CHECK-NEXT: [0,4]     .DPPeER .   movl	%edx, %eax
 # CHECK-NEXT: [1,0]     .D----R .   xorl	%eax, %eax
 # CHECK-NEXT: [1,1]     .DeE--R .   movl	%eax, %ebx
-# CHECK-NEXT: [1,2]     .D=eE-R .   movl	%ebx, %ecx
-# CHECK-NEXT: [1,3]     . D=eER .   movl	%ecx, %edx
-# CHECK-NEXT: [1,4]     . D==eER.   movl	%edx, %eax
+# CHECK-NEXT: [1,2]     .DPeE-R .   movl	%ebx, %ecx
+# CHECK-NEXT: [1,3]     . DPeER .   movl	%ecx, %edx
+# CHECK-NEXT: [1,4]     . DPPeER.   movl	%edx, %eax
 # CHECK-NEXT: [2,0]     . D----R.   xorl	%eax, %eax
 # CHECK-NEXT: [2,1]     . DeE--R.   movl	%eax, %ebx
 # CHECK-NEXT: [2,2]     .  DeE-R.   movl	%ebx, %ecx
-# CHECK-NEXT: [2,3]     .  D=eER.   movl	%ecx, %edx
-# CHECK-NEXT: [2,4]     .  D==eER   movl	%edx, %eax
+# CHECK-NEXT: [2,3]     .  DPeER.   movl	%ecx, %edx
+# CHECK-NEXT: [2,4]     .  DPPeER   movl	%edx, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-5.s b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-5.s
index 775781c5072d5..540f69a822865 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-5.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-5.s
@@ -59,23 +59,24 @@ mov %rdx, %rax
 # CHECK-NEXT:  -      -     0.33    -      -     0.67    -      -     movq	%rdx, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DR   .  .   xorq	%rax, %rax
 # CHECK-NEXT: [0,1]     DeER .  .   movq	%rax, %rbx
-# CHECK-NEXT: [0,2]     D=eER.  .   movq	%rbx, %rcx
-# CHECK-NEXT: [0,3]     D==eER  .   movq	%rcx, %rdx
-# CHECK-NEXT: [0,4]     .D==eER .   movq	%rdx, %rax
+# CHECK-NEXT: [0,2]     DPeER.  .   movq	%rbx, %rcx
+# CHECK-NEXT: [0,3]     DPPeER  .   movq	%rcx, %rdx
+# CHECK-NEXT: [0,4]     .DPPeER .   movq	%rdx, %rax
 # CHECK-NEXT: [1,0]     .D----R .   xorq	%rax, %rax
 # CHECK-NEXT: [1,1]     .DeE--R .   movq	%rax, %rbx
-# CHECK-NEXT: [1,2]     .D=eE-R .   movq	%rbx, %rcx
-# CHECK-NEXT: [1,3]     . D=eER .   movq	%rcx, %rdx
-# CHECK-NEXT: [1,4]     . D==eER.   movq	%rdx, %rax
+# CHECK-NEXT: [1,2]     .DPeE-R .   movq	%rbx, %rcx
+# CHECK-NEXT: [1,3]     . DPeER .   movq	%rcx, %rdx
+# CHECK-NEXT: [1,4]     . DPPeER.   movq	%rdx, %rax
 # CHECK-NEXT: [2,0]     . D----R.   xorq	%rax, %rax
 # CHECK-NEXT: [2,1]     . DeE--R.   movq	%rax, %rbx
 # CHECK-NEXT: [2,2]     .  DeE-R.   movq	%rbx, %rcx
-# CHECK-NEXT: [2,3]     .  D=eER.   movq	%rcx, %rdx
-# CHECK-NEXT: [2,4]     .  D==eER   movq	%rdx, %rax
+# CHECK-NEXT: [2,3]     .  DPeER.   movq	%rcx, %rdx
+# CHECK-NEXT: [2,4]     .  DPPeER   movq	%rdx, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-6.s b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-6.s
index d3aee3db57356..ebae5a7e0b512 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-6.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/reg-move-elimination-6.s
@@ -62,25 +62,26 @@ mov %esi, %ecx
 # CHECK-NEXT:  -      -     1.00    -      -      -      -      -     movl	%esi, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DR   .   .   xorq	%rsi, %rsi
 # CHECK-NEXT: [0,1]     DeER .   .   addq	%rcx, %rcx
-# CHECK-NEXT: [0,2]     D=eER.   .   addq	%rcx, %rcx
-# CHECK-NEXT: [0,3]     D==eER   .   addq	%rcx, %rcx
-# CHECK-NEXT: [0,4]     .D==eER  .   addq	%rcx, %rcx
+# CHECK-NEXT: [0,2]     DPeER.   .   addq	%rcx, %rcx
+# CHECK-NEXT: [0,3]     DPPeER   .   addq	%rcx, %rcx
+# CHECK-NEXT: [0,4]     .DPPeER  .   addq	%rcx, %rcx
 # CHECK-NEXT: [0,5]     .DeE--R  .   movl	%esi, %ecx
 # CHECK-NEXT: [1,0]     .D----R  .   xorq	%rsi, %rsi
-# CHECK-NEXT: [1,1]     .D=eE-R  .   addq	%rcx, %rcx
-# CHECK-NEXT: [1,2]     . D=eER  .   addq	%rcx, %rcx
-# CHECK-NEXT: [1,3]     . D==eER .   addq	%rcx, %rcx
-# CHECK-NEXT: [1,4]     . D===eER.   addq	%rcx, %rcx
+# CHECK-NEXT: [1,1]     .DPeE-R  .   addq	%rcx, %rcx
+# CHECK-NEXT: [1,2]     . DPeER  .   addq	%rcx, %rcx
+# CHECK-NEXT: [1,3]     . DPPeER .   addq	%rcx, %rcx
+# CHECK-NEXT: [1,4]     . DPPPeER.   addq	%rcx, %rcx
 # CHECK-NEXT: [1,5]     . DeE---R.   movl	%esi, %ecx
 # CHECK-NEXT: [2,0]     .  D----R.   xorq	%rsi, %rsi
 # CHECK-NEXT: [2,1]     .  DeE--R.   addq	%rcx, %rcx
-# CHECK-NEXT: [2,2]     .  D=eE-R.   addq	%rcx, %rcx
-# CHECK-NEXT: [2,3]     .  D==eER.   addq	%rcx, %rcx
-# CHECK-NEXT: [2,4]     .   D==eER   addq	%rcx, %rcx
+# CHECK-NEXT: [2,2]     .  DPeE-R.   addq	%rcx, %rcx
+# CHECK-NEXT: [2,3]     .  DPPeER.   addq	%rcx, %rcx
+# CHECK-NEXT: [2,4]     .   DPPeER   addq	%rcx, %rcx
 # CHECK-NEXT: [2,5]     .   DeE--R   movl	%esi, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/store-throughput.s b/llvm/test/tools/llvm-mca/X86/Barcelona/store-throughput.s
index d9aabb783f1e7..f7719c2894844 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/store-throughput.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/store-throughput.s
@@ -121,12 +121,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movb	%dil, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movb	%spl, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movb	%bpl, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movb	%sil, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movb	%dil, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movb	%sil, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movb	%dil, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -219,12 +220,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movw	%di, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movw	%sp, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movw	%bp, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movw	%si, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movw	%di, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movw	%si, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movw	%di, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -317,12 +319,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movl	%edi, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movl	%esp, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movl	%ebp, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movl	%esi, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movl	%edi, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movl	%esi, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movl	%edi, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -415,12 +418,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movq	%rdi, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movq	%rsp, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movq	%rbp, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movq	%rsi, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movq	%rdi, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movq	%rsi, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movq	%rdi, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -513,12 +517,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movd	%mm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movd	%mm0, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movd	%mm1, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movd	%mm2, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movd	%mm3, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movd	%mm2, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movd	%mm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -611,12 +616,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -     movaps	%xmm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movaps	%xmm0, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movaps	%xmm1, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movaps	%xmm2, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movaps	%xmm3, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movaps	%xmm2, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movaps	%xmm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Barcelona/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/Barcelona/zero-idioms.s
index 54ff0134bc8c4..aa03d6533bff4 100644
--- a/llvm/test/tools/llvm-mca/X86/Barcelona/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/Barcelona/zero-idioms.s
@@ -159,6 +159,7 @@ pxor   %xmm2, %xmm2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     pxor	%xmm2, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -167,35 +168,35 @@ pxor   %xmm2, %xmm2
 # CHECK-NEXT: [0,2]     DR   .    .    .    .    .    .    ..   xorl	%eax, %eax
 # CHECK-NEXT: [0,3]     DR   .    .    .    .    .    .    ..   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     .DeeeER   .    .    .    .    .    ..   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     .D===eeeER.    .    .    .    .    ..   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D======eeeER  .    .    .    .    ..   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     .DPPPeeeER.    .    .    .    .    ..   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPPPPPPeeeER  .    .    .    .    ..   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .D----------R  .    .    .    .    ..   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     . D---------R  .    .    .    .    ..   pcmpgtd	%xmm2, %xmm2
 # CHECK-NEXT: [0,9]     . D---------R  .    .    .    .    ..   pcmpgtq	%xmm2, %xmm2
 # CHECK-NEXT: [0,10]    . D---------R  .    .    .    .    ..   pcmpgtw	%xmm2, %xmm2
-# CHECK-NEXT: [0,11]    . D========eeeER    .    .    .    ..   psubb	%mm2, %mm2
-# CHECK-NEXT: [0,12]    .  D==========eeeER .    .    .    ..   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,13]    .  D=============eER.    .    .    ..   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,14]    .  D==============eeeER  .    .    ..   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,11]    . DPPPPPPPPeeeER    .    .    .    ..   psubb	%mm2, %mm2
+# CHECK-NEXT: [0,12]    .  DPPPPPPPPPPeeeER .    .    .    ..   psubd	%mm2, %mm2
+# CHECK-NEXT: [0,13]    .  DPPPPPPPPPPPPPeER.    .    .    ..   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,14]    .  DPPPPPPPPPPPPPPeeeER  .    .    ..   psubw	%mm2, %mm2
 # CHECK-NEXT: [0,15]    .  D------------------R  .    .    ..   psubb	%xmm2, %xmm2
 # CHECK-NEXT: [0,16]    .   D-----------------R  .    .    ..   psubd	%xmm2, %xmm2
 # CHECK-NEXT: [0,17]    .   D-----------------R  .    .    ..   psubq	%xmm2, %xmm2
 # CHECK-NEXT: [0,18]    .   D-----------------R  .    .    ..   psubw	%xmm2, %xmm2
-# CHECK-NEXT: [0,19]    .   D================eeeER    .    ..   psubsb	%mm2, %mm2
-# CHECK-NEXT: [0,20]    .    D==================eeeER .    ..   psubsw	%mm2, %mm2
+# CHECK-NEXT: [0,19]    .   DPPPPPPPPPPPPPPPPeeeER    .    ..   psubsb	%mm2, %mm2
+# CHECK-NEXT: [0,20]    .    DPPPPPPPPPPPPPPPPPPeeeER .    ..   psubsw	%mm2, %mm2
 # CHECK-NEXT: [0,21]    .    DeE--------------------R .    ..   psubsb	%xmm2, %xmm2
-# CHECK-NEXT: [0,22]    .    D=eE-------------------R .    ..   psubsw	%xmm2, %xmm2
-# CHECK-NEXT: [0,23]    .    D=====================eeeER   ..   psubusb	%mm2, %mm2
-# CHECK-NEXT: [0,24]    .    .D=======================eeeER..   psubusw	%mm2, %mm2
-# CHECK-NEXT: [0,25]    .    .D=eE------------------------R..   psubusb	%xmm2, %xmm2
-# CHECK-NEXT: [0,26]    .    .D==eE-----------------------R..   psubusw	%xmm2, %xmm2
+# CHECK-NEXT: [0,22]    .    DPeE-------------------R .    ..   psubsw	%xmm2, %xmm2
+# CHECK-NEXT: [0,23]    .    DPPPPPPPPPPPPPPPPPPPPPeeeER   ..   psubusb	%mm2, %mm2
+# CHECK-NEXT: [0,24]    .    .DPPPPPPPPPPPPPPPPPPPPPPPeeeER..   psubusw	%mm2, %mm2
+# CHECK-NEXT: [0,25]    .    .DPeE------------------------R..   psubusb	%xmm2, %xmm2
+# CHECK-NEXT: [0,26]    .    .DPPeE-----------------------R..   psubusw	%xmm2, %xmm2
 # CHECK-NEXT: [0,27]    .    .D==eE-----------------------R..   andnps	%xmm0, %xmm0
 # CHECK-NEXT: [0,28]    .    . D==eE----------------------R..   andnpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,29]    .    . D=========================eER.   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    . D==eE-----------------------R.   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,29]    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPeER.   pandn	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    . DPPeE-----------------------R.   pandn	%xmm2, %xmm2
 # CHECK-NEXT: [0,31]    .    . D---------------------------R.   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,32]    .    .  D--------------------------R.   xorpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,33]    .    .  D=========================eER   pxor	%mm2, %mm2
+# CHECK-NEXT: [0,33]    .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPeER   pxor	%mm2, %mm2
 # CHECK-NEXT: [0,34]    .    .  D---------------------------R   pxor	%xmm2, %xmm2
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/add-sequence.s b/llvm/test/tools/llvm-mca/X86/BdVer2/add-sequence.s
index 918fb1d1d3a41..ac7aaf64c719e 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/add-sequence.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/add-sequence.s
@@ -64,39 +64,40 @@ add %eax, %edx
 # CHECK-NEXT:  -      -      -      -      -     1.00   1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addl	%eax, %edx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeER .    .    .    .    .    ..   addl	%eax, %ecx
 # CHECK-NEXT: [0,1]     DeER .    .    .    .    .    ..   addl	%esi, %eax
-# CHECK-NEXT: [0,2]     D==eER    .    .    .    .    ..   addl	%eax, %edx
-# CHECK-NEXT: [1,0]     D====eER  .    .    .    .    ..   addl	%eax, %ecx
+# CHECK-NEXT: [0,2]     DP=eER    .    .    .    .    ..   addl	%eax, %edx
+# CHECK-NEXT: [1,0]     DP===eER  .    .    .    .    ..   addl	%eax, %ecx
 # CHECK-NEXT: [1,1]     .D=eE--R  .    .    .    .    ..   addl	%esi, %eax
-# CHECK-NEXT: [1,2]     .D===eER  .    .    .    .    ..   addl	%eax, %edx
-# CHECK-NEXT: [2,0]     .D=====eER.    .    .    .    ..   addl	%eax, %ecx
-# CHECK-NEXT: [2,1]     .D=====eER.    .    .    .    ..   addl	%esi, %eax
-# CHECK-NEXT: [2,2]     . D======eER   .    .    .    ..   addl	%eax, %edx
-# CHECK-NEXT: [3,0]     . D========eER .    .    .    ..   addl	%eax, %ecx
-# CHECK-NEXT: [3,1]     . D======eE--R .    .    .    ..   addl	%esi, %eax
-# CHECK-NEXT: [3,2]     . D========eER .    .    .    ..   addl	%eax, %edx
-# CHECK-NEXT: [4,0]     .  D=========eER    .    .    ..   addl	%eax, %ecx
-# CHECK-NEXT: [4,1]     .  D=========eER    .    .    ..   addl	%esi, %eax
-# CHECK-NEXT: [4,2]     .  D===========eER  .    .    ..   addl	%eax, %edx
-# CHECK-NEXT: [5,0]     .  D=============eER.    .    ..   addl	%eax, %ecx
-# CHECK-NEXT: [5,1]     .   D==========eE--R.    .    ..   addl	%esi, %eax
-# CHECK-NEXT: [5,2]     .   D============eER.    .    ..   addl	%eax, %edx
-# CHECK-NEXT: [6,0]     .   D==============eER   .    ..   addl	%eax, %ecx
-# CHECK-NEXT: [6,1]     .   D==============eER   .    ..   addl	%esi, %eax
-# CHECK-NEXT: [6,2]     .    D===============eER .    ..   addl	%eax, %edx
-# CHECK-NEXT: [7,0]     .    D=================eER    ..   addl	%eax, %ecx
-# CHECK-NEXT: [7,1]     .    D===============eE--R    ..   addl	%esi, %eax
-# CHECK-NEXT: [7,2]     .    D=================eER    ..   addl	%eax, %edx
-# CHECK-NEXT: [8,0]     .    .D==================eER  ..   addl	%eax, %ecx
-# CHECK-NEXT: [8,1]     .    .D==================eER  ..   addl	%esi, %eax
-# CHECK-NEXT: [8,2]     .    .D====================eER..   addl	%eax, %edx
-# CHECK-NEXT: [9,0]     .    .D======================eER   addl	%eax, %ecx
-# CHECK-NEXT: [9,1]     .    . D===================eE--R   addl	%esi, %eax
-# CHECK-NEXT: [9,2]     .    . D=====================eER   addl	%eax, %edx
+# CHECK-NEXT: [1,2]     .DPP=eER  .    .    .    .    ..   addl	%eax, %edx
+# CHECK-NEXT: [2,0]     .DPPPP=eER.    .    .    .    ..   addl	%eax, %ecx
+# CHECK-NEXT: [2,1]     .DPP===eER.    .    .    .    ..   addl	%esi, %eax
+# CHECK-NEXT: [2,2]     . DPPPPP=eER   .    .    .    ..   addl	%eax, %edx
+# CHECK-NEXT: [3,0]     . DPPPPP===eER .    .    .    ..   addl	%eax, %ecx
+# CHECK-NEXT: [3,1]     . DPPPPP=eE--R .    .    .    ..   addl	%esi, %eax
+# CHECK-NEXT: [3,2]     . DPPPPPPP=eER .    .    .    ..   addl	%eax, %edx
+# CHECK-NEXT: [4,0]     .  DPPPPPPPP=eER    .    .    ..   addl	%eax, %ecx
+# CHECK-NEXT: [4,1]     .  DPPPPPP===eER    .    .    ..   addl	%esi, %eax
+# CHECK-NEXT: [4,2]     .  DPPPPPPPPPP=eER  .    .    ..   addl	%eax, %edx
+# CHECK-NEXT: [5,0]     .  DPPPPPPPPPP===eER.    .    ..   addl	%eax, %ecx
+# CHECK-NEXT: [5,1]     .   DPPPPPPPPP=eE--R.    .    ..   addl	%esi, %eax
+# CHECK-NEXT: [5,2]     .   DPPPPPPPPPPP=eER.    .    ..   addl	%eax, %edx
+# CHECK-NEXT: [6,0]     .   DPPPPPPPPPPPPP=eER   .    ..   addl	%eax, %ecx
+# CHECK-NEXT: [6,1]     .   DPPPPPPPPPPP===eER   .    ..   addl	%esi, %eax
+# CHECK-NEXT: [6,2]     .    DPPPPPPPPPPPPPP=eER .    ..   addl	%eax, %edx
+# CHECK-NEXT: [7,0]     .    DPPPPPPPPPPPPPP===eER    ..   addl	%eax, %ecx
+# CHECK-NEXT: [7,1]     .    DPPPPPPPPPPPPPP=eE--R    ..   addl	%esi, %eax
+# CHECK-NEXT: [7,2]     .    DPPPPPPPPPPPPPPPP=eER    ..   addl	%eax, %edx
+# CHECK-NEXT: [8,0]     .    .DPPPPPPPPPPPPPPPPP=eER  ..   addl	%eax, %ecx
+# CHECK-NEXT: [8,1]     .    .DPPPPPPPPPPPPPPP===eER  ..   addl	%esi, %eax
+# CHECK-NEXT: [8,2]     .    .DPPPPPPPPPPPPPPPPPPP=eER..   addl	%eax, %edx
+# CHECK-NEXT: [9,0]     .    .DPPPPPPPPPPPPPPPPPPP===eER   addl	%eax, %ecx
+# CHECK-NEXT: [9,1]     .    . DPPPPPPPPPPPPPPPPPP=eE--R   addl	%esi, %eax
+# CHECK-NEXT: [9,2]     .    . DPPPPPPPPPPPPPPPPPPPP=eER   addl	%eax, %edx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-1.s b/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-1.s
index bc0aa4e6e3344..9d462c1e7cdfe 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-1.s
@@ -38,17 +38,18 @@ bsf   %rax, %rcx
 # CHECK-NEXT:  6      3     3.00                        bsfq	%rax, %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    . .   imulq	$5, %rcx, %rax
 # CHECK-NEXT: [0,1]     DeeE----R .    . .   lzcntl	%ecx, %eax
-# CHECK-NEXT: [0,2]     D==eE---R .    . .   andq	%rcx, %rax
-# CHECK-NEXT: [0,3]     .D==eeeER .    . .   bsfq	%rax, %rcx
-# CHECK-NEXT: [1,0]     . D====eeeeeeER. .   imulq	$5, %rcx, %rax
-# CHECK-NEXT: [1,1]     .  D======eeE-R. .   lzcntl	%ecx, %eax
-# CHECK-NEXT: [1,2]     .  D========eER. .   andq	%rcx, %rax
-# CHECK-NEXT: [1,3]     .   D========eeeER   bsfq	%rax, %rcx
+# CHECK-NEXT: [0,2]     DPPeE---R .    . .   andq	%rcx, %rax
+# CHECK-NEXT: [0,3]     .DPPeeeER .    . .   bsfq	%rax, %rcx
+# CHECK-NEXT: [1,0]     . DPPPPeeeeeeER. .   imulq	$5, %rcx, %rax
+# CHECK-NEXT: [1,1]     .  DPPP===eeE-R. .   lzcntl	%ecx, %eax
+# CHECK-NEXT: [1,2]     .  DPPPPPPPPeER. .   andq	%rcx, %rax
+# CHECK-NEXT: [1,3]     .   DPPPPPPPPeeeER   bsfq	%rax, %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-2.s
index 35754bba21cc9..38d934695416c 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-2.s
@@ -70,19 +70,20 @@ vandps %xmm4, %xmm1, %xmm0
 # CHECK-NEXT:  1      2     0.50                        vandps	%xmm4, %xmm1, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .    .    .    .    .    .    .    .    .    .    ..   vdivps	%ymm0, %ymm1, %ymm3
 # CHECK-NEXT: [0,1]     DeeeeeE----R   .    .    .    .    .    .    .    .    .    .    ..   vaddps	%xmm0, %xmm1, %xmm3
-# CHECK-NEXT: [0,2]     .D====eeeeeER  .    .    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,3]     .D======eeeeeER.    .    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,4]     . D=======eeeeeER   .    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,5]     . D=========eeeeeER .    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,6]     .  D==========eeeeeER    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,7]     .  D============eeeeeER  .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,8]     .   D=============eeeeeER.    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,9]     .   D==============eeeeeER    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,2]     .DPPPPeeeeeER  .    .    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,3]     .DPPPP==eeeeeER.    .    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,4]     . DPPP====eeeeeER   .    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,5]     . DPPP======eeeeeER .    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,6]     .  DPP========eeeeeER    .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,7]     .  DPP==========eeeeeER  .    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,8]     .   DP============eeeeeER.    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,9]     .   DP=============eeeeeER    .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,10]    .    D==============eeeeeER   .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,11]    .    D===============eeeeeER  .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,12]    .    .D===============eeeeeER .    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
@@ -90,25 +91,25 @@ vandps %xmm4, %xmm1, %xmm0
 # CHECK-NEXT: [0,14]    .    . D================eeeeeER    .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,15]    .    . D=================eeeeeER   .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,16]    .    .  D=================eeeeeER  .    .    .    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,17]    .    .  D======================eeER.    .    .    .    .    .    ..   vandps	%xmm4, %xmm1, %xmm0
-# CHECK-NEXT: [1,0]     .    .   D=======================eeeeeeeeeER .    .    .    .    ..   vdivps	%ymm0, %ymm1, %ymm3
-# CHECK-NEXT: [1,1]     .    .   D=======================eeeeeE----R .    .    .    .    ..   vaddps	%xmm0, %xmm1, %xmm3
-# CHECK-NEXT: [1,2]     .    .    D===========================eeeeeER.    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,3]     .    .    D=============================eeeeeER   .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,4]     .    .    .D==============================eeeeeER .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,5]     .    .    .D================================eeeeeER    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,6]     .    .    . D=================================eeeeeER  .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,7]     .    .    . D===================================eeeeeER.    .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,8]     .    .    .  D====================================eeeeeER   .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,9]     .    .    .  D=====================================eeeeeER  .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,10]    .    .    .   D=====================================eeeeeER .    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,11]    .    .    .   D======================================eeeeeER.    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,12]    .    .    .    D======================================eeeeeER    ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,13]    .    .    .    D=======================================eeeeeER   ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,14]    .    .    .    .D=======================================eeeeeER  ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,15]    .    .    .    .D========================================eeeeeER ..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,16]    .    .    .    . D========================================eeeeeER..   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,17]    .    .    .    . D=============================================eeER   vandps	%xmm4, %xmm1, %xmm0
+# CHECK-NEXT: [0,17]    .    .  DPPPPPPPPPPPPPPPPPPPPPPeeER.    .    .    .    .    .    ..   vandps	%xmm4, %xmm1, %xmm0
+# CHECK-NEXT: [1,0]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeER .    .    .    .    ..   vdivps	%ymm0, %ymm1, %ymm3
+# CHECK-NEXT: [1,1]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPeeeeeE----R .    .    .    .    ..   vaddps	%xmm0, %xmm1, %xmm3
+# CHECK-NEXT: [1,2]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER.    .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,3]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPP==eeeeeER   .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,4]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPP====eeeeeER .    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,5]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPP======eeeeeER    .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,6]     .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPP========eeeeeER  .    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,7]     .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPP==========eeeeeER.    .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,8]     .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPP============eeeeeER   .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,9]     .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPP=============eeeeeER  .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,10]    .    .    .   DPPPPPPPPPPPPPPPPPPPPPPP==============eeeeeER .    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,11]    .    .    .   DPPPPPPPPPPPPPPPPPPPPPPP===============eeeeeER.    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,12]    .    .    .    DPPPPPPPPPPPPPPPPPPPPPP================eeeeeER    ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,13]    .    .    .    DPPPPPPPPPPPPPPPPPPPPPP=================eeeeeER   ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,14]    .    .    .    .DPPPPPPPPPPPPPPPPPPPPP==================eeeeeER  ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,15]    .    .    .    .DPPPPPPPPPPPPPPPPPPPPP===================eeeeeER ..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,16]    .    .    .    . DPPPPPPPPPPPPPPPPPPPP====================eeeeeER..   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,17]    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER   vandps	%xmm4, %xmm1, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-3.s b/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-3.s
index 32a440966f876..b651368b3a87b 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/clear-super-register-3.s
@@ -43,15 +43,16 @@ addps  %xmm0, %xmm0
 # CHECK-NEXT:  1      5     1.00                        addps	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
 # CHECK:      [0,0]     D=eeeeeeeeeER  .    . .   sqrtss	%xmm0, %xmm0
 # CHECK-NEXT: [0,1]     DeeeeeE-----R  .    . .   movss	(%eax), %xmm0
-# CHECK-NEXT: [0,2]     D======eeeeeER .    . .   addps	%xmm0, %xmm0
-# CHECK-NEXT: [1,0]     D===========eeeeeeeeeER   sqrtss	%xmm0, %xmm0
+# CHECK-NEXT: [0,2]     DPPPPP=eeeeeER .    . .   addps	%xmm0, %xmm0
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPeeeeeeeeeER   sqrtss	%xmm0, %xmm0
 # CHECK-NEXT: [1,1]     .D==eeeeeE------------R   movss	(%eax), %xmm0
-# CHECK-NEXT: [1,2]     .D=========eeeeeE-----R   addps	%xmm0, %xmm0
+# CHECK-NEXT: [1,2]     .DPPPPPPP==eeeeeE-----R   addps	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -91,15 +92,16 @@ addps  %xmm0, %xmm0
 # CHECK-NEXT:  1      5     1.00                        addps	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
 # CHECK:      [0,0]     D=eeeeeeeeeER  .    . .   sqrtsd	%xmm0, %xmm0
 # CHECK-NEXT: [0,1]     DeeeeeE-----R  .    . .   movsd	(%eax), %xmm0
-# CHECK-NEXT: [0,2]     D======eeeeeER .    . .   addps	%xmm0, %xmm0
-# CHECK-NEXT: [1,0]     D===========eeeeeeeeeER   sqrtsd	%xmm0, %xmm0
+# CHECK-NEXT: [0,2]     DPPPPP=eeeeeER .    . .   addps	%xmm0, %xmm0
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPeeeeeeeeeER   sqrtsd	%xmm0, %xmm0
 # CHECK-NEXT: [1,1]     .D==eeeeeE------------R   movsd	(%eax), %xmm0
-# CHECK-NEXT: [1,2]     .D=========eeeeeE-----R   addps	%xmm0, %xmm0
+# CHECK-NEXT: [1,2]     .DPPPPPPP==eeeeeE-----R   addps	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-cmp.s b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-cmp.s
index fbf47e4d83ef8..6da4001f7ca20 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-cmp.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-cmp.s
@@ -66,14 +66,15 @@ cmovae %ebx, %eax
 # CHECK-NEXT:  -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     cmovael	%ebx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   cmpl	%eax, %eax
-# CHECK-NEXT: [0,1]     D==eER .   cmovael	%ebx, %eax
+# CHECK-NEXT: [0,1]     DP=eER .   cmovael	%ebx, %eax
 # CHECK-NEXT: [1,0]     DeE--R .   cmpl	%eax, %eax
-# CHECK-NEXT: [1,1]     D===eER.   cmovael	%ebx, %eax
+# CHECK-NEXT: [1,1]     DPPPeER.   cmovael	%ebx, %eax
 # CHECK-NEXT: [2,0]     .D=eE-R.   cmpl	%eax, %eax
-# CHECK-NEXT: [2,1]     .D===eER   cmovael	%ebx, %eax
+# CHECK-NEXT: [2,1]     .DPPPeER   cmovael	%ebx, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-pcmpeq.s b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-pcmpeq.s
index a1a921e59fed1..db9324d90a286 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-pcmpeq.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-pcmpeq.s
@@ -73,21 +73,22 @@ vpcmpeqq %xmm3, %xmm3, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -     1.00    -      -      -      -      -     vpcmpeqq	%xmm3, %xmm3, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   vpcmpeqb	%xmm0, %xmm0, %xmm1
 # CHECK-NEXT: [0,1]     D=eeER    .   vpcmpeqw	%xmm1, %xmm1, %xmm2
 # CHECK-NEXT: [0,2]     DeeE-R    .   vpcmpeqd	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [0,3]     D==eeER   .   vpcmpeqq	%xmm3, %xmm3, %xmm0
+# CHECK-NEXT: [0,3]     DPPeeER   .   vpcmpeqq	%xmm3, %xmm3, %xmm0
 # CHECK-NEXT: [1,0]     .DeeE-R   .   vpcmpeqb	%xmm0, %xmm0, %xmm1
 # CHECK-NEXT: [1,1]     .D==eeER  .   vpcmpeqw	%xmm1, %xmm1, %xmm2
 # CHECK-NEXT: [1,2]     .D=eeE-R  .   vpcmpeqd	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [1,3]     .D===eeER .   vpcmpeqq	%xmm3, %xmm3, %xmm0
+# CHECK-NEXT: [1,3]     .DPPPeeER .   vpcmpeqq	%xmm3, %xmm3, %xmm0
 # CHECK-NEXT: [2,0]     . D=eeE-R .   vpcmpeqb	%xmm0, %xmm0, %xmm1
 # CHECK-NEXT: [2,1]     . D===eeER.   vpcmpeqw	%xmm1, %xmm1, %xmm2
 # CHECK-NEXT: [2,2]     . D==eeE-R.   vpcmpeqd	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [2,3]     . D====eeER   vpcmpeqq	%xmm3, %xmm3, %xmm0
+# CHECK-NEXT: [2,3]     . DPPPPeeER   vpcmpeqq	%xmm3, %xmm3, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-pcmpgt.s b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-pcmpgt.s
index 09d67e761aea3..fadf74c950246 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-pcmpgt.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-pcmpgt.s
@@ -74,6 +74,7 @@ vpcmpgtq %xmm3, %xmm3, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -     vpcmpgtq	%xmm3, %xmm3, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DR   ..   vpcmpgtb	%xmm0, %xmm0, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-1.s b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-1.s
index 233586223ad9a..6cb1dd302bc6e 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-1.s
@@ -67,14 +67,15 @@ sbb %eax, %eax
 # CHECK-NEXT:  -      -      -      -      -     2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     sbbl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   sbbl	%edx, %edx
-# CHECK-NEXT: [0,1]     D=eER.  .   sbbl	%eax, %eax
-# CHECK-NEXT: [1,0]     D==eER  .   sbbl	%edx, %edx
-# CHECK-NEXT: [1,1]     D===eER .   sbbl	%eax, %eax
-# CHECK-NEXT: [2,0]     .D===eER.   sbbl	%edx, %edx
-# CHECK-NEXT: [2,1]     .D====eER   sbbl	%eax, %eax
+# CHECK-NEXT: [0,1]     DPeER.  .   sbbl	%eax, %eax
+# CHECK-NEXT: [1,0]     DPPeER  .   sbbl	%edx, %edx
+# CHECK-NEXT: [1,1]     DPPPeER .   sbbl	%eax, %eax
+# CHECK-NEXT: [2,0]     .DPPPeER.   sbbl	%edx, %edx
+# CHECK-NEXT: [2,1]     .DPPPPeER   sbbl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-2.s
index 0b48eb597fc14..39e3f4d097634 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-2.s
@@ -70,18 +70,19 @@ sbb %eax, %eax
 # CHECK-NEXT:  -      -      -      -      -     1.33   0.67    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     sbbl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     D==eeeeER .   .   imull	%edx, %eax
 # CHECK-NEXT: [0,1]     DeE-----R .   .   addl	%edx, %edx
-# CHECK-NEXT: [0,2]     D===eE--R .   .   sbbl	%eax, %eax
-# CHECK-NEXT: [1,0]     D=====eeeeER  .   imull	%edx, %eax
+# CHECK-NEXT: [0,2]     DP==eE--R .   .   sbbl	%eax, %eax
+# CHECK-NEXT: [1,0]     DPPPP=eeeeER  .   imull	%edx, %eax
 # CHECK-NEXT: [1,1]     .DeE-------R  .   addl	%edx, %edx
-# CHECK-NEXT: [1,2]     .D====eE---R  .   sbbl	%eax, %eax
-# CHECK-NEXT: [2,0]     .D=======eeeeER   imull	%edx, %eax
-# CHECK-NEXT: [2,1]     .D==eE--------R   addl	%edx, %edx
-# CHECK-NEXT: [2,2]     . D=====eE----R   sbbl	%eax, %eax
+# CHECK-NEXT: [1,2]     .DP===eE---R  .   sbbl	%eax, %eax
+# CHECK-NEXT: [2,0]     .DPPPPP==eeeeER   imull	%edx, %eax
+# CHECK-NEXT: [2,1]     .DP=eE--------R   addl	%edx, %edx
+# CHECK-NEXT: [2,2]     . DPP===eE----R   sbbl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/dependent-pmuld-paddd.s b/llvm/test/tools/llvm-mca/X86/BdVer2/dependent-pmuld-paddd.s
index ade61a03b6a62..10332487d8fa1 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/dependent-pmuld-paddd.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/dependent-pmuld-paddd.s
@@ -64,39 +64,40 @@ vpaddd %xmm0, %xmm0, %xmm3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -     1.00    -      -      -      -      -      -     vpaddd	%xmm0, %xmm0, %xmm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          01234
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .    .    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [0,1]     D====eeER .    .    .    .    .    .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [0,2]     D======eeER    .    .    .    .    .    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [1,0]     D======eeeeER  .    .    .    .    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [1,1]     .D=========eeER.    .    .    .    .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [1,2]     .D===========eeER   .    .    .    .    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [2,0]     .D===========eeeeER .    .    .    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [2,1]     .D===============eeER    .    .    .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [2,2]     . D================eeER  .    .    .    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [3,0]     . D================eeeeER.    .    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [3,1]     . D====================eeER   .    .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [3,2]     . D======================eeER .    .    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [4,0]     .  D=====================eeeeER    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [4,1]     .  D=========================eeER  .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [4,2]     .  D===========================eeER.    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [5,0]     .  D===========================eeeeER   .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [5,1]     .   D==============================eeER .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [5,2]     .   D================================eeER    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [6,0]     .   D================================eeeeER  .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [6,1]     .   D====================================eeER.    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [6,2]     .    D=====================================eeER   .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [7,0]     .    D=====================================eeeeER .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [7,1]     .    D=========================================eeER    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [7,2]     .    D===========================================eeER  .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [8,0]     .    .D==========================================eeeeER.    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [8,1]     .    .D==============================================eeER   .   .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [8,2]     .    .D================================================eeER .   .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [9,0]     .    .D================================================eeeeER   .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [9,1]     .    . D===================================================eeER .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [9,2]     .    . D=====================================================eeER   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [0,1]     DPPPPeeER .    .    .    .    .    .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [0,2]     DPPPPPPeeER    .    .    .    .    .    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [1,0]     DPPPPPPeeeeER  .    .    .    .    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [1,1]     .DPPPPPPPPPeeER.    .    .    .    .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [1,2]     .DPPPPPPPPPPPeeER   .    .    .    .    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [2,0]     .DPPPPPPPPPPPeeeeER .    .    .    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [2,1]     .DPPPPPPPPPPPPPPPeeER    .    .    .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [2,2]     . DPPPPPPPPPPPPPPPPeeER  .    .    .    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [3,0]     . DPPPPPPPPPPPPPPPPeeeeER.    .    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [3,1]     . DPPPPPPPPPPPPPPPPPPPPeeER   .    .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [3,2]     . DPPPPPPPPPPPPPPPPPPPPPPeeER .    .    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [4,0]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeER    .    .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [4,1]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPeeER  .    .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [4,2]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER.    .    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [5,0]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   .    .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [5,1]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER .    .    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [5,2]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER    .    .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [6,0]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER  .    .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [6,1]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER.    .    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [6,2]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER   .    .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [7,0]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER .    .    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [7,1]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER    .    .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [7,2]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER  .    .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [8,0]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER.    .   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [8,1]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER   .   .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [8,2]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER .   .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [9,0]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeER   .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [9,1]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [9,2]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER   vpaddd	%xmm0, %xmm0, %xmm3
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/dot-product.s b/llvm/test/tools/llvm-mca/X86/BdVer2/dot-product.s
index 15c12903c94b6..773d74f3c1e4a 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/dot-product.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/dot-product.s
@@ -64,18 +64,19 @@ vhaddps  %xmm3, %xmm3, %xmm4
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     2.48   2.52    -      -      -      -     1.00    -      -      -      -      -      -      -      -     vhaddps	%xmm3, %xmm3, %xmm4
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .   .   vmulps	%xmm0, %xmm1, %xmm2
-# CHECK-NEXT: [0,1]     D=====eeeeeeeeeeeER .    .    .   .   vhaddps	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [0,2]     .D===============eeeeeeeeeeeER.   .   vhaddps	%xmm3, %xmm3, %xmm4
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeeeeeeeER .    .    .   .   vhaddps	%xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [0,2]     .DPPPPPPPPPPPPPPPeeeeeeeeeeeER.   .   vhaddps	%xmm3, %xmm3, %xmm4
 # CHECK-NEXT: [1,0]     .DeeeeeE---------------------R.   .   vmulps	%xmm0, %xmm1, %xmm2
-# CHECK-NEXT: [1,1]     . D====eeeeeeeeeeeE----------R.   .   vhaddps	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [1,2]     .  D==============eeeeeeeeeeeER   .   vhaddps	%xmm3, %xmm3, %xmm4
+# CHECK-NEXT: [1,1]     . DPPPPeeeeeeeeeeeE----------R.   .   vhaddps	%xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [1,2]     .  DPPPPPPPPPPPPPPeeeeeeeeeeeER   .   vhaddps	%xmm3, %xmm3, %xmm4
 # CHECK-NEXT: [2,0]     .  DeeeeeE--------------------R   .   vmulps	%xmm0, %xmm1, %xmm2
-# CHECK-NEXT: [2,1]     .   D======eeeeeeeeeeeE-------R   .   vhaddps	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [2,2]     .    D================eeeeeeeeeeeER   vhaddps	%xmm3, %xmm3, %xmm4
+# CHECK-NEXT: [2,1]     .   DPPPP==eeeeeeeeeeeE-------R   .   vhaddps	%xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [2,2]     .    DPPPPPPPPPPPPPPPPeeeeeeeeeeeER   vhaddps	%xmm3, %xmm3, %xmm4
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/hadd-read-after-ld-1.s b/llvm/test/tools/llvm-mca/X86/BdVer2/hadd-read-after-ld-1.s
index 3a94cf970c7d6..dde723592ef05 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/hadd-read-after-ld-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/hadd-read-after-ld-1.s
@@ -27,6 +27,7 @@ vhaddps (%rdi), %xmm1, %xmm2
 # CHECK-NEXT:  4      16    2.50    *                   vhaddps	(%rdi), %xmm1, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/hadd-read-after-ld-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/hadd-read-after-ld-2.s
index cd05a43407a87..8fc35208569be 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/hadd-read-after-ld-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/hadd-read-after-ld-2.s
@@ -27,6 +27,7 @@ vhaddps (%rdi), %ymm1, %ymm2
 # CHECK-NEXT:  10     16    4.00    *                   vhaddps	(%rdi), %ymm1, %ymm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/int-to-fpu-forwarding-3.s b/llvm/test/tools/llvm-mca/X86/BdVer2/int-to-fpu-forwarding-3.s
index 1df029fdcb24e..24199d40e25a0 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/int-to-fpu-forwarding-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/int-to-fpu-forwarding-3.s
@@ -64,18 +64,19 @@ vpinsrb $1, %eax, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     3.00    -      -      -     1.00    -      -      -      -      -      -      -      -     vpinsrb	$1, %eax, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
 # CHECK:      [0,0]     DeER .    .    .    .    .   addl	%eax, %eax
-# CHECK-NEXT: [0,1]     D===========eeER    .    .   vpinsrb	$0, %eax, %xmm0, %xmm0
-# CHECK-NEXT: [0,2]     .D============eeER  .    .   vpinsrb	$1, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPPPPPPPPPPPeeER    .    .   vpinsrb	$0, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [0,2]     .DPPPPPPPPPPPPeeER  .    .   vpinsrb	$1, %eax, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     .DeE-------------R  .    .   addl	%eax, %eax
-# CHECK-NEXT: [1,1]     . D=============eeER.    .   vpinsrb	$0, %eax, %xmm0, %xmm0
-# CHECK-NEXT: [1,2]     . D===============eeER   .   vpinsrb	$1, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     . DPPPPPPPPPPPPPeeER.    .   vpinsrb	$0, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [1,2]     . DPPPPPPPPPPPPPPPeeER   .   vpinsrb	$1, %eax, %xmm0, %xmm0
 # CHECK-NEXT: [2,0]     .  DeE---------------R   .   addl	%eax, %eax
-# CHECK-NEXT: [2,1]     .  D================eeER .   vpinsrb	$0, %eax, %xmm0, %xmm0
-# CHECK-NEXT: [2,2]     .   D=================eeER   vpinsrb	$1, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [2,1]     .  DPPPPPPPPPPPPPPPPeeER .   vpinsrb	$0, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [2,2]     .   DPPPPPPPPPPPPPPPPPeeER   vpinsrb	$1, %eax, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/load-store-alias.s b/llvm/test/tools/llvm-mca/X86/BdVer2/load-store-alias.s
index 54c07d70e2a74..e08c2f2d29478 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/load-store-alias.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/load-store-alias.s
@@ -79,17 +79,18 @@ vmovaps %xmm0, 48(%rdi)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -     3.00    -      -      -      -      -     1.00   vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   vmovaps	(%rsi), %xmm0
-# CHECK-NEXT: [0,1]     D=====eER .    .    .    ..   vmovaps	%xmm0, (%rdi)
-# CHECK-NEXT: [0,2]     D======eeeeeER .    .    ..   vmovaps	16(%rsi), %xmm0
-# CHECK-NEXT: [0,3]     D===========eER.    .    ..   vmovaps	%xmm0, 16(%rdi)
-# CHECK-NEXT: [0,4]     .D===========eeeeeER.    ..   vmovaps	32(%rsi), %xmm0
-# CHECK-NEXT: [0,5]     .D================eER    ..   vmovaps	%xmm0, 32(%rdi)
-# CHECK-NEXT: [0,6]     .D=================eeeeeER.   vmovaps	48(%rsi), %xmm0
-# CHECK-NEXT: [0,7]     .D======================eER   vmovaps	%xmm0, 48(%rdi)
+# CHECK-NEXT: [0,1]     DPPPPPeER .    .    .    ..   vmovaps	%xmm0, (%rdi)
+# CHECK-NEXT: [0,2]     DPPPPPPeeeeeER .    .    ..   vmovaps	16(%rsi), %xmm0
+# CHECK-NEXT: [0,3]     DPPPPPPPPPPPeER.    .    ..   vmovaps	%xmm0, 16(%rdi)
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPPeeeeeER.    ..   vmovaps	32(%rsi), %xmm0
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPPeER    ..   vmovaps	%xmm0, 32(%rdi)
+# CHECK-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPeeeeeER.   vmovaps	48(%rsi), %xmm0
+# CHECK-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPeER   vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s b/llvm/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s
index 1259de2cdd8b1..caa50d7f9672e 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s
@@ -141,12 +141,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   movb	%dil, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movb	%spl, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movb	(%rcx), %bpl
 # CHECK-NEXT: [0,2]     D=eeeeeER   movb	(%rdx), %sil
-# CHECK-NEXT: [0,3]     D==eE---R   movb	%dil, (%rbx)
+# CHECK-NEXT: [0,3]     DP=eE---R   movb	%dil, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -259,12 +260,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   movw	%di, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movw	%sp, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movw	(%rcx), %bp
 # CHECK-NEXT: [0,2]     D=eeeeeER   movw	(%rdx), %si
-# CHECK-NEXT: [0,3]     D==eE---R   movw	%di, (%rbx)
+# CHECK-NEXT: [0,3]     DP=eE---R   movw	%di, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -377,12 +379,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   movl	%edi, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movl	%esp, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movl	(%rcx), %ebp
 # CHECK-NEXT: [0,2]     D=eeeeeER   movl	(%rdx), %esi
-# CHECK-NEXT: [0,3]     D==eE---R   movl	%edi, (%rbx)
+# CHECK-NEXT: [0,3]     DP=eE---R   movl	%edi, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -495,12 +498,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   movq	%rdi, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movq	%rsp, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movq	(%rcx), %rbp
 # CHECK-NEXT: [0,2]     D=eeeeeER   movq	(%rdx), %rsi
-# CHECK-NEXT: [0,3]     D==eE---R   movq	%rdi, (%rbx)
+# CHECK-NEXT: [0,3]     DP=eE---R   movq	%rdi, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -612,12 +616,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -     3.00    -      -      -      -      -     1.00   movd	%mm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   movd	%mm0, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movd	(%rcx), %mm1
 # CHECK-NEXT: [0,2]     D=eeeeeER   movd	(%rdx), %mm2
-# CHECK-NEXT: [0,3]     D===eeE-R   movd	%mm3, (%rbx)
+# CHECK-NEXT: [0,3]     DP==eeE-R   movd	%mm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -729,12 +734,13 @@ movaps %xmm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -     3.00    -      -      -      -      -     1.00   movaps	%xmm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   movaps	%xmm0, (%rax)
 # CHECK-NEXT: [0,1]     DeeeeeER.   movaps	(%rcx), %xmm1
 # CHECK-NEXT: [0,2]     D=eeeeeER   movaps	(%rdx), %xmm2
-# CHECK-NEXT: [0,3]     D===eE--R   movaps	%xmm3, (%rbx)
+# CHECK-NEXT: [0,3]     DP==eE--R   movaps	%xmm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/load-throughput.s b/llvm/test/tools/llvm-mca/X86/BdVer2/load-throughput.s
index 60566b7119f57..0e6e14e7035c9 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/load-throughput.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/load-throughput.s
@@ -145,6 +145,7 @@ vmovaps (%rbx), %ymm3
 # CHECK-NEXT: 2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     movb	(%rbx), %dil
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   movb	(%rax), %spl
@@ -260,6 +261,7 @@ vmovaps (%rbx), %ymm3
 # CHECK-NEXT: 2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     movw	(%rbx), %di
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   movw	(%rax), %sp
@@ -375,6 +377,7 @@ vmovaps (%rbx), %ymm3
 # CHECK-NEXT: 2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     movl	(%rbx), %edi
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   movl	(%rax), %esp
@@ -490,6 +493,7 @@ vmovaps (%rbx), %ymm3
 # CHECK-NEXT: 2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     movq	(%rbx), %rdi
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   movq	(%rax), %rsp
@@ -605,6 +609,7 @@ vmovaps (%rbx), %ymm3
 # CHECK-NEXT: 3.00    -      -      -      -      -      -      -      -      -     3.00    -      -      -     1.00    -      -      -      -     3.00    -      -      -     movd	(%rbx), %mm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -721,6 +726,7 @@ vmovaps (%rbx), %ymm3
 # CHECK-NEXT: 3.00    -      -      -      -      -      -      -     3.00    -      -      -      -      -     1.00    -      -      -      -     3.00    -      -      -     movaps	(%rbx), %xmm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
@@ -836,6 +842,7 @@ vmovaps (%rbx), %ymm3
 # CHECK-NEXT: 3.00    -      -      -      -      -      -      -     3.00    -      -      -      -      -     1.00    -      -      -      -     3.00    -      -      -     vmovaps	(%rbx), %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/memcpy-like-test.s b/llvm/test/tools/llvm-mca/X86/BdVer2/memcpy-like-test.s
index e1753784c7e64..50fca9e5fee67 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/memcpy-like-test.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/memcpy-like-test.s
@@ -79,17 +79,18 @@ vmovaps %xmm0, 48(%rdi)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -     3.00    -      -      -      -      -     1.00   vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .  .   vmovaps	(%rsi), %xmm0
-# CHECK-NEXT: [0,1]     D======eER.  .   vmovaps	%xmm0, (%rdi)
+# CHECK-NEXT: [0,1]     DPPPPP=eER.  .   vmovaps	%xmm0, (%rdi)
 # CHECK-NEXT: [0,2]     DeeeeeE--R.  .   vmovaps	16(%rsi), %xmm0
-# CHECK-NEXT: [0,3]     D=======eER  .   vmovaps	%xmm0, 16(%rdi)
+# CHECK-NEXT: [0,3]     DPPPPPP=eER  .   vmovaps	%xmm0, 16(%rdi)
 # CHECK-NEXT: [0,4]     .D==eeeeeER  .   vmovaps	32(%rsi), %xmm0
-# CHECK-NEXT: [0,5]     .D========eER.   vmovaps	%xmm0, 32(%rdi)
+# CHECK-NEXT: [0,5]     .DPPPPPPP=eER.   vmovaps	%xmm0, 32(%rdi)
 # CHECK-NEXT: [0,6]     .D==eeeeeE--R.   vmovaps	48(%rsi), %xmm0
-# CHECK-NEXT: [0,7]     .D=========eER   vmovaps	%xmm0, 48(%rdi)
+# CHECK-NEXT: [0,7]     .DPPPPPPPP=eER   vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/one-idioms.s b/llvm/test/tools/llvm-mca/X86/BdVer2/one-idioms.s
index 8589949a98583..d5e6c6fe48a5d 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/one-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/one-idioms.s
@@ -124,6 +124,7 @@ vpcmpeqw  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -     vpcmpeqw	%xmm3, %xmm3, %xmm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
@@ -132,15 +133,15 @@ vpcmpeqw  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,2]     D=eeER    ..   pcmpeqw	%mm2, %mm2
 # CHECK-NEXT: [0,3]     D==eeER   ..   pcmpeqb	%xmm2, %xmm2
 # CHECK-NEXT: [0,4]     .DeeE-R   ..   pcmpeqd	%xmm2, %xmm2
-# CHECK-NEXT: [0,5]     .D==eeER  ..   pcmpeqq	%xmm2, %xmm2
+# CHECK-NEXT: [0,5]     .DPPeeER  ..   pcmpeqq	%xmm2, %xmm2
 # CHECK-NEXT: [0,6]     .D=eeE-R  ..   pcmpeqw	%xmm2, %xmm2
 # CHECK-NEXT: [0,7]     .D===eeER ..   vpcmpeqb	%xmm3, %xmm3, %xmm3
 # CHECK-NEXT: [0,8]     . D=eeE-R ..   vpcmpeqd	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,9]     . D===eeER..   vpcmpeqq	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,9]     . DPPPeeER..   vpcmpeqq	%xmm3, %xmm3, %xmm3
 # CHECK-NEXT: [0,10]    . D==eeE-R..   vpcmpeqw	%xmm3, %xmm3, %xmm3
 # CHECK-NEXT: [0,11]    . D===eeER..   vpcmpeqb	%xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,12]    .  D===eeER.   vpcmpeqd	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,13]    .  D===eeER.   vpcmpeqq	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,13]    .  DPPPeeER.   vpcmpeqq	%xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,14]    .  D====eeER   vpcmpeqw	%xmm3, %xmm3, %xmm5
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-2.s
index fed8508572a12..75bef4502f25b 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-2.s
@@ -29,12 +29,13 @@ add    %ecx, %ebx
 # CHECK-NEXT:  1      1     1.00                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   imulq	%rax, %rbx
-# CHECK-NEXT: [0,1]     D=====eeER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D=======eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPPPeeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-3.s b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-3.s
index 14e191f564119..7d2dbbaf1a747 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-3.s
@@ -69,18 +69,19 @@ xor %bx, %dx
 # CHECK-NEXT:  -      -      -      -      -     1.00   1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     xorw	%bx, %dx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    ..   addw	%cx, %dx
-# CHECK-NEXT: [0,1]     D=eER.    ..   movw	%ax, %dx
-# CHECK-NEXT: [0,2]     D==eER    ..   xorw	%bx, %dx
-# CHECK-NEXT: [1,0]     D===eER   ..   addw	%cx, %dx
-# CHECK-NEXT: [1,1]     .D===eER  ..   movw	%ax, %dx
-# CHECK-NEXT: [1,2]     .D====eER ..   xorw	%bx, %dx
-# CHECK-NEXT: [2,0]     .D=====eER..   addw	%cx, %dx
-# CHECK-NEXT: [2,1]     .D======eER.   movw	%ax, %dx
-# CHECK-NEXT: [2,2]     . D======eER   xorw	%bx, %dx
+# CHECK-NEXT: [0,1]     DPeER.    ..   movw	%ax, %dx
+# CHECK-NEXT: [0,2]     DPPeER    ..   xorw	%bx, %dx
+# CHECK-NEXT: [1,0]     DPPPeER   ..   addw	%cx, %dx
+# CHECK-NEXT: [1,1]     .DPPPeER  ..   movw	%ax, %dx
+# CHECK-NEXT: [1,2]     .DPPPPeER ..   xorw	%bx, %dx
+# CHECK-NEXT: [2,0]     .DPPPPPeER..   addw	%cx, %dx
+# CHECK-NEXT: [2,1]     .DPPPPPPeER.   movw	%ax, %dx
+# CHECK-NEXT: [2,2]     . DPPPPPPeER   xorw	%bx, %dx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-4.s b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-4.s
index 5fa4e5ea96393..7ea8986ddcae4 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-4.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-4.s
@@ -69,18 +69,19 @@ add %cx, %bx
 # CHECK-NEXT:  -      -      -      -      -     1.00   1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addw	%cx, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01
 
 # CHECK:      [0,0]     DeeeeER   .    .    ..   imulw	%ax, %bx
-# CHECK-NEXT: [0,1]     D===eeER  .    .    ..   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D=====eER .    .    ..   addw	%cx, %bx
-# CHECK-NEXT: [1,0]     .D======eeeeER .    ..   imulw	%ax, %bx
-# CHECK-NEXT: [1,1]     .D=========eeER.    ..   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,2]     .D===========eER    ..   addw	%cx, %bx
-# CHECK-NEXT: [2,0]     . D===========eeeeER..   imulw	%ax, %bx
-# CHECK-NEXT: [2,1]     . D==============eeER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,2]     . D================eER   addw	%cx, %bx
+# CHECK-NEXT: [0,1]     DPPPeeER  .    .    ..   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPPeER .    .    ..   addw	%cx, %bx
+# CHECK-NEXT: [1,0]     .DPPPPP=eeeeER .    ..   imulw	%ax, %bx
+# CHECK-NEXT: [1,1]     .DPPPPPPPPPeeER.    ..   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,2]     .DPPPPPPPPPPPeER    ..   addw	%cx, %bx
+# CHECK-NEXT: [2,0]     . DPPPPPPPPPPPeeeeER..   imulw	%ax, %bx
+# CHECK-NEXT: [2,1]     . DPPPPPPPPPPPPPPeeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,2]     . DPPPPPPPPPPPPPPPPeER   addw	%cx, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-5.s b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-5.s
index e4dddfca3a0f1..fcb285132b663 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-5.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-5.s
@@ -60,11 +60,12 @@ lzcnt %ax, %bx  ## partial register stall.
 # CHECK-NEXT:  -      -      -      -      -     2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     lzcntw	%ax, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,0]     D==eeER .   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,0]     .D===eeER   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,0]     DP=eeER .   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,0]     .DPP=eeER   lzcntw	%ax, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-6.s b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-6.s
index 03ad95df54925..df8eea6a5b2ac 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-6.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update-6.s
@@ -70,18 +70,19 @@ lzcnt 2(%rsp), %cx
 # CHECK-NEXT: 3.00    -      -      -      -     2.00    -      -      -      -      -      -      -      -      -      -      -      -      -     3.00    -      -      -     lzcntw	2(%rsp), %cx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    ..   imull	%edx, %ecx
 # CHECK-NEXT: [0,1]     DeeeeeeER .    .    .    ..   lzcntw	(%rsp), %cx
 # CHECK-NEXT: [0,2]     .D=eeeeeeER    .    .    ..   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [1,0]     .D=======eeeeER.    .    ..   imull	%edx, %ecx
-# CHECK-NEXT: [1,1]     . D======eeeeeeER   .    ..   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [1,2]     . D========eeeeeeER .    ..   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [2,0]     .  D=============eeeeER  ..   imull	%edx, %ecx
-# CHECK-NEXT: [2,1]     .  D=============eeeeeeER..   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [2,2]     .   D==============eeeeeeER   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [1,0]     .DPPPPPPPeeeeER.    .    ..   imull	%edx, %ecx
+# CHECK-NEXT: [1,1]     . DPPPPPPeeeeeeER   .    ..   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [1,2]     . DPPPPPPP=eeeeeeER .    ..   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [2,0]     .  DPPPPPPPPPPPPPeeeeER  ..   imull	%edx, %ecx
+# CHECK-NEXT: [2,1]     .  DPPPPPPPPPPPPPeeeeeeER..   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [2,2]     .   DPPPPPPPPPPPPP=eeeeeeER   lzcntw	2(%rsp), %cx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update.s b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update.s
index 3c0c38d7cc05f..c221bfd914e23 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/partial-reg-update.s
@@ -29,11 +29,12 @@ add  %ecx, %ebx
 # CHECK-NEXT:  1      1     1.00                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   imulw	%ax, %cx
-# CHECK-NEXT: [0,1]     D====eER.   addb	%al, %cl
-# CHECK-NEXT: [0,2]     D=====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPPeER.   addb	%al, %cl
+# CHECK-NEXT: [0,2]     DPPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/pipes-fpu.s b/llvm/test/tools/llvm-mca/X86/BdVer2/pipes-fpu.s
index 857df60f2a6ed..afca986e9a7db 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/pipes-fpu.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/pipes-fpu.s
@@ -86,6 +86,7 @@ vsqrtps     %ymm0, %ymm2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -      -     2.00    -      -      -      -      -      -      -     vsqrtps	%ymm0, %ymm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/pr37790.s b/llvm/test/tools/llvm-mca/X86/BdVer2/pr37790.s
index 5caf3b67f5b35..722c645244f64 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/pr37790.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/pr37790.s
@@ -27,6 +27,7 @@ stmxcsr (%rsp)
 # CHECK-NEXT:  2      1     18.00          *      U     stmxcsr	(%rsp)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789          012
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/rank.s b/llvm/test/tools/llvm-mca/X86/BdVer2/rank.s
index c929b8bae3b14..713979730fdb5 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/rank.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/rank.s
@@ -79,33 +79,34 @@ add %ebx, %eax
 # CHECK-NEXT:  -      -      -      -      -     2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addl	%ebx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeER .    .    .    .    ..   addl	%eax, %ecx
 # CHECK-NEXT: [0,1]     DeER .    .    .    .    ..   addl	%eax, %edx
 # CHECK-NEXT: [0,2]     D==eER    .    .    .    ..   addl	%eax, %ebx
-# CHECK-NEXT: [0,3]     D==eER    .    .    .    ..   addl	%edx, %esi
-# CHECK-NEXT: [0,4]     .D===eER  .    .    .    ..   addl	%ebx, %eax
-# CHECK-NEXT: [0,5]     .D===eER  .    .    .    ..   addl	%edx, %esi
-# CHECK-NEXT: [0,6]     .D=====eER.    .    .    ..   addl	%ebx, %eax
-# CHECK-NEXT: [0,7]     .D======eER    .    .    ..   addl	%ebx, %eax
-# CHECK-NEXT: [1,0]     . D========eER .    .    ..   addl	%eax, %ecx
-# CHECK-NEXT: [1,1]     . D======eE--R .    .    ..   addl	%eax, %edx
-# CHECK-NEXT: [1,2]     . D=======eE-R .    .    ..   addl	%eax, %ebx
-# CHECK-NEXT: [1,3]     . D=========eER.    .    ..   addl	%edx, %esi
-# CHECK-NEXT: [1,4]     .  D=========eER    .    ..   addl	%ebx, %eax
-# CHECK-NEXT: [1,5]     .  D==========eER   .    ..   addl	%edx, %esi
-# CHECK-NEXT: [1,6]     .  D===========eER  .    ..   addl	%ebx, %eax
-# CHECK-NEXT: [1,7]     .  D============eER .    ..   addl	%ebx, %eax
-# CHECK-NEXT: [2,0]     .   D==============eER   ..   addl	%eax, %ecx
-# CHECK-NEXT: [2,1]     .   D============eE--R   ..   addl	%eax, %edx
-# CHECK-NEXT: [2,2]     .   D=============eE-R   ..   addl	%eax, %ebx
-# CHECK-NEXT: [2,3]     .   D===============eER  ..   addl	%edx, %esi
-# CHECK-NEXT: [2,4]     .    D===============eER ..   addl	%ebx, %eax
-# CHECK-NEXT: [2,5]     .    D================eER..   addl	%edx, %esi
-# CHECK-NEXT: [2,6]     .    D=================eER.   addl	%ebx, %eax
-# CHECK-NEXT: [2,7]     .    D==================eER   addl	%ebx, %eax
+# CHECK-NEXT: [0,3]     DP=eER    .    .    .    ..   addl	%edx, %esi
+# CHECK-NEXT: [0,4]     .DPP=eER  .    .    .    ..   addl	%ebx, %eax
+# CHECK-NEXT: [0,5]     .DPP=eER  .    .    .    ..   addl	%edx, %esi
+# CHECK-NEXT: [0,6]     .DPPPP=eER.    .    .    ..   addl	%ebx, %eax
+# CHECK-NEXT: [0,7]     .DPPPPPPeER    .    .    ..   addl	%ebx, %eax
+# CHECK-NEXT: [1,0]     . DPPPPPP==eER .    .    ..   addl	%eax, %ecx
+# CHECK-NEXT: [1,1]     . DPPPPPPeE--R .    .    ..   addl	%eax, %edx
+# CHECK-NEXT: [1,2]     . DPPPPPP=eE-R .    .    ..   addl	%eax, %ebx
+# CHECK-NEXT: [1,3]     . DPPPPPPP==eER.    .    ..   addl	%edx, %esi
+# CHECK-NEXT: [1,4]     .  DPPPPPPP==eER    .    ..   addl	%ebx, %eax
+# CHECK-NEXT: [1,5]     .  DPPPPPPPPP=eER   .    ..   addl	%edx, %esi
+# CHECK-NEXT: [1,6]     .  DPPPPPPPPPP=eER  .    ..   addl	%ebx, %eax
+# CHECK-NEXT: [1,7]     .  DPPPPPPPPPPPPeER .    ..   addl	%ebx, %eax
+# CHECK-NEXT: [2,0]     .   DPPPPPPPPPPPP==eER   ..   addl	%eax, %ecx
+# CHECK-NEXT: [2,1]     .   DPPPPPPPPPPPPeE--R   ..   addl	%eax, %edx
+# CHECK-NEXT: [2,2]     .   DPPPPPPPPPPPP=eE-R   ..   addl	%eax, %ebx
+# CHECK-NEXT: [2,3]     .   DPPPPPPPPPPPPP==eER  ..   addl	%edx, %esi
+# CHECK-NEXT: [2,4]     .    DPPPPPPPPPPPPP==eER ..   addl	%ebx, %eax
+# CHECK-NEXT: [2,5]     .    DPPPPPPPPPPPPPPP=eER..   addl	%edx, %esi
+# CHECK-NEXT: [2,6]     .    DPPPPPPPPPPPPPPPP=eER.   addl	%ebx, %eax
+# CHECK-NEXT: [2,7]     .    DPPPPPPPPPPPPPPPPPPeER   addl	%ebx, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-1.s b/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-1.s
index e62f816acb074..8e1c0c835080b 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-1.s
@@ -31,6 +31,7 @@ vmulps  (%rdi), %xmm1, %xmm2
 # CHECK-NEXT:  1      10    1.50    *                   vmulps	(%rdi), %xmm1, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-2.s
index be28b7af9dafd..79253f13c4b22 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-2.s
@@ -30,6 +30,7 @@
 # CHECK-NEXT:  1      8     4.00    *                   imull	(%rdi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-3.s b/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-3.s
index e5e02b264e508..f8d4cf0a7dc71 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/read-advance-3.s
@@ -29,6 +29,7 @@
 # CHECK-NEXT:  1      1     1.00                        addq	%rdx, %r8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   addq	%rdi, %rsi
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-1.s b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-1.s
index 7bfb210abf9ce..3773aec1bf387 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-1.s
@@ -81,18 +81,19 @@ vaddps %xmm1, %xmm1, %xmm2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.67   0.33    -      -      -      -     1.00    -      -      -      -      -      -      -      -     vaddps	%xmm1, %xmm1, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DR   .    . .   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [0,1]     DeER .    . .   vmovaps	%xmm0, %xmm1
-# CHECK-NEXT: [0,2]     D=eeeeeER . .   vaddps	%xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [0,2]     DPeeeeeER . .   vaddps	%xmm1, %xmm1, %xmm2
 # CHECK-NEXT: [1,0]     D-------R . .   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [1,1]     .D=eE---R . .   vmovaps	%xmm0, %xmm1
-# CHECK-NEXT: [1,2]     .D===eeeeeER.   vaddps	%xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [1,2]     .DPP=eeeeeER.   vaddps	%xmm1, %xmm1, %xmm2
 # CHECK-NEXT: [2,0]     .D---------R.   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [2,1]     .D=eE------R.   vmovaps	%xmm0, %xmm1
-# CHECK-NEXT: [2,2]     . D===eeeeeER   vaddps	%xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [2,2]     . DP==eeeeeER   vaddps	%xmm1, %xmm1, %xmm2
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-2.s
index a6e2fa94ace24..ca0fa4a58e8b7 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-2.s
@@ -97,6 +97,7 @@ movdqu %xmm5, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.67   1.33    -      -     0.33   0.67    -      -      -      -      -      -      -     movdqu	%xmm5, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
@@ -105,28 +106,28 @@ movdqu %xmm5, %xmm0
 # CHECK-NEXT: [0,2]     D---R.    .    ..   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,3]     DeE-R.    .    ..   movaps	%xmm0, %xmm1
 # CHECK-NEXT: [0,4]     .DeER.    .    ..   movups	%xmm1, %xmm2
-# CHECK-NEXT: [0,5]     .D=eER    .    ..   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [0,6]     .D==eER   .    ..   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [0,7]     .D===eER  .    ..   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [0,8]     . D===eER .    ..   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [0,5]     .DPeER    .    ..   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [0,6]     .DPPeER   .    ..   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [0,7]     .DPPPeER  .    ..   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [0,8]     . DPPPeER .    ..   movdqu	%xmm5, %xmm0
 # CHECK-NEXT: [1,0]     . D-----R .    ..   pxor	%mm0, %mm0
 # CHECK-NEXT: [1,1]     . DeeE--R .    ..   movq	%mm0, %mm1
 # CHECK-NEXT: [1,2]     . D-----R .    ..   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [1,3]     .  D=eE--R.    ..   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [1,4]     .  D==eE-R.    ..   movups	%xmm1, %xmm2
-# CHECK-NEXT: [1,5]     .  D===eER.    ..   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [1,6]     .  D====eER    ..   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [1,7]     .   D====eER   ..   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [1,8]     .   D=====eER  ..   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [1,4]     .  DPPeE-R.    ..   movups	%xmm1, %xmm2
+# CHECK-NEXT: [1,5]     .  DPPPeER.    ..   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [1,6]     .  DPPPPeER    ..   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [1,7]     .   DPPPPeER   ..   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [1,8]     .   DPPPPPeER  ..   movdqu	%xmm5, %xmm0
 # CHECK-NEXT: [2,0]     .   D-------R  ..   pxor	%mm0, %mm0
 # CHECK-NEXT: [2,1]     .   D==eeE--R  ..   movq	%mm0, %mm1
 # CHECK-NEXT: [2,2]     .    D------R  ..   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [2,3]     .    D===eE--R ..   movaps	%xmm0, %xmm1
-# CHECK-NEXT: [2,4]     .    D====eE-R ..   movups	%xmm1, %xmm2
-# CHECK-NEXT: [2,5]     .    D=====eER ..   movapd	%xmm2, %xmm3
-# CHECK-NEXT: [2,6]     .    .D=====eER..   movupd	%xmm3, %xmm4
-# CHECK-NEXT: [2,7]     .    .D======eER.   movdqa	%xmm4, %xmm5
-# CHECK-NEXT: [2,8]     .    .D=======eER   movdqu	%xmm5, %xmm0
+# CHECK-NEXT: [2,4]     .    DPPPPeE-R ..   movups	%xmm1, %xmm2
+# CHECK-NEXT: [2,5]     .    DPPPPPeER ..   movapd	%xmm2, %xmm3
+# CHECK-NEXT: [2,6]     .    .DPPPPPeER..   movupd	%xmm3, %xmm4
+# CHECK-NEXT: [2,7]     .    .DPPPPPPeER.   movdqa	%xmm4, %xmm5
+# CHECK-NEXT: [2,8]     .    .DPPPPPPPeER   movdqu	%xmm5, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-3.s b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-3.s
index 0a8fda9fe2eb7..24f51b0a8e25a 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-3.s
@@ -90,30 +90,31 @@ vmovdqu %xmm5, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.33   0.67    -      -      -      -      -      -      -     vmovdqu	%xmm5, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DR   .    .    ..   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [0,1]     DeER .    .    ..   vmovaps	%xmm0, %xmm1
-# CHECK-NEXT: [0,2]     D=eER.    .    ..   vmovups	%xmm1, %xmm2
-# CHECK-NEXT: [0,3]     D==eER    .    ..   vmovapd	%xmm2, %xmm3
-# CHECK-NEXT: [0,4]     .D==eER   .    ..   vmovupd	%xmm3, %xmm4
-# CHECK-NEXT: [0,5]     .D===eER  .    ..   vmovdqa	%xmm4, %xmm5
-# CHECK-NEXT: [0,6]     .D====eER .    ..   vmovdqu	%xmm5, %xmm0
+# CHECK-NEXT: [0,2]     DPeER.    .    ..   vmovups	%xmm1, %xmm2
+# CHECK-NEXT: [0,3]     DPPeER    .    ..   vmovapd	%xmm2, %xmm3
+# CHECK-NEXT: [0,4]     .DPPeER   .    ..   vmovupd	%xmm3, %xmm4
+# CHECK-NEXT: [0,5]     .DPPPeER  .    ..   vmovdqa	%xmm4, %xmm5
+# CHECK-NEXT: [0,6]     .DPPPPeER .    ..   vmovdqu	%xmm5, %xmm0
 # CHECK-NEXT: [1,0]     .D------R .    ..   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [1,1]     . D==eE-R .    ..   vmovaps	%xmm0, %xmm1
-# CHECK-NEXT: [1,2]     . D===eER .    ..   vmovups	%xmm1, %xmm2
-# CHECK-NEXT: [1,3]     . D====eER.    ..   vmovapd	%xmm2, %xmm3
-# CHECK-NEXT: [1,4]     . D=====eER    ..   vmovupd	%xmm3, %xmm4
-# CHECK-NEXT: [1,5]     .  D=====eER   ..   vmovdqa	%xmm4, %xmm5
-# CHECK-NEXT: [1,6]     .  D======eER  ..   vmovdqu	%xmm5, %xmm0
+# CHECK-NEXT: [1,2]     . DPPPeER .    ..   vmovups	%xmm1, %xmm2
+# CHECK-NEXT: [1,3]     . DPPPPeER.    ..   vmovapd	%xmm2, %xmm3
+# CHECK-NEXT: [1,4]     . DPPPPPeER    ..   vmovupd	%xmm3, %xmm4
+# CHECK-NEXT: [1,5]     .  DPPPPPeER   ..   vmovdqa	%xmm4, %xmm5
+# CHECK-NEXT: [1,6]     .  DPPPPPPeER  ..   vmovdqu	%xmm5, %xmm0
 # CHECK-NEXT: [2,0]     .  D--------R  ..   vxorps	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [2,1]     .  D=====eE-R  ..   vmovaps	%xmm0, %xmm1
-# CHECK-NEXT: [2,2]     .   D=====eER  ..   vmovups	%xmm1, %xmm2
-# CHECK-NEXT: [2,3]     .   D======eER ..   vmovapd	%xmm2, %xmm3
-# CHECK-NEXT: [2,4]     .   D=======eER..   vmovupd	%xmm3, %xmm4
-# CHECK-NEXT: [2,5]     .   D========eER.   vmovdqa	%xmm4, %xmm5
-# CHECK-NEXT: [2,6]     .    D========eER   vmovdqu	%xmm5, %xmm0
+# CHECK-NEXT: [2,2]     .   DPPPPPeER  ..   vmovups	%xmm1, %xmm2
+# CHECK-NEXT: [2,3]     .   DPPPPPPeER ..   vmovapd	%xmm2, %xmm3
+# CHECK-NEXT: [2,4]     .   DPPPPPPPeER..   vmovupd	%xmm3, %xmm4
+# CHECK-NEXT: [2,5]     .   DPPPPPPPPeER.   vmovdqa	%xmm4, %xmm5
+# CHECK-NEXT: [2,6]     .    DPPPPPPPPeER   vmovdqu	%xmm5, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-4.s b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-4.s
index 94163b1162b4d..ba8d1bb20b877 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-4.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-4.s
@@ -84,24 +84,25 @@ mov %edx, %eax
 # CHECK-NEXT:  -      -      -      -      -     2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movl	%edx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DR   .    .   .   xorl	%eax, %eax
 # CHECK-NEXT: [0,1]     DeER .    .   .   movl	%eax, %ebx
-# CHECK-NEXT: [0,2]     D=eER.    .   .   movl	%ebx, %ecx
-# CHECK-NEXT: [0,3]     D==eER    .   .   movl	%ecx, %edx
-# CHECK-NEXT: [0,4]     .D==eER   .   .   movl	%edx, %eax
+# CHECK-NEXT: [0,2]     DPeER.    .   .   movl	%ebx, %ecx
+# CHECK-NEXT: [0,3]     DPPeER    .   .   movl	%ecx, %edx
+# CHECK-NEXT: [0,4]     .DPPeER   .   .   movl	%edx, %eax
 # CHECK-NEXT: [1,0]     .D----R   .   .   xorl	%eax, %eax
 # CHECK-NEXT: [1,1]     .D===eER  .   .   movl	%eax, %ebx
-# CHECK-NEXT: [1,2]     .D====eER .   .   movl	%ebx, %ecx
-# CHECK-NEXT: [1,3]     . D====eER.   .   movl	%ecx, %edx
-# CHECK-NEXT: [1,4]     . D=====eER   .   movl	%edx, %eax
+# CHECK-NEXT: [1,2]     .DPPPPeER .   .   movl	%ebx, %ecx
+# CHECK-NEXT: [1,3]     . DPPPPeER.   .   movl	%ecx, %edx
+# CHECK-NEXT: [1,4]     . DPPPPPeER   .   movl	%edx, %eax
 # CHECK-NEXT: [2,0]     . D-------R   .   xorl	%eax, %eax
 # CHECK-NEXT: [2,1]     . D======eER  .   movl	%eax, %ebx
-# CHECK-NEXT: [2,2]     .  D======eER .   movl	%ebx, %ecx
-# CHECK-NEXT: [2,3]     .  D=======eER.   movl	%ecx, %edx
-# CHECK-NEXT: [2,4]     .  D========eER   movl	%edx, %eax
+# CHECK-NEXT: [2,2]     .  DPPPPPPeER .   movl	%ebx, %ecx
+# CHECK-NEXT: [2,3]     .  DPPPPPPPeER.   movl	%ecx, %edx
+# CHECK-NEXT: [2,4]     .  DPPPPPPPPeER   movl	%edx, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-5.s b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-5.s
index 8ccbbeab3cc2d..71ec742302a3d 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-5.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/reg-move-elimination-5.s
@@ -84,24 +84,25 @@ mov %rdx, %rax
 # CHECK-NEXT:  -      -      -      -      -     2.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movq	%rdx, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DR   .    .   .   xorq	%rax, %rax
 # CHECK-NEXT: [0,1]     DeER .    .   .   movq	%rax, %rbx
-# CHECK-NEXT: [0,2]     D=eER.    .   .   movq	%rbx, %rcx
-# CHECK-NEXT: [0,3]     D==eER    .   .   movq	%rcx, %rdx
-# CHECK-NEXT: [0,4]     .D==eER   .   .   movq	%rdx, %rax
+# CHECK-NEXT: [0,2]     DPeER.    .   .   movq	%rbx, %rcx
+# CHECK-NEXT: [0,3]     DPPeER    .   .   movq	%rcx, %rdx
+# CHECK-NEXT: [0,4]     .DPPeER   .   .   movq	%rdx, %rax
 # CHECK-NEXT: [1,0]     .D----R   .   .   xorq	%rax, %rax
 # CHECK-NEXT: [1,1]     .D===eER  .   .   movq	%rax, %rbx
-# CHECK-NEXT: [1,2]     .D====eER .   .   movq	%rbx, %rcx
-# CHECK-NEXT: [1,3]     . D====eER.   .   movq	%rcx, %rdx
-# CHECK-NEXT: [1,4]     . D=====eER   .   movq	%rdx, %rax
+# CHECK-NEXT: [1,2]     .DPPPPeER .   .   movq	%rbx, %rcx
+# CHECK-NEXT: [1,3]     . DPPPPeER.   .   movq	%rcx, %rdx
+# CHECK-NEXT: [1,4]     . DPPPPPeER   .   movq	%rdx, %rax
 # CHECK-NEXT: [2,0]     . D-------R   .   xorq	%rax, %rax
 # CHECK-NEXT: [2,1]     . D======eER  .   movq	%rax, %rbx
-# CHECK-NEXT: [2,2]     .  D======eER .   movq	%rbx, %rcx
-# CHECK-NEXT: [2,3]     .  D=======eER.   movq	%rcx, %rdx
-# CHECK-NEXT: [2,4]     .  D========eER   movq	%rdx, %rax
+# CHECK-NEXT: [2,2]     .  DPPPPPPeER .   movq	%rbx, %rcx
+# CHECK-NEXT: [2,3]     .  DPPPPPPPeER.   movq	%rcx, %rdx
+# CHECK-NEXT: [2,4]     .  DPPPPPPPPeER   movq	%rdx, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-1.s b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-1.s
index eb9f3e6194e4c..ceea8a8f2db88 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-1.s
@@ -78,19 +78,20 @@ vmulps %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     vmulps	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=====eeeeeER  .    .    .    .    .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,0]     D==========eeeeeER  .    .    .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D===============eeeeeER  .    .    .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [2,0]     .D===================eeeeeER  .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [2,1]     .D========================eeeeeER  .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [3,0]     .D=============================eeeeeER  .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [3,1]     .D==================================eeeeeER  .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [4,0]     . D======================================eeeeeER  . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [4,1]     . D===========================================eeeeeER   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER  .    .    .    .    .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPeeeeeER  .    .    .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPeeeeeER  .    .    .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [2,0]     .DPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [2,1]     .DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [3,0]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [3,1]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [4,0]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER  . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [4,1]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER   vmulps	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-2.s
index f7a6bfaebe5eb..91feaf140a9cd 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-2.s
@@ -78,19 +78,20 @@ vmulps %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     vmulps	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=====eeeeeER  .    .    .    .    .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,0]     D==========eeeeeER  .    .    .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D===============eeeeeER  .    .    .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [2,0]     .D===================eeeeeER  .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [2,1]     .    . D==================eeeeeER  .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [3,0]     .    .    . D==================eeeeeER  .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [3,1]     .    .    .    . D==================eeeeeER  .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [4,0]     .    .    .    .    . D==================eeeeeER  . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [4,1]     .    .    .    .    .    . D==================eeeeeER   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPPPPPeeeeeER  .    .    .    .    .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPeeeeeER  .    .    .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPPPPPPPPPPPPPPPeeeeeER  .    .    .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [2,0]     .DPPPPPPPPPPPPPPPPPPPeeeeeER  .    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [2,1]     .    . DPPPPPPPPPPPPPPPPPPeeeeeER  .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [3,0]     .    .    . DPPPPPPPPPPPPPPPPPPeeeeeER  .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [3,1]     .    .    .    . DPPPPPPPPPPPPPPPPPPeeeeeER  .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [4,0]     .    .    .    .    . DPPPPPPPPPPPPPPPPPPeeeeeER  . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [4,1]     .    .    .    .    .    . DPPPPPPPPPPPPPPPPPPeeeeeER   vmulps	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-3.s b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-3.s
index df6613cec2831..dd8c9b07d7ebe 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-3.s
@@ -86,6 +86,7 @@ idiv %eax
 # CHECK-NEXT:  -      -      -      -     25.00   -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     idivl	%eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-4.s b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-4.s
index 10d3859062c0b..f6dac1d77a8b4 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-4.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-4.s
@@ -53,12 +53,13 @@ idiv %eax
 # CHECK-NEXT:    Max number of mappings used:      66
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeER   .    .    .    .    .    .    .    .    .    ..   idivl	%eax
-# CHECK-NEXT: [1,0]     D=========================eeeeeeeeeeeeeeER   .    .    .    .    ..   idivl	%eax
-# CHECK-NEXT: [2,0]     .D=================================================eeeeeeeeeeeeeeER   idivl	%eax
+# CHECK-NEXT: [1,0]     DPPPPPPPPPPPPPP===========eeeeeeeeeeeeeeER   .    .    .    .    ..   idivl	%eax
+# CHECK-NEXT: [2,0]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPP===========eeeeeeeeeeeeeeER   idivl	%eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-5.s b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-5.s
index 465e904abd3ed..7bb31107d8412 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-5.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/register-files-5.s
@@ -75,6 +75,7 @@
 # CHECK-NEXT:    Max number of mappings used:      0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234567
 
@@ -94,23 +95,23 @@
 # CHECK-NEXT: [0,13]    .    .D=================eeeeeER    .    .    . .   vaddps	%ymm0, %ymm0, %ymm14
 # CHECK-NEXT: [0,14]    .    . D=================eeeeeER   .    .    . .   vaddps	%ymm0, %ymm0, %ymm15
 # CHECK-NEXT: [0,15]    .    . D=====eeeeeE------------R   .    .    . .   vaddps	%ymm2, %ymm0, %ymm0
-# CHECK-NEXT: [0,16]    .    .  D==============eeeeeE--R   .    .    . .   vaddps	%ymm2, %ymm0, %ymm3
-# CHECK-NEXT: [0,17]    .    .  D=================eeeeeER  .    .    . .   vaddps	%ymm2, %ymm0, %ymm4
-# CHECK-NEXT: [0,18]    .    .   D=================eeeeeER .    .    . .   vaddps	%ymm2, %ymm0, %ymm5
-# CHECK-NEXT: [0,19]    .    .   D==================eeeeeER.    .    . .   vaddps	%ymm2, %ymm0, %ymm6
-# CHECK-NEXT: [0,20]    .    .    D==================eeeeeER    .    . .   vaddps	%ymm2, %ymm0, %ymm7
-# CHECK-NEXT: [0,21]    .    .    D===================eeeeeER   .    . .   vaddps	%ymm2, %ymm0, %ymm8
-# CHECK-NEXT: [0,22]    .    .    .D===================eeeeeER  .    . .   vaddps	%ymm2, %ymm0, %ymm9
-# CHECK-NEXT: [0,23]    .    .    .D====================eeeeeER .    . .   vaddps	%ymm2, %ymm0, %ymm10
-# CHECK-NEXT: [0,24]    .    .    . D====================eeeeeER.    . .   vaddps	%ymm2, %ymm0, %ymm11
-# CHECK-NEXT: [0,25]    .    .    . D=====================eeeeeER    . .   vaddps	%ymm2, %ymm0, %ymm12
-# CHECK-NEXT: [0,26]    .    .    .  D=====================eeeeeER   . .   vaddps	%ymm2, %ymm0, %ymm13
-# CHECK-NEXT: [0,27]    .    .    .  D======================eeeeeER  . .   vaddps	%ymm2, %ymm0, %ymm14
-# CHECK-NEXT: [0,28]    .    .    .   D======================eeeeeER . .   vaddps	%ymm2, %ymm0, %ymm15
-# CHECK-NEXT: [0,29]    .    .    .   D=======================eeeeeER. .   vaddps	%ymm3, %ymm0, %ymm2
-# CHECK-NEXT: [0,30]    .    .    .    D=======================eeeeeER .   vaddps	%ymm3, %ymm0, %ymm4
-# CHECK-NEXT: [0,31]    .    .    .    D========================eeeeeER.   vaddps	%ymm3, %ymm0, %ymm5
-# CHECK-NEXT: [0,32]    .    .    .    .D========================eeeeeER   vaddps	%ymm3, %ymm0, %ymm6
+# CHECK-NEXT: [0,16]    .    .  DPPPPPPPPP=====eeeeeE--R   .    .    . .   vaddps	%ymm2, %ymm0, %ymm3
+# CHECK-NEXT: [0,17]    .    .  DPPPPPPPPP========eeeeeER  .    .    . .   vaddps	%ymm2, %ymm0, %ymm4
+# CHECK-NEXT: [0,18]    .    .   DPPPPPPPP=========eeeeeER .    .    . .   vaddps	%ymm2, %ymm0, %ymm5
+# CHECK-NEXT: [0,19]    .    .   DPPPPPPPP==========eeeeeER.    .    . .   vaddps	%ymm2, %ymm0, %ymm6
+# CHECK-NEXT: [0,20]    .    .    DPPPPPPP===========eeeeeER    .    . .   vaddps	%ymm2, %ymm0, %ymm7
+# CHECK-NEXT: [0,21]    .    .    DPPPPPPP============eeeeeER   .    . .   vaddps	%ymm2, %ymm0, %ymm8
+# CHECK-NEXT: [0,22]    .    .    .DPPPPPP=============eeeeeER  .    . .   vaddps	%ymm2, %ymm0, %ymm9
+# CHECK-NEXT: [0,23]    .    .    .DPPPPPP==============eeeeeER .    . .   vaddps	%ymm2, %ymm0, %ymm10
+# CHECK-NEXT: [0,24]    .    .    . DPPPPP===============eeeeeER.    . .   vaddps	%ymm2, %ymm0, %ymm11
+# CHECK-NEXT: [0,25]    .    .    . DPPPPP================eeeeeER    . .   vaddps	%ymm2, %ymm0, %ymm12
+# CHECK-NEXT: [0,26]    .    .    .  DPPPP=================eeeeeER   . .   vaddps	%ymm2, %ymm0, %ymm13
+# CHECK-NEXT: [0,27]    .    .    .  DPPPP==================eeeeeER  . .   vaddps	%ymm2, %ymm0, %ymm14
+# CHECK-NEXT: [0,28]    .    .    .   DPPP===================eeeeeER . .   vaddps	%ymm2, %ymm0, %ymm15
+# CHECK-NEXT: [0,29]    .    .    .   DPPPPPPPPPPPPP==========eeeeeER. .   vaddps	%ymm3, %ymm0, %ymm2
+# CHECK-NEXT: [0,30]    .    .    .    DPPPPPPPPPPPP===========eeeeeER .   vaddps	%ymm3, %ymm0, %ymm4
+# CHECK-NEXT: [0,31]    .    .    .    DPPPPPPPPPPPP============eeeeeER.   vaddps	%ymm3, %ymm0, %ymm5
+# CHECK-NEXT: [0,32]    .    .    .    .DPPPPPPPPPPP=============eeeeeER   vaddps	%ymm3, %ymm0, %ymm6
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/store-throughput.s b/llvm/test/tools/llvm-mca/X86/BdVer2/store-throughput.s
index 0a2368f5f3f58..1f1617d74c8e2 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/store-throughput.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/store-throughput.s
@@ -145,12 +145,13 @@ vmovaps %ymm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   movb	%dil, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movb	%spl, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movb	%bpl, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movb	%sil, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movb	%dil, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movb	%sil, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movb	%dil, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -260,12 +261,13 @@ vmovaps %ymm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   movw	%di, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movw	%sp, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movw	%bp, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movw	%si, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movw	%di, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movw	%si, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movw	%di, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -375,12 +377,13 @@ vmovaps %ymm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   movl	%edi, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movl	%esp, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movl	%ebp, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movl	%esi, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movl	%edi, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movl	%esi, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movl	%edi, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -490,12 +493,13 @@ vmovaps %ymm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   movq	%rdi, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   movq	%rsp, (%rax)
 # CHECK-NEXT: [0,1]     D=eER..   movq	%rbp, (%rcx)
-# CHECK-NEXT: [0,2]     D==eER.   movq	%rsi, (%rdx)
-# CHECK-NEXT: [0,3]     D===eER   movq	%rdi, (%rbx)
+# CHECK-NEXT: [0,2]     DP=eER.   movq	%rsi, (%rdx)
+# CHECK-NEXT: [0,3]     DPP=eER   movq	%rdi, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -606,12 +610,13 @@ vmovaps %ymm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -     3.00    -      -      -      -      -     1.00   movd	%mm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeER.  .   movd	%mm0, (%rax)
 # CHECK-NEXT: [0,1]     D=eeER  .   movd	%mm1, (%rcx)
-# CHECK-NEXT: [0,2]     D===eeER.   movd	%mm2, (%rdx)
-# CHECK-NEXT: [0,3]     D====eeER   movd	%mm3, (%rbx)
+# CHECK-NEXT: [0,2]     DP==eeER.   movd	%mm2, (%rdx)
+# CHECK-NEXT: [0,3]     DPPP=eeER   movd	%mm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -722,12 +727,13 @@ vmovaps %ymm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -     3.00    -      -      -      -      -     1.00   movaps	%xmm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeER . .   movaps	%xmm0, (%rax)
 # CHECK-NEXT: [0,1]     D=eER. .   movaps	%xmm1, (%rcx)
-# CHECK-NEXT: [0,2]     D===eER.   movaps	%xmm2, (%rdx)
-# CHECK-NEXT: [0,3]     D====eER   movaps	%xmm3, (%rbx)
+# CHECK-NEXT: [0,2]     DP==eER.   movaps	%xmm2, (%rdx)
+# CHECK-NEXT: [0,3]     DPPP=eER   movaps	%xmm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -836,13 +842,14 @@ vmovaps %ymm3, (%rbx)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     36.00   -      -      -      -      -     1.00   vmovaps	%ymm3, (%rbx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01
 
 # CHECK:      [0,0]     DeER .    .    .    .    .    .    .    ..   vmovaps	%ymm0, (%rax)
 # CHECK-NEXT: [0,1]     .D=eER    .    .    .    .    .    .    ..   vmovaps	%ymm1, (%rcx)
 # CHECK-NEXT: [0,2]     . D==================================eER..   vmovaps	%ymm2, (%rdx)
-# CHECK-NEXT: [0,3]     .  D===================================eER   vmovaps	%ymm3, (%rbx)
+# CHECK-NEXT: [0,3]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPP==eER   vmovaps	%ymm3, (%rbx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/vbroadcast-operand-latency.s b/llvm/test/tools/llvm-mca/X86/BdVer2/vbroadcast-operand-latency.s
index a24feaebbf9eb..defaa0f265eac 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/vbroadcast-operand-latency.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/vbroadcast-operand-latency.s
@@ -61,6 +61,7 @@ vbroadcastss (%rax), %ymm0
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00    -      -      -     0.50   0.50    -      -     vbroadcastss	(%rax), %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/vec-logic-read-after-ld-1.s b/llvm/test/tools/llvm-mca/X86/BdVer2/vec-logic-read-after-ld-1.s
index 96e19db3b3a3b..eb566ffc7dfaf 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/vec-logic-read-after-ld-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/vec-logic-read-after-ld-1.s
@@ -27,6 +27,7 @@ vandps (%rdi), %xmm1, %xmm2
 # CHECK-NEXT:  1      7     1.50    *                   vandps	(%rdi), %xmm1, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   vaddps	%xmm0, %xmm0, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/vec-logic-read-after-ld-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/vec-logic-read-after-ld-2.s
index ccedadfc0cd5a..9477df17eea6a 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/vec-logic-read-after-ld-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/vec-logic-read-after-ld-2.s
@@ -27,6 +27,7 @@ vandps (%rdi), %ymm1, %ymm2
 # CHECK-NEXT:  2      7     1.50    *                   vandps	(%rdi), %ymm1, %ymm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   vaddps	%ymm0, %ymm0, %ymm1
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/xop-super-registers-1.s b/llvm/test/tools/llvm-mca/X86/BdVer2/xop-super-registers-1.s
index f694a0429e2a1..16d4442a1a4a3 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/xop-super-registers-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/xop-super-registers-1.s
@@ -73,21 +73,22 @@
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00    -      -      -      -      -      -      -      -     vaddps	%ymm4, %ymm5, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .   .   vmulps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: [0,1]     D=eeeeeeeeeeER .    .    .    .    .   .   vfrczpd	%xmm1, %xmm2
-# CHECK-NEXT: [0,2]     .D==========eeeeeER .    .    .    .   .   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [0,3]     .D===============eeeeeER .    .    .   .   vaddps	%ymm4, %ymm5, %ymm6
-# CHECK-NEXT: [0,4]     . D===================eeeeeER .    .   .   vmulps	%ymm6, %ymm3, %ymm4
-# CHECK-NEXT: [0,5]     . D========================eeeeeER .   .   vaddps	%ymm4, %ymm5, %ymm0
-# CHECK-NEXT: [1,0]     .  D============================eeeeeER.   vmulps	%ymm0, %ymm1, %ymm2
+# CHECK-NEXT: [0,2]     .DPPPPPPPPPPeeeeeER .    .    .    .   .   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPPPPPPPeeeeeER .    .    .   .   vaddps	%ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPeeeeeER .    .   .   vmulps	%ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER .   .   vaddps	%ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,0]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeER.   vmulps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: [1,1]     .  DeeeeeeeeeeE-----------------------R.   vfrczpd	%xmm1, %xmm2
-# CHECK-NEXT: [1,2]     .   D==========eeeeeE-----------------R.   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [1,3]     .   D===============eeeeeE------------R.   vaddps	%ymm4, %ymm5, %ymm6
-# CHECK-NEXT: [1,4]     .    D===================eeeeeE--------R   vmulps	%ymm6, %ymm3, %ymm4
-# CHECK-NEXT: [1,5]     .    D========================eeeeeE---R   vaddps	%ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,2]     .   DPPPPPPPPP=eeeeeE-----------------R.   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     .   DPPPPPPPPPPPPPPPeeeeeE------------R.   vaddps	%ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [1,4]     .    DPPPPPPPPPPPPPPPPPPPeeeeeE--------R   vmulps	%ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [1,5]     .    DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeE---R   vaddps	%ymm4, %ymm5, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/xop-super-registers-2.s b/llvm/test/tools/llvm-mca/X86/BdVer2/xop-super-registers-2.s
index 72f072b764647..13b476c7e158b 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/xop-super-registers-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/xop-super-registers-2.s
@@ -73,21 +73,22 @@
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00    -      -      -      -      -      -      -      -     vaddps	%ymm4, %ymm5, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    .    . .   vmulps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: [0,1]     D=eeeE-R  .    .    .    .    . .   vpermil2pd	$15, %xmm3, %xmm5, %xmm1, %xmm2
-# CHECK-NEXT: [0,2]     .D===eeeeeER   .    .    .    . .   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [0,3]     .D========eeeeeER   .    .    . .   vaddps	%ymm4, %ymm5, %ymm6
-# CHECK-NEXT: [0,4]     . D============eeeeeER   .    . .   vmulps	%ymm6, %ymm3, %ymm4
-# CHECK-NEXT: [0,5]     . D=================eeeeeER   . .   vaddps	%ymm4, %ymm5, %ymm0
-# CHECK-NEXT: [1,0]     .  D=====================eeeeeER.   vmulps	%ymm0, %ymm1, %ymm2
+# CHECK-NEXT: [0,2]     .DPPPeeeeeER   .    .    .    . .   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     .DPPPPPPPPeeeeeER   .    .    . .   vaddps	%ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPPPeeeeeER   .    . .   vmulps	%ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPPPeeeeeER   . .   vaddps	%ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,0]     .  DPPPPPPPPPPPPPPPPPPPPPeeeeeER.   vmulps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: [1,1]     .  DeeeE-----------------------R.   vpermil2pd	$15, %xmm3, %xmm5, %xmm1, %xmm2
-# CHECK-NEXT: [1,2]     .   D==eeeeeE------------------R.   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [1,3]     .   D=======eeeeeE-------------R.   vaddps	%ymm4, %ymm5, %ymm6
-# CHECK-NEXT: [1,4]     .    D===========eeeeeE---------R   vmulps	%ymm6, %ymm3, %ymm4
-# CHECK-NEXT: [1,5]     .    D================eeeeeE----R   vaddps	%ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,2]     .   DPPeeeeeE------------------R.   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     .   DPPPPPPPeeeeeE-------------R.   vaddps	%ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [1,4]     .    DPPPPPPPPPPPeeeeeE---------R   vmulps	%ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [1,5]     .    DPPPPPPPPPPPPPPPPeeeeeE----R   vaddps	%ymm4, %ymm5, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/zero-idioms-avx-256.s b/llvm/test/tools/llvm-mca/X86/BdVer2/zero-idioms-avx-256.s
index df03ff86dbbf9..1b4e34834be1e 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/zero-idioms-avx-256.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/zero-idioms-avx-256.s
@@ -97,18 +97,19 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -      -      -     2.00    -      -      -      -      -      -     vblendps	$2, %ymm1, %ymm2, %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .   vaddps	%ymm0, %ymm0, %ymm1
 # CHECK-NEXT: [0,1]     DeeE---R  .   vxorps	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,2]     .D=eeE-R  .   vblendps	$2, %ymm1, %ymm2, %ymm3
+# CHECK-NEXT: [0,2]     .DPeeE-R  .   vblendps	$2, %ymm1, %ymm2, %ymm3
 # CHECK-NEXT: [1,0]     .DeeeeeER .   vaddps	%ymm0, %ymm0, %ymm1
 # CHECK-NEXT: [1,1]     . DeeE--R .   vxorps	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [1,2]     . D==eeER .   vblendps	$2, %ymm1, %ymm2, %ymm3
+# CHECK-NEXT: [1,2]     . DPPeeER .   vblendps	$2, %ymm1, %ymm2, %ymm3
 # CHECK-NEXT: [2,0]     .  DeeeeeER   vaddps	%ymm0, %ymm0, %ymm1
 # CHECK-NEXT: [2,1]     .  D=eeE--R   vxorps	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [2,2]     .   D==eeER   vblendps	$2, %ymm1, %ymm2, %ymm3
+# CHECK-NEXT: [2,2]     .   DPPeeER   vblendps	$2, %ymm1, %ymm2, %ymm3
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -183,18 +184,19 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -      -      -     2.00    -      -      -      -      -      -     vblendpd	$2, %ymm1, %ymm2, %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  .   vaddpd	%ymm0, %ymm0, %ymm1
 # CHECK-NEXT: [0,1]     DeeE---R  .   vxorpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,2]     .D=eeE-R  .   vblendpd	$2, %ymm1, %ymm2, %ymm3
+# CHECK-NEXT: [0,2]     .DPeeE-R  .   vblendpd	$2, %ymm1, %ymm2, %ymm3
 # CHECK-NEXT: [1,0]     .DeeeeeER .   vaddpd	%ymm0, %ymm0, %ymm1
 # CHECK-NEXT: [1,1]     . DeeE--R .   vxorpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [1,2]     . D==eeER .   vblendpd	$2, %ymm1, %ymm2, %ymm3
+# CHECK-NEXT: [1,2]     . DPPeeER .   vblendpd	$2, %ymm1, %ymm2, %ymm3
 # CHECK-NEXT: [2,0]     .  DeeeeeER   vaddpd	%ymm0, %ymm0, %ymm1
 # CHECK-NEXT: [2,1]     .  D=eeE--R   vxorpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [2,2]     .   D==eeER   vblendpd	$2, %ymm1, %ymm2, %ymm3
+# CHECK-NEXT: [2,2]     .   DPPeeER   vblendpd	$2, %ymm1, %ymm2, %ymm3
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -267,6 +269,7 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -      -      -      -     vandnps	%ymm2, %ymm2, %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   vaddps	%ymm0, %ymm1, %ymm2
@@ -346,6 +349,7 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -      -      -      -     vandnps	%ymm2, %ymm2, %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER .   vaddps	%ymm0, %ymm1, %ymm2
@@ -425,15 +429,16 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00    -      -      -      -      -     1.00    -      -      -      -      -      -      -      -     vaddps	%ymm1, %ymm1, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeER   .    .    .    .   .   vperm2f128	$136, %ymm0, %ymm0, %ymm1
-# CHECK-NEXT: [0,1]     . D==eeeeeER   .    .    .   .   vaddps	%ymm1, %ymm1, %ymm0
-# CHECK-NEXT: [1,0]     .  D======eeeeER    .    .   .   vperm2f128	$136, %ymm0, %ymm0, %ymm1
-# CHECK-NEXT: [1,1]     .    D========eeeeeER    .   .   vaddps	%ymm1, %ymm1, %ymm0
-# CHECK-NEXT: [2,0]     .    .D============eeeeER.   .   vperm2f128	$136, %ymm0, %ymm0, %ymm1
-# CHECK-NEXT: [2,1]     .    .  D==============eeeeeER   vaddps	%ymm1, %ymm1, %ymm0
+# CHECK-NEXT: [0,1]     . DPPeeeeeER   .    .    .   .   vaddps	%ymm1, %ymm1, %ymm0
+# CHECK-NEXT: [1,0]     .  DPPPPPPeeeeER    .    .   .   vperm2f128	$136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: [1,1]     .    DPPPPPPPPeeeeeER    .   .   vaddps	%ymm1, %ymm1, %ymm0
+# CHECK-NEXT: [2,0]     .    .DPPPPPPPPPPPPeeeeER.   .   vperm2f128	$136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: [2,1]     .    .  DPPPPPPPPPPPPPPeeeeeER   vaddps	%ymm1, %ymm1, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BdVer2/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/BdVer2/zero-idioms.s
index 54c1055a60d2f..23b5f3593adab 100644
--- a/llvm/test/tools/llvm-mca/X86/BdVer2/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/BdVer2/zero-idioms.s
@@ -297,6 +297,7 @@ vpxor  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpxor	%xmm3, %xmm3, %xmm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345
 
diff --git a/llvm/test/tools/llvm-mca/X86/Broadwell/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/Broadwell/zero-idioms.s
index b93b501d09baa..b763eae814acb 100644
--- a/llvm/test/tools/llvm-mca/X86/Broadwell/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/Broadwell/zero-idioms.s
@@ -287,6 +287,7 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     vpxor	%ymm3, %ymm3, %ymm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -295,8 +296,8 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,2]     DR   .    .    .    . .   xorl	%eax, %eax
 # CHECK-NEXT: [0,3]     DR   .    .    .    . .   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     .DeER.    .    .    . .   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     .D=eER    .    .    . .   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D==eER   .    .    . .   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     .DPeER    .    .    . .   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPPeER   .    .    . .   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .D----R   .    .    . .   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     . D---R   .    .    . .   pcmpgtd	%xmm2, %xmm2
 # CHECK-NEXT: [0,9]     . D---R   .    .    . .   pcmpgtq	%xmm2, %xmm2
@@ -311,8 +312,8 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,18]    .   D-R   .    .    . .   vpcmpgtw	%xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,19]    .   DeER  .    .    . .   psubb	%mm2, %mm2
 # CHECK-NEXT: [0,20]    .    DeER .    .    . .   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,21]    .    D=eER.    .    . .   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,22]    .    D==eER    .    . .   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,21]    .    DPeER.    .    . .   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,22]    .    DPPeER    .    . .   psubw	%mm2, %mm2
 # CHECK-NEXT: [0,23]    .    D----R    .    . .   psubb	%xmm2, %xmm2
 # CHECK-NEXT: [0,24]    .    .D---R    .    . .   psubd	%xmm2, %xmm2
 # CHECK-NEXT: [0,25]    .    .D---R    .    . .   psubq	%xmm2, %xmm2
@@ -336,18 +337,18 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,43]    .    .    DeER .    . .   andnps	%xmm0, %xmm0
 # CHECK-NEXT: [0,44]    .    .    .DeER.    . .   andnpd	%xmm1, %xmm1
 # CHECK-NEXT: [0,45]    .    .    .D=eER    . .   vandnps	%xmm2, %xmm2, %xmm2
-# CHECK-NEXT: [0,46]    .    .    .D==eER   . .   vandnpd	%xmm1, %xmm1, %xmm1
-# CHECK-NEXT: [0,47]    .    .    .D===eER  . .   vandnps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,48]    .    .    . D===eER . .   vandnpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,46]    .    .    .DP=eER   . .   vandnpd	%xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,47]    .    .    .DPP=eER  . .   vandnps	%ymm2, %ymm2, %ymm2
+# CHECK-NEXT: [0,48]    .    .    . DPP=eER . .   vandnpd	%ymm1, %ymm1, %ymm1
 # CHECK-NEXT: [0,49]    .    .    . DeE---R . .   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,50]    .    .    . D===eER . .   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,50]    .    .    . DPPPeER . .   pandn	%xmm2, %xmm2
 # CHECK-NEXT: [0,51]    .    .    . DeE---R . .   vpandn	%xmm3, %xmm3, %xmm3
 # CHECK-NEXT: [0,52]    .    .    .  DeE--R . .   vpandn	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,53]    .    .    .  D===eER. .   vandnps	%xmm2, %xmm2, %xmm5
-# CHECK-NEXT: [0,54]    .    .    .  D====eER .   vandnpd	%xmm1, %xmm1, %xmm5
-# CHECK-NEXT: [0,55]    .    .    .  D=eE---R .   vpandn	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,56]    .    .    .   D====eER.   vandnps	%ymm2, %ymm2, %ymm5
-# CHECK-NEXT: [0,57]    .    .    .   D=====eER   vandnpd	%ymm1, %ymm1, %ymm5
+# CHECK-NEXT: [0,53]    .    .    .  DPPPeER. .   vandnps	%xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,54]    .    .    .  DPPP=eER .   vandnpd	%xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,55]    .    .    .  DPeE---R .   vpandn	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,56]    .    .    .   DPP==eER.   vandnps	%ymm2, %ymm2, %ymm5
+# CHECK-NEXT: [0,57]    .    .    .   DPP===eER   vandnpd	%ymm1, %ymm1, %ymm5
 # CHECK-NEXT: [0,58]    .    .    .   DeE-----R   vpandn	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,59]    .    .    .   D-------R   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,60]    .    .    .    D------R   xorpd	%xmm1, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/adc-sequence-readadvance.s b/llvm/test/tools/llvm-mca/X86/BtVer2/adc-sequence-readadvance.s
index 4d563adf0cbf6..807cc115cde19 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/adc-sequence-readadvance.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/adc-sequence-readadvance.s
@@ -49,12 +49,13 @@ adc 4(%rsp), %eax
 # CHECK-NEXT: 1.00   1.00    -      -      -      -      -     1.00    -      -      -      -      -      -     adcl	4(%rsp), %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   adcl	4(%rsp), %eax
-# CHECK-NEXT: [1,0]     D=eeeeER .   adcl	4(%rsp), %eax
-# CHECK-NEXT: [2,0]     .D=eeeeER.   adcl	4(%rsp), %eax
-# CHECK-NEXT: [3,0]     .D==eeeeER   adcl	4(%rsp), %eax
+# CHECK-NEXT: [1,0]     DPeeeeER .   adcl	4(%rsp), %eax
+# CHECK-NEXT: [2,0]     .DPeeeeER.   adcl	4(%rsp), %eax
+# CHECK-NEXT: [3,0]     .DPPeeeeER   adcl	4(%rsp), %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/add-sequence.s b/llvm/test/tools/llvm-mca/X86/BtVer2/add-sequence.s
index 80f42c9e8f6bf..0b632b5905de3 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/add-sequence.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/add-sequence.s
@@ -55,6 +55,7 @@ add %eax, %edx
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     addl	%eax, %edx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
@@ -63,31 +64,31 @@ add %eax, %edx
 # CHECK-NEXT: [0,2]     .DeER.    .    .    .   addl	%eax, %edx
 # CHECK-NEXT: [1,0]     .DeER.    .    .    .   addl	%eax, %ecx
 # CHECK-NEXT: [1,1]     . DeER    .    .    .   addl	%esi, %eax
-# CHECK-NEXT: [1,2]     . D=eER   .    .    .   addl	%eax, %edx
+# CHECK-NEXT: [1,2]     . DPeER   .    .    .   addl	%eax, %edx
 # CHECK-NEXT: [2,0]     .  DeER   .    .    .   addl	%eax, %ecx
 # CHECK-NEXT: [2,1]     .  D=eER  .    .    .   addl	%esi, %eax
-# CHECK-NEXT: [2,2]     .   D=eER .    .    .   addl	%eax, %edx
-# CHECK-NEXT: [3,0]     .   D=eER .    .    .   addl	%eax, %ecx
+# CHECK-NEXT: [2,2]     .   DPeER .    .    .   addl	%eax, %edx
+# CHECK-NEXT: [3,0]     .   DPeER .    .    .   addl	%eax, %ecx
 # CHECK-NEXT: [3,1]     .    D=eER.    .    .   addl	%esi, %eax
-# CHECK-NEXT: [3,2]     .    D==eER    .    .   addl	%eax, %edx
-# CHECK-NEXT: [4,0]     .    .D=eER    .    .   addl	%eax, %ecx
-# CHECK-NEXT: [4,1]     .    .D==eER   .    .   addl	%esi, %eax
-# CHECK-NEXT: [4,2]     .    . D==eER  .    .   addl	%eax, %edx
-# CHECK-NEXT: [5,0]     .    . D===eER .    .   addl	%eax, %ecx
-# CHECK-NEXT: [5,1]     .    .  D=eE-R .    .   addl	%esi, %eax
-# CHECK-NEXT: [5,2]     .    .  D==eE-R.    .   addl	%eax, %edx
-# CHECK-NEXT: [6,0]     .    .   D==eER.    .   addl	%eax, %ecx
-# CHECK-NEXT: [6,1]     .    .   D==eE-R    .   addl	%esi, %eax
-# CHECK-NEXT: [6,2]     .    .    D==eER    .   addl	%eax, %edx
-# CHECK-NEXT: [7,0]     .    .    D===eER   .   addl	%eax, %ecx
-# CHECK-NEXT: [7,1]     .    .    .D=eE-R   .   addl	%esi, %eax
-# CHECK-NEXT: [7,2]     .    .    .D==eE-R  .   addl	%eax, %edx
-# CHECK-NEXT: [8,0]     .    .    . D==eER  .   addl	%eax, %ecx
-# CHECK-NEXT: [8,1]     .    .    . D==eE-R .   addl	%esi, %eax
-# CHECK-NEXT: [8,2]     .    .    .  D==eER .   addl	%eax, %edx
-# CHECK-NEXT: [9,0]     .    .    .  D===eER.   addl	%eax, %ecx
-# CHECK-NEXT: [9,1]     .    .    .   D=eE-R.   addl	%esi, %eax
-# CHECK-NEXT: [9,2]     .    .    .   D==eE-R   addl	%eax, %edx
+# CHECK-NEXT: [3,2]     .    DPPeER    .    .   addl	%eax, %edx
+# CHECK-NEXT: [4,0]     .    .DPeER    .    .   addl	%eax, %ecx
+# CHECK-NEXT: [4,1]     .    .DP=eER   .    .   addl	%esi, %eax
+# CHECK-NEXT: [4,2]     .    . DPPeER  .    .   addl	%eax, %edx
+# CHECK-NEXT: [5,0]     .    . DPP=eER .    .   addl	%eax, %ecx
+# CHECK-NEXT: [5,1]     .    .  DPeE-R .    .   addl	%esi, %eax
+# CHECK-NEXT: [5,2]     .    .  DPPeE-R.    .   addl	%eax, %edx
+# CHECK-NEXT: [6,0]     .    .   DPPeER.    .   addl	%eax, %ecx
+# CHECK-NEXT: [6,1]     .    .   DP=eE-R    .   addl	%esi, %eax
+# CHECK-NEXT: [6,2]     .    .    DPPeER    .   addl	%eax, %edx
+# CHECK-NEXT: [7,0]     .    .    DPP=eER   .   addl	%eax, %ecx
+# CHECK-NEXT: [7,1]     .    .    .DPeE-R   .   addl	%esi, %eax
+# CHECK-NEXT: [7,2]     .    .    .DPPeE-R  .   addl	%eax, %edx
+# CHECK-NEXT: [8,0]     .    .    . DPPeER  .   addl	%eax, %ecx
+# CHECK-NEXT: [8,1]     .    .    . DP=eE-R .   addl	%esi, %eax
+# CHECK-NEXT: [8,2]     .    .    .  DPPeER .   addl	%eax, %edx
+# CHECK-NEXT: [9,0]     .    .    .  DPP=eER.   addl	%eax, %ecx
+# CHECK-NEXT: [9,1]     .    .    .   DPeE-R.   addl	%esi, %eax
+# CHECK-NEXT: [9,2]     .    .    .   DPPeE-R   addl	%eax, %edx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-1.s
index 30b05eb290efd..13c78d7f14f76 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-1.s
@@ -81,12 +81,13 @@ add %edx, %eax
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -     addl	%edx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   addl	%eax, %ebx
-# CHECK-NEXT: [0,1]     D=eER..   addl	%ebx, %ecx
-# CHECK-NEXT: [0,2]     .D=eER.   addl	%ecx, %edx
-# CHECK-NEXT: [0,3]     .D==eER   addl	%edx, %eax
+# CHECK-NEXT: [0,1]     DPeER..   addl	%ebx, %ecx
+# CHECK-NEXT: [0,2]     .DPeER.   addl	%ecx, %edx
+# CHECK-NEXT: [0,3]     .DPPeER   addl	%edx, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-2.s
index 4ff19360c921b..c212233b7927f 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-2.s
@@ -71,6 +71,7 @@ vhaddps %xmm0, %xmm0, %xmm1
 # CHECK-NEXT:  -      -      -     1.00    -     1.00    -      -      -      -      -      -      -      -     vhaddps	%xmm0, %xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeeeeER   vhaddps	%xmm0, %xmm0, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-3.s b/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-3.s
index 1f13a1f5e8752..e1a807bdae582 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/bottleneck-hints-3.s
@@ -97,17 +97,18 @@ vmovaps %xmm0, 48(%rdi)
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -     1.00   1.00    -      -      -     vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   vmovaps	(%rsi), %xmm0
-# CHECK-NEXT: [0,1]     D=====eER .    .    .    ..   vmovaps	%xmm0, (%rdi)
-# CHECK-NEXT: [0,2]     .D=====eeeeeER .    .    ..   vmovaps	16(%rsi), %xmm0
-# CHECK-NEXT: [0,3]     .D==========eER.    .    ..   vmovaps	%xmm0, 16(%rdi)
-# CHECK-NEXT: [0,4]     . D==========eeeeeER.    ..   vmovaps	32(%rsi), %xmm0
-# CHECK-NEXT: [0,5]     . D===============eER    ..   vmovaps	%xmm0, 32(%rdi)
-# CHECK-NEXT: [0,6]     .  D===============eeeeeER.   vmovaps	48(%rsi), %xmm0
-# CHECK-NEXT: [0,7]     .  D====================eER   vmovaps	%xmm0, 48(%rdi)
+# CHECK-NEXT: [0,1]     DPPPPPeER .    .    .    ..   vmovaps	%xmm0, (%rdi)
+# CHECK-NEXT: [0,2]     .DPPPPPeeeeeER .    .    ..   vmovaps	16(%rsi), %xmm0
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPPeER.    .    ..   vmovaps	%xmm0, 16(%rdi)
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPeeeeeER.    ..   vmovaps	32(%rsi), %xmm0
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeER    ..   vmovaps	%xmm0, 32(%rdi)
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPeeeeeER.   vmovaps	48(%rsi), %xmm0
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPeER   vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/clear-super-register-1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/clear-super-register-1.s
index 0bd5f451e2e34..b182b068a89c9 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/clear-super-register-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/clear-super-register-1.s
@@ -38,6 +38,7 @@ bsf   %rax, %rcx
 # CHECK-NEXT:  7      4     4.00                        bsfq	%rax, %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
@@ -45,10 +46,10 @@ bsf   %rax, %rcx
 # CHECK-NEXT: [0,1]     DeE-----R .    .   lzcntl	%ecx, %eax
 # CHECK-NEXT: [0,2]     .DeE-----R.    .   andq	%rcx, %rax
 # CHECK-NEXT: [0,3]     . DeeeeE-R.    .   bsfq	%rax, %rcx
-# CHECK-NEXT: [1,0]     .    D=eeeeeeER.   imulq	$5, %rcx, %rax
+# CHECK-NEXT: [1,0]     .    DPeeeeeeER.   imulq	$5, %rcx, %rax
 # CHECK-NEXT: [1,1]     .    .D=eE----R.   lzcntl	%ecx, %eax
-# CHECK-NEXT: [1,2]     .    .D==eE----R   andq	%rcx, %rax
-# CHECK-NEXT: [1,3]     .    . D==eeeeER   bsfq	%rax, %rcx
+# CHECK-NEXT: [1,2]     .    .DPPeE----R   andq	%rcx, %rax
+# CHECK-NEXT: [1,3]     .    . DPPeeeeER   bsfq	%rax, %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/clear-super-register-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/clear-super-register-2.s
index 134e83f73fb12..b6a1d580ab172 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/clear-super-register-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/clear-super-register-2.s
@@ -70,13 +70,14 @@ vandps %xmm4, %xmm1, %xmm0
 # CHECK-NEXT:  1      1     0.50                        vandps	%xmm4, %xmm1, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeER    .    .    .    .    .    .    .   .   vdivps	%ymm0, %ymm1, %ymm3
 # CHECK-NEXT: [0,1]     .DeeeE----------------------------------R    .    .    .    .    .    .    .   .   vaddps	%xmm0, %xmm1, %xmm3
-# CHECK-NEXT: [0,2]     . D==eeeE--------------------------------R   .    .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,3]     .  D===eeeE------------------------------R   .    .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,2]     . DPPeeeE--------------------------------R   .    .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,3]     .  DP==eeeE------------------------------R   .    .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,4]     .   D====eeeE-----------------------------R  .    .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,5]     .    D=====eeeE---------------------------R  .    .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,6]     .    .D======eeeE--------------------------R .    .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
@@ -90,11 +91,11 @@ vandps %xmm4, %xmm1, %xmm0
 # CHECK-NEXT: [0,14]    .    .    .   D==============eeeE--------------R  .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,15]    .    .    .    D===============eeeE------------R  .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: [0,16]    .    .    .    .D================eeeE-----------R .    .    .    .    .    .   .   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [0,17]    .    .    .    . D==================eE----------R .    .    .    .    .    .   .   vandps	%xmm4, %xmm1, %xmm0
-# CHECK-NEXT: [1,0]     .    .    .    .  D====================eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeER.   vdivps	%ymm0, %ymm1, %ymm3
-# CHECK-NEXT: [1,1]     .    .    .    .   D=================eeeE-------------------------------------R.   vaddps	%xmm0, %xmm1, %xmm3
-# CHECK-NEXT: [1,2]     .    .    .    .    D===================eeeE-----------------------------------R   vaddps	%ymm3, %ymm1, %ymm4
-# CHECK-NEXT: [1,3]     .    .    .    .    .D====================eeeE---------------------------------R   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [0,17]    .    .    .    . DPPPPPPPPPPPPPPPPPPeE----------R .    .    .    .    .    .   .   vandps	%xmm4, %xmm1, %xmm0
+# CHECK-NEXT: [1,0]     .    .    .    .  DPPPPPPPPPPPPPPPPPP==eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeER.   vdivps	%ymm0, %ymm1, %ymm3
+# CHECK-NEXT: [1,1]     .    .    .    .   DPPPPPPPPPPPPPPPPPeeeE-------------------------------------R.   vaddps	%xmm0, %xmm1, %xmm3
+# CHECK-NEXT: [1,2]     .    .    .    .    DPPPPPPPPPPPPPPPPPPPeeeE-----------------------------------R   vaddps	%ymm3, %ymm1, %ymm4
+# CHECK-NEXT: [1,3]     .    .    .    .    .DPPPPPPPPPPPPPPPPPP==eeeE---------------------------------R   vaddps	%ymm3, %ymm1, %ymm4
 # CHECK-NEXT: Truncated display due to cycle limit
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/cmpxchg-read-advance.s b/llvm/test/tools/llvm-mca/X86/BtVer2/cmpxchg-read-advance.s
index c0b9c7ed37d95..247ed13acc58b 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/cmpxchg-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/cmpxchg-read-advance.s
@@ -95,11 +95,12 @@ lock cmpxchg16b (%rsp)
 # CHECK-NEXT: 3.00    -      -      -      -      -      -     1.00    -     1.00    -      -      -      -     cmpxchgq	%rcx, (%rdx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   imulq	%rax, %rax
-# CHECK-NEXT: [0,1]     .D==eeeeeeeeeeeER   cmpxchgq	%rcx, (%rdx)
+# CHECK-NEXT: [0,1]     .DPPeeeeeeeeeeeER   cmpxchgq	%rcx, (%rdx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -162,11 +163,12 @@ lock cmpxchg16b (%rsp)
 # CHECK-NEXT: 3.00    -      -      -      -      -      -     1.00    -     1.00    -      -      -      -     cmpxchgq	%rcx, (%rdx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .    ..   imulq	%rcx, %rcx
-# CHECK-NEXT: [0,1]     .D==eeeeeeeeeeeER   cmpxchgq	%rcx, (%rdx)
+# CHECK-NEXT: [0,1]     .DPPeeeeeeeeeeeER   cmpxchgq	%rcx, (%rdx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -229,11 +231,12 @@ lock cmpxchg16b (%rsp)
 # CHECK-NEXT: 3.00    -      -      -      -      -      -     17.00   -     17.00   -      -      -      -     lock		cmpxchgq	%rcx, (%rdx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeER .    .    . .   imulq	%rax, %rax
-# CHECK-NEXT: [0,1]     .D==eeeeeeeeeeeeeeeeeER   lock		cmpxchgq	%rcx, (%rdx)
+# CHECK-NEXT: [0,1]     .DPPeeeeeeeeeeeeeeeeeER   lock		cmpxchgq	%rcx, (%rdx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -296,11 +299,12 @@ lock cmpxchg16b (%rsp)
 # CHECK-NEXT: 3.00    -      -      -      -      -      -     17.00   -     17.00   -      -      -      -     lock		cmpxchgq	%rcx, (%rdx)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
 # CHECK:      [0,0]     DeeeeeeER .    .    . .   imulq	%rcx, %rcx
-# CHECK-NEXT: [0,1]     .D==eeeeeeeeeeeeeeeeeER   lock		cmpxchgq	%rcx, (%rdx)
+# CHECK-NEXT: [0,1]     .DPPeeeeeeeeeeeeeeeeeER   lock		cmpxchgq	%rcx, (%rdx)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -365,6 +369,7 @@ lock cmpxchg16b (%rsp)
 # CHECK-NEXT: 3.00    -      -      -      -      -      -     1.00    -     1.00    -      -      -      -     cmpxchg8b	(%rsp)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
@@ -436,6 +441,7 @@ lock cmpxchg16b (%rsp)
 # CHECK-NEXT: 6.00    -      -      -      -      -      -     1.00    -     1.00    -      -      -      -     cmpxchg16b	(%rsp)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012345
 # CHECK-NEXT: Index     0123456789          0123456789
 
@@ -507,6 +513,7 @@ lock cmpxchg16b (%rsp)
 # CHECK-NEXT: 3.00    -      -      -      -      -      -     19.00   -     19.00   -      -      -      -     lock		cmpxchg8b	(%rsp)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012
 
@@ -578,6 +585,7 @@ lock cmpxchg16b (%rsp)
 # CHECK-NEXT: 6.00    -      -      -      -      -      -     38.00   -     38.00   -      -      -      -     lock		cmpxchg16b	(%rsp)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-cmp.s b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-cmp.s
index 25762ec14ad3b..7003fbc19900a 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-cmp.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-cmp.s
@@ -57,14 +57,15 @@ cmovae %ebx, %eax
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -     cmovael	%ebx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   cmpl	%eax, %eax
-# CHECK-NEXT: [0,1]     D=eER..   cmovael	%ebx, %eax
+# CHECK-NEXT: [0,1]     DPeER..   cmovael	%ebx, %eax
 # CHECK-NEXT: [1,0]     .DeER..   cmpl	%eax, %eax
-# CHECK-NEXT: [1,1]     .D=eER.   cmovael	%ebx, %eax
+# CHECK-NEXT: [1,1]     .DPeER.   cmovael	%ebx, %eax
 # CHECK-NEXT: [2,0]     . DeER.   cmpl	%eax, %eax
-# CHECK-NEXT: [2,1]     . D=eER   cmovael	%ebx, %eax
+# CHECK-NEXT: [2,1]     . DPeER   cmovael	%ebx, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpeq.s b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpeq.s
index 4f7187fa1e14b..120056d2c1738 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpeq.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpeq.s
@@ -64,6 +64,7 @@ vpcmpeqq %xmm3, %xmm3, %xmm0
 # CHECK-NEXT:  -      -      -      -      -     1.00    -      -      -      -      -     1.00    -      -     vpcmpeqq	%xmm3, %xmm3, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   vpcmpeqb	%xmm0, %xmm0, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpgt.s b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpgt.s
index 014062abed383..9e8fab16f51e9 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpgt.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpgt.s
@@ -65,6 +65,7 @@ vpcmpgtq %xmm3, %xmm3, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpcmpgtq	%xmm3, %xmm3, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DR   ..   vpcmpgtb	%xmm0, %xmm0, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-1.s
index 6466998763c25..02aa227ad353e 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-1.s
@@ -58,14 +58,15 @@ sbb %eax, %eax
 # CHECK-NEXT: 2.00    -      -      -      -      -      -      -      -      -      -      -      -      -     sbbl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   sbbl	%edx, %edx
-# CHECK-NEXT: [0,1]     D=eER.  .   sbbl	%eax, %eax
-# CHECK-NEXT: [1,0]     .D=eER  .   sbbl	%edx, %edx
-# CHECK-NEXT: [1,1]     .D==eER .   sbbl	%eax, %eax
-# CHECK-NEXT: [2,0]     . D==eER.   sbbl	%edx, %edx
-# CHECK-NEXT: [2,1]     . D===eER   sbbl	%eax, %eax
+# CHECK-NEXT: [0,1]     DPeER.  .   sbbl	%eax, %eax
+# CHECK-NEXT: [1,0]     .DPeER  .   sbbl	%edx, %edx
+# CHECK-NEXT: [1,1]     .DPPeER .   sbbl	%eax, %eax
+# CHECK-NEXT: [2,0]     . DPPeER.   sbbl	%edx, %edx
+# CHECK-NEXT: [2,1]     . DPPPeER   sbbl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-2.s
index 69179506e4741..889bade165329 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-2.s
@@ -61,18 +61,19 @@ sbb %eax, %eax
 # CHECK-NEXT: 2.00    -      -      -      -      -      -      -      -      -      -      -      -      -     sbbl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    ..   imull	%edx, %eax
 # CHECK-NEXT: [0,1]     DeE--R    ..   addl	%edx, %edx
 # CHECK-NEXT: [0,2]     .DeE--R   ..   sbbl	%eax, %eax
-# CHECK-NEXT: [1,0]     .D==eeeER ..   imull	%edx, %eax
+# CHECK-NEXT: [1,0]     .DP=eeeER ..   imull	%edx, %eax
 # CHECK-NEXT: [1,1]     . DeE---R ..   addl	%edx, %edx
-# CHECK-NEXT: [1,2]     . D=eE---R..   sbbl	%eax, %eax
-# CHECK-NEXT: [2,0]     .  D==eeeER.   imull	%edx, %eax
+# CHECK-NEXT: [1,2]     . DPeE---R..   sbbl	%eax, %eax
+# CHECK-NEXT: [2,0]     .  DP=eeeER.   imull	%edx, %eax
 # CHECK-NEXT: [2,1]     .  D=eE---R.   addl	%edx, %edx
-# CHECK-NEXT: [2,2]     .   D=eE---R   sbbl	%eax, %eax
+# CHECK-NEXT: [2,2]     .   DPeE---R   sbbl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/dependent-pmuld-paddd.s b/llvm/test/tools/llvm-mca/X86/BtVer2/dependent-pmuld-paddd.s
index 2804ef6977091..ad848502fcfb4 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/dependent-pmuld-paddd.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/dependent-pmuld-paddd.s
@@ -55,39 +55,40 @@ vpaddd %xmm0, %xmm0, %xmm3
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     vpaddd	%xmm0, %xmm0, %xmm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeER.    .    .    .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [0,1]     D==eER    .    .    .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [0,2]     .D==eER   .    .    .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [1,0]     .D==eeER  .    .    .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [1,1]     . D===eER .    .    .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [1,2]     . D====eER.    .    .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [2,0]     .  D===eeER    .    .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [2,1]     .  D=====eER   .    .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [2,2]     .   D=====eER  .    .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [3,0]     .   D=====eeER .    .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [3,1]     .    D======eER.    .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [3,2]     .    D=======eER    .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [4,0]     .    .D======eeER   .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [4,1]     .    .D========eER  .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [4,2]     .    . D========eER .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [5,0]     .    . D========eeER.    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [5,1]     .    .  D=========eER    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [5,2]     .    .  D==========eER   .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [6,0]     .    .   D=========eeER  .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [6,1]     .    .   D===========eER .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [6,2]     .    .    D===========eER.    .  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [7,0]     .    .    D===========eeER    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [7,1]     .    .    .D============eER   .  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [7,2]     .    .    .D=============eER  .  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [8,0]     .    .    . D============eeER .  .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [8,1]     .    .    . D==============eER.  .   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [8,2]     .    .    .  D==============eER  .   vpaddd	%xmm0, %xmm0, %xmm3
-# CHECK-NEXT: [9,0]     .    .    .  D==============eeER .   vpmuldq	%xmm0, %xmm0, %xmm1
-# CHECK-NEXT: [9,1]     .    .    .   D===============eER.   vpaddd	%xmm1, %xmm1, %xmm0
-# CHECK-NEXT: [9,2]     .    .    .   D================eER   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [0,1]     DPPeER    .    .    .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [0,2]     .DPPeER   .    .    .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [1,0]     .DPPeeER  .    .    .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [1,1]     . DPPPeER .    .    .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [1,2]     . DPPPPeER.    .    .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [2,0]     .  DPPPeeER    .    .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [2,1]     .  DPPPPPeER   .    .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [2,2]     .   DPPPPPeER  .    .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [3,0]     .   DPPPPPeeER .    .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [3,1]     .    DPPPPPPeER.    .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [3,2]     .    DPPPPPPPeER    .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [4,0]     .    .DPPPPPPeeER   .    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [4,1]     .    .DPPPPPPPPeER  .    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [4,2]     .    . DPPPPPPPPeER .    .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [5,0]     .    . DPPPPPPPPeeER.    .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [5,1]     .    .  DPPPPPPPPPeER    .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [5,2]     .    .  DPPPPPPPPPPeER   .    .  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [6,0]     .    .   DPPPPPPPPPeeER  .    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [6,1]     .    .   DPPPPPPPPPPPeER .    .  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [6,2]     .    .    DPPPPPPPPPPPeER.    .  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [7,0]     .    .    DPPPPPPPPPPPeeER    .  .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [7,1]     .    .    .DPPPPPPPPPPPPeER   .  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [7,2]     .    .    .DPPPPPPPPPPPPPeER  .  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [8,0]     .    .    . DPPPPPPPPPPPPeeER .  .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [8,1]     .    .    . DPPPPPPPPPPPPPPeER.  .   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [8,2]     .    .    .  DPPPPPPPPPPPPPPeER  .   vpaddd	%xmm0, %xmm0, %xmm3
+# CHECK-NEXT: [9,0]     .    .    .  DPPPPPPPPPPPPPPeeER .   vpmuldq	%xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [9,1]     .    .    .   DPPPPPPPPPPPPPPPeER.   vpaddd	%xmm1, %xmm1, %xmm0
+# CHECK-NEXT: [9,2]     .    .    .   DPPPPPPPPPPPPPPPPeER   vpaddd	%xmm0, %xmm0, %xmm3
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/dot-product.s b/llvm/test/tools/llvm-mca/X86/BtVer2/dot-product.s
index fdfbf311b1a22..a1e277c931b01 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/dot-product.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/dot-product.s
@@ -55,18 +55,19 @@ vhaddps  %xmm3, %xmm3, %xmm4
 # CHECK-NEXT:  -      -      -     1.00    -     1.00    -      -      -      -      -      -      -      -     vhaddps	%xmm3, %xmm3, %xmm4
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .    .   vmulps	%xmm0, %xmm1, %xmm2
-# CHECK-NEXT: [0,1]     D==eeeeER .    .   vhaddps	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [0,2]     .D=====eeeeER  .   vhaddps	%xmm3, %xmm3, %xmm4
+# CHECK-NEXT: [0,1]     DPPeeeeER .    .   vhaddps	%xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [0,2]     .DPPPPPeeeeER  .   vhaddps	%xmm3, %xmm3, %xmm4
 # CHECK-NEXT: [1,0]     .DeeE-------R  .   vmulps	%xmm0, %xmm1, %xmm2
-# CHECK-NEXT: [1,1]     . D=eeeeE----R .   vhaddps	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [1,2]     . D=====eeeeER .   vhaddps	%xmm3, %xmm3, %xmm4
+# CHECK-NEXT: [1,1]     . DPeeeeE----R .   vhaddps	%xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [1,2]     . DPPPPPeeeeER .   vhaddps	%xmm3, %xmm3, %xmm4
 # CHECK-NEXT: [2,0]     .  DeeE-------R.   vmulps	%xmm0, %xmm1, %xmm2
-# CHECK-NEXT: [2,1]     .  D==eeeeE---R.   vhaddps	%xmm2, %xmm2, %xmm3
-# CHECK-NEXT: [2,2]     .   D=====eeeeER   vhaddps	%xmm3, %xmm3, %xmm4
+# CHECK-NEXT: [2,1]     .  DPPeeeeE---R.   vhaddps	%xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [2,2]     .   DPPPPPeeeeER   vhaddps	%xmm3, %xmm3, %xmm4
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/hadd-read-after-ld-1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/hadd-read-after-ld-1.s
index ebf2739665620..23bf12e2d4910 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/hadd-read-after-ld-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/hadd-read-after-ld-1.s
@@ -27,6 +27,7 @@ vhaddps (%rdi), %xmm1, %xmm2
 # CHECK-NEXT:  1      9     1.00    *                   vhaddps	(%rdi), %xmm1, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/hadd-read-after-ld-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/hadd-read-after-ld-2.s
index 7b9a1e601b704..5d16c1a764a49 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/hadd-read-after-ld-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/hadd-read-after-ld-2.s
@@ -27,6 +27,7 @@ vhaddps (%rdi), %ymm1, %ymm2
 # CHECK-NEXT:  2      9     2.00    *                   vhaddps	(%rdi), %ymm1, %ymm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/independent-load-stores.s b/llvm/test/tools/llvm-mca/X86/BtVer2/independent-load-stores.s
index bd202b604458f..dc42cb09ff68d 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/independent-load-stores.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/independent-load-stores.s
@@ -85,6 +85,7 @@
 # ALL-NEXT:      1.00    -      -      -      -      -      -     1.00    -     1.00    -      -      -      -     addq	$44, 640(%r14)
 
 # ALL:           Timeline view:
+# ALL-NEXT:      D: Instruction dispatched
 
 # NOALIAS-NEXT:                      01234567
 # NOALIAS-NEXT:  Index     0123456789
@@ -95,24 +96,24 @@
 # NOALIAS:       [0,0]     DeeeeeeER .    . .   addq	$44, 64(%r14)
 # NOALIAS-NEXT:  [0,1]     D=eeeeeeER.    . .   addq	$44, 128(%r14)
 # NOALIAS-NEXT:  [0,2]     .D=eeeeeeER    . .   addq	$44, 192(%r14)
-# NOALIAS-NEXT:  [0,3]     .D==eeeeeeER   . .   addq	$44, 256(%r14)
-# NOALIAS-NEXT:  [0,4]     . D==eeeeeeER  . .   addq	$44, 320(%r14)
-# NOALIAS-NEXT:  [0,5]     . D===eeeeeeER . .   addq	$44, 384(%r14)
-# NOALIAS-NEXT:  [0,6]     .  D===eeeeeeER. .   addq	$44, 448(%r14)
-# NOALIAS-NEXT:  [0,7]     .  D====eeeeeeER .   addq	$44, 512(%r14)
-# NOALIAS-NEXT:  [0,8]     .   D====eeeeeeER.   addq	$44, 576(%r14)
-# NOALIAS-NEXT:  [0,9]     .   D=====eeeeeeER   addq	$44, 640(%r14)
+# NOALIAS-NEXT:  [0,3]     .DP=eeeeeeER   . .   addq	$44, 256(%r14)
+# NOALIAS-NEXT:  [0,4]     . DP=eeeeeeER  . .   addq	$44, 320(%r14)
+# NOALIAS-NEXT:  [0,5]     . DPP=eeeeeeER . .   addq	$44, 384(%r14)
+# NOALIAS-NEXT:  [0,6]     .  DPP=eeeeeeER. .   addq	$44, 448(%r14)
+# NOALIAS-NEXT:  [0,7]     .  DPPP=eeeeeeER .   addq	$44, 512(%r14)
+# NOALIAS-NEXT:  [0,8]     .   DPPP=eeeeeeER.   addq	$44, 576(%r14)
+# NOALIAS-NEXT:  [0,9]     .   DPPPP=eeeeeeER   addq	$44, 640(%r14)
 
 # YESALIAS:      [0,0]     DeeeeeeER .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 64(%r14)
-# YESALIAS-NEXT: [0,1]     D======eeeeeeER.    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
-# YESALIAS-NEXT: [0,2]     .D===========eeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
-# YESALIAS-NEXT: [0,3]     .D=================eeeeeeER   .    .    .    .    .    .    . .   addq	$44, 256(%r14)
-# YESALIAS-NEXT: [0,4]     . D======================eeeeeeER  .    .    .    .    .    . .   addq	$44, 320(%r14)
-# YESALIAS-NEXT: [0,5]     . D============================eeeeeeER .    .    .    .    . .   addq	$44, 384(%r14)
-# YESALIAS-NEXT: [0,6]     .  D=================================eeeeeeER.    .    .    . .   addq	$44, 448(%r14)
-# YESALIAS-NEXT: [0,7]     .  D=======================================eeeeeeER    .    . .   addq	$44, 512(%r14)
-# YESALIAS-NEXT: [0,8]     .   D============================================eeeeeeER   . .   addq	$44, 576(%r14)
-# YESALIAS-NEXT: [0,9]     .   D==================================================eeeeeeER   addq	$44, 640(%r14)
+# YESALIAS-NEXT: [0,1]     DPPPPPPeeeeeeER.    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
+# YESALIAS-NEXT: [0,2]     .DPPPPPPPPPPPeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
+# YESALIAS-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPeeeeeeER   .    .    .    .    .    .    . .   addq	$44, 256(%r14)
+# YESALIAS-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPPPPeeeeeeER  .    .    .    .    .    . .   addq	$44, 320(%r14)
+# YESALIAS-NEXT: [0,5]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER .    .    .    .    . .   addq	$44, 384(%r14)
+# YESALIAS-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER.    .    .    . .   addq	$44, 448(%r14)
+# YESALIAS-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER    .    . .   addq	$44, 512(%r14)
+# YESALIAS-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER   . .   addq	$44, 576(%r14)
+# YESALIAS-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER   addq	$44, 640(%r14)
 
 # ALL:           Average Wait times (based on the timeline view):
 # ALL-NEXT:      [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/int-to-fpu-forwarding-3.s b/llvm/test/tools/llvm-mca/X86/BtVer2/int-to-fpu-forwarding-3.s
index 432b262c12198..1166fe12af7ea 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/int-to-fpu-forwarding-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/int-to-fpu-forwarding-3.s
@@ -57,18 +57,19 @@ vpinsrb $1, %eax, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -     1.00    -      -      -      -      -     1.00    -      -     vpinsrb	$1, %eax, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    .    . .   addl	%eax, %eax
-# CHECK-NEXT: [0,1]     .D======eER    . .   vpinsrb	$0, %eax, %xmm0, %xmm0
-# CHECK-NEXT: [0,2]     . D======eER   . .   vpinsrb	$1, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     .DPPPPPPeER    . .   vpinsrb	$0, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [0,2]     . DPPPPPPeER   . .   vpinsrb	$1, %eax, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     .  DeE-----R   . .   addl	%eax, %eax
-# CHECK-NEXT: [1,1]     .   D======eER . .   vpinsrb	$0, %eax, %xmm0, %xmm0
-# CHECK-NEXT: [1,2]     .    D======eER. .   vpinsrb	$1, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     .   DPPPPPPeER . .   vpinsrb	$0, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [1,2]     .    DPPPPPPeER. .   vpinsrb	$1, %eax, %xmm0, %xmm0
 # CHECK-NEXT: [2,0]     .    .DeE-----R. .   addl	%eax, %eax
-# CHECK-NEXT: [2,1]     .    . D======eER.   vpinsrb	$0, %eax, %xmm0, %xmm0
-# CHECK-NEXT: [2,2]     .    .  D======eER   vpinsrb	$1, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [2,1]     .    . DPPPPPPeER.   vpinsrb	$0, %eax, %xmm0, %xmm0
+# CHECK-NEXT: [2,2]     .    .  DPPPPPPeER   vpinsrb	$1, %eax, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/load-store-alias.s b/llvm/test/tools/llvm-mca/X86/BtVer2/load-store-alias.s
index e6294d6536d19..1a77f98a3d4c5 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/load-store-alias.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/load-store-alias.s
@@ -70,17 +70,18 @@ vmovaps %xmm0, 48(%rdi)
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -     1.00   1.00    -      -      -     vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   vmovaps	(%rsi), %xmm0
-# CHECK-NEXT: [0,1]     D=====eER .    .    .    ..   vmovaps	%xmm0, (%rdi)
-# CHECK-NEXT: [0,2]     .D=====eeeeeER .    .    ..   vmovaps	16(%rsi), %xmm0
-# CHECK-NEXT: [0,3]     .D==========eER.    .    ..   vmovaps	%xmm0, 16(%rdi)
-# CHECK-NEXT: [0,4]     . D==========eeeeeER.    ..   vmovaps	32(%rsi), %xmm0
-# CHECK-NEXT: [0,5]     . D===============eER    ..   vmovaps	%xmm0, 32(%rdi)
-# CHECK-NEXT: [0,6]     .  D===============eeeeeER.   vmovaps	48(%rsi), %xmm0
-# CHECK-NEXT: [0,7]     .  D====================eER   vmovaps	%xmm0, 48(%rdi)
+# CHECK-NEXT: [0,1]     DPPPPPeER .    .    .    ..   vmovaps	%xmm0, (%rdi)
+# CHECK-NEXT: [0,2]     .DPPPPPeeeeeER .    .    ..   vmovaps	16(%rsi), %xmm0
+# CHECK-NEXT: [0,3]     .DPPPPPPPPPPeER.    .    ..   vmovaps	%xmm0, 16(%rdi)
+# CHECK-NEXT: [0,4]     . DPPPPPPPPPPeeeeeER.    ..   vmovaps	32(%rsi), %xmm0
+# CHECK-NEXT: [0,5]     . DPPPPPPPPPPPPPPPeER    ..   vmovaps	%xmm0, 32(%rdi)
+# CHECK-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPeeeeeER.   vmovaps	48(%rsi), %xmm0
+# CHECK-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPeER   vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/memcpy-like-test.s b/llvm/test/tools/llvm-mca/X86/BtVer2/memcpy-like-test.s
index 4162d85166f19..c01a8271f6e48 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/memcpy-like-test.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/memcpy-like-test.s
@@ -70,17 +70,18 @@ vmovaps %xmm0, 48(%rdi)
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -     1.00   1.00    -      -      -     vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeER  ..   vmovaps	(%rsi), %xmm0
-# CHECK-NEXT: [0,1]     D=====eER ..   vmovaps	%xmm0, (%rdi)
+# CHECK-NEXT: [0,1]     DPPPPPeER ..   vmovaps	%xmm0, (%rdi)
 # CHECK-NEXT: [0,2]     .DeeeeeER ..   vmovaps	16(%rsi), %xmm0
-# CHECK-NEXT: [0,3]     .D=====eER..   vmovaps	%xmm0, 16(%rdi)
+# CHECK-NEXT: [0,3]     .DPPPPPeER..   vmovaps	%xmm0, 16(%rdi)
 # CHECK-NEXT: [0,4]     . DeeeeeER..   vmovaps	32(%rsi), %xmm0
-# CHECK-NEXT: [0,5]     . D=====eER.   vmovaps	%xmm0, 32(%rdi)
+# CHECK-NEXT: [0,5]     . DPPPPPeER.   vmovaps	%xmm0, 32(%rdi)
 # CHECK-NEXT: [0,6]     .  DeeeeeER.   vmovaps	48(%rsi), %xmm0
-# CHECK-NEXT: [0,7]     .  D=====eER   vmovaps	%xmm0, 48(%rdi)
+# CHECK-NEXT: [0,7]     .  DPPPPPeER   vmovaps	%xmm0, 48(%rdi)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/negative-read-advance.s b/llvm/test/tools/llvm-mca/X86/BtVer2/negative-read-advance.s
index de409e1c28d04..90302f51cf38f 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/negative-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/negative-read-advance.s
@@ -64,15 +64,16 @@ vpinsrd $3, %ebx, %xmm8, %xmm10
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -      -      -      -     1.00    -     vpinsrd	$3, %ebx, %xmm8, %xmm10
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    . .   addl	%ebx, %ebx
-# CHECK-NEXT: [0,1]     .D======eER .   vpinsrd	$1, %ebx, %xmm0, %xmm1
-# CHECK-NEXT: [0,2]     . D=====eER .   vpinsrd	$1, %ebx, %xmm2, %xmm3
-# CHECK-NEXT: [0,3]     .  D=====eER.   vpinsrd	$2, %ebx, %xmm4, %xmm5
-# CHECK-NEXT: [0,4]     .   D====eER.   vpinsrd	$2, %ebx, %xmm6, %xmm7
-# CHECK-NEXT: [0,5]     .    D====eER   vpinsrd	$3, %ebx, %xmm8, %xmm10
+# CHECK-NEXT: [0,1]     .DPPPPPPeER .   vpinsrd	$1, %ebx, %xmm0, %xmm1
+# CHECK-NEXT: [0,2]     . DPPPPPeER .   vpinsrd	$1, %ebx, %xmm2, %xmm3
+# CHECK-NEXT: [0,3]     .  DPPPP=eER.   vpinsrd	$2, %ebx, %xmm4, %xmm5
+# CHECK-NEXT: [0,4]     .   DPPP=eER.   vpinsrd	$2, %ebx, %xmm6, %xmm7
+# CHECK-NEXT: [0,5]     .    DPP==eER   vpinsrd	$3, %ebx, %xmm8, %xmm10
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/one-idioms.s b/llvm/test/tools/llvm-mca/X86/BtVer2/one-idioms.s
index 3377e92253b16..62e5f70c6db9a 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/one-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/one-idioms.s
@@ -115,6 +115,7 @@ vpcmpeqw  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT:  -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -     vpcmpeqw	%xmm3, %xmm3, %xmm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-2.s
index 722e37a70831c..97f9572f6ba07 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-2.s
@@ -29,12 +29,13 @@ add    %ecx, %ebx
 # CHECK-NEXT:  1      1     0.50                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeER .   imulq	%rax, %rbx
-# CHECK-NEXT: [0,1]     D======eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     .D======eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPPPPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     .DPPPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-3.s b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-3.s
index 9e824acab7142..763550b507927 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-3.s
@@ -60,18 +60,19 @@ xor %bx, %dx
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     xorw	%bx, %dx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    ..   addw	%cx, %dx
-# CHECK-NEXT: [0,1]     D=eER.    ..   movw	%ax, %dx
-# CHECK-NEXT: [0,2]     .D=eER    ..   xorw	%bx, %dx
-# CHECK-NEXT: [1,0]     .D==eER   ..   addw	%cx, %dx
-# CHECK-NEXT: [1,1]     . D==eER  ..   movw	%ax, %dx
-# CHECK-NEXT: [1,2]     . D===eER ..   xorw	%bx, %dx
-# CHECK-NEXT: [2,0]     .  D===eER..   addw	%cx, %dx
-# CHECK-NEXT: [2,1]     .  D====eER.   movw	%ax, %dx
-# CHECK-NEXT: [2,2]     .   D====eER   xorw	%bx, %dx
+# CHECK-NEXT: [0,1]     DPeER.    ..   movw	%ax, %dx
+# CHECK-NEXT: [0,2]     .DPeER    ..   xorw	%bx, %dx
+# CHECK-NEXT: [1,0]     .DPPeER   ..   addw	%cx, %dx
+# CHECK-NEXT: [1,1]     . DPPeER  ..   movw	%ax, %dx
+# CHECK-NEXT: [1,2]     . DPPPeER ..   xorw	%bx, %dx
+# CHECK-NEXT: [2,0]     .  DPPPeER..   addw	%cx, %dx
+# CHECK-NEXT: [2,1]     .  DPPPPeER.   movw	%ax, %dx
+# CHECK-NEXT: [2,2]     .   DPPPPeER   xorw	%bx, %dx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-4.s b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-4.s
index bdd6d341166fd..ee4133a86e4e1 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-4.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-4.s
@@ -60,18 +60,19 @@ add %cx, %bx
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     addw	%cx, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [0,1]     D===eER   .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     .D===eER  .    . .   addw	%cx, %bx
-# CHECK-NEXT: [1,0]     .D====eeeER    . .   imulw	%ax, %bx
-# CHECK-NEXT: [1,1]     . D======eER   . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,2]     . D=======eER  . .   addw	%cx, %bx
-# CHECK-NEXT: [2,0]     .  D=======eeeER .   imulw	%ax, %bx
-# CHECK-NEXT: [2,1]     .  D==========eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,2]     .   D==========eER   addw	%cx, %bx
+# CHECK-NEXT: [0,1]     DPPPeER   .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     .DPPPeER  .    . .   addw	%cx, %bx
+# CHECK-NEXT: [1,0]     .DPPPPeeeER    . .   imulw	%ax, %bx
+# CHECK-NEXT: [1,1]     . DPPPPPPeER   . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,2]     . DPPPPPPPeER  . .   addw	%cx, %bx
+# CHECK-NEXT: [2,0]     .  DPPPPPPPeeeER .   imulw	%ax, %bx
+# CHECK-NEXT: [2,1]     .  DPPPPPPPPPPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,2]     .   DPPPPPPPPPPeER   addw	%cx, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-5.s b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-5.s
index 2d1397c101ff8..1a64314ee591f 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-5.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-5.s
@@ -51,11 +51,12 @@ lzcnt %ax, %bx  ## partial register stall.
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     lzcntw	%ax, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345
 
 # CHECK:      [0,0]     DeER .   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,0]     D=eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,0]     .D=eER   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,0]     DPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,0]     .DPeER   lzcntw	%ax, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-6.s b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-6.s
index 7ca046be68e38..6619e91366f2c 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-6.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-6.s
@@ -61,18 +61,19 @@ lzcnt 2(%rsp), %cx
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -     1.00    -      -      -      -      -      -     lzcntw	2(%rsp), %cx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .    . .   imull	%edx, %ecx
 # CHECK-NEXT: [0,1]     DeeeeER   .    . .   lzcntw	(%rsp), %cx
 # CHECK-NEXT: [0,2]     .DeeeeER  .    . .   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [1,0]     .D====eeeER    . .   imull	%edx, %ecx
-# CHECK-NEXT: [1,1]     . D===eeeeER   . .   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [1,2]     . D====eeeeER  . .   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [2,0]     .  D=======eeeER .   imull	%edx, %ecx
-# CHECK-NEXT: [2,1]     .  D=======eeeeER.   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [2,2]     .   D=======eeeeER   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [1,0]     .DPPPPeeeER    . .   imull	%edx, %ecx
+# CHECK-NEXT: [1,1]     . DPPPeeeeER   . .   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [1,2]     . DPPPPeeeeER  . .   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [2,0]     .  DPPPPPPPeeeER .   imull	%edx, %ecx
+# CHECK-NEXT: [2,1]     .  DPPPPPPPeeeeER.   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [2,2]     .   DPPPPPPPeeeeER   lzcntw	2(%rsp), %cx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-7.s b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-7.s
index 0cd064bcb872e..45964ee7ba5fd 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-7.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update-7.s
@@ -61,34 +61,35 @@ cmpl $1025, %eax
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -     cmpl	$1025, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          012345678
 
 # CHECK:      [0,0]     DeER .    .    .    .    .  .   sete	%r9b
 # CHECK-NEXT: [0,1]     DeER .    .    .    .    .  .   movzbl	%al, %eax
 # CHECK-NEXT: [0,2]     .DeER.    .    .    .    .  .   shll	$2, %eax
-# CHECK-NEXT: [0,3]     .D=eeeER  .    .    .    .  .   imull	%ecx, %eax
-# CHECK-NEXT: [0,4]     . D===eER .    .    .    .  .   cmpl	$1025, %eax
-# CHECK-NEXT: [1,0]     . D====eER.    .    .    .  .   sete	%r9b
-# CHECK-NEXT: [1,1]     .  D==eE-R.    .    .    .  .   movzbl	%al, %eax
-# CHECK-NEXT: [1,2]     .  D===eE-R    .    .    .  .   shll	$2, %eax
-# CHECK-NEXT: [1,3]     .   D===eeeER  .    .    .  .   imull	%ecx, %eax
-# CHECK-NEXT: [1,4]     .   D======eER .    .    .  .   cmpl	$1025, %eax
-# CHECK-NEXT: [2,0]     .    D======eER.    .    .  .   sete	%r9b
-# CHECK-NEXT: [2,1]     .    D=====eE-R.    .    .  .   movzbl	%al, %eax
-# CHECK-NEXT: [2,2]     .    .D=====eE-R    .    .  .   shll	$2, %eax
-# CHECK-NEXT: [2,3]     .    .D======eeeER  .    .  .   imull	%ecx, %eax
-# CHECK-NEXT: [2,4]     .    . D========eER .    .  .   cmpl	$1025, %eax
-# CHECK-NEXT: [3,0]     .    . D=========eER.    .  .   sete	%r9b
-# CHECK-NEXT: [3,1]     .    .  D=======eE-R.    .  .   movzbl	%al, %eax
-# CHECK-NEXT: [3,2]     .    .  D========eE-R    .  .   shll	$2, %eax
-# CHECK-NEXT: [3,3]     .    .   D========eeeER  .  .   imull	%ecx, %eax
-# CHECK-NEXT: [3,4]     .    .   D===========eER .  .   cmpl	$1025, %eax
-# CHECK-NEXT: [4,0]     .    .    D===========eER.  .   sete	%r9b
-# CHECK-NEXT: [4,1]     .    .    D==========eE-R.  .   movzbl	%al, %eax
-# CHECK-NEXT: [4,2]     .    .    .D==========eE-R  .   shll	$2, %eax
-# CHECK-NEXT: [4,3]     .    .    .D===========eeeER.   imull	%ecx, %eax
-# CHECK-NEXT: [4,4]     .    .    . D=============eER   cmpl	$1025, %eax
+# CHECK-NEXT: [0,3]     .DPeeeER  .    .    .    .  .   imull	%ecx, %eax
+# CHECK-NEXT: [0,4]     . DPPPeER .    .    .    .  .   cmpl	$1025, %eax
+# CHECK-NEXT: [1,0]     . DPPPPeER.    .    .    .  .   sete	%r9b
+# CHECK-NEXT: [1,1]     .  DPPeE-R.    .    .    .  .   movzbl	%al, %eax
+# CHECK-NEXT: [1,2]     .  DPPPeE-R    .    .    .  .   shll	$2, %eax
+# CHECK-NEXT: [1,3]     .   DPPPeeeER  .    .    .  .   imull	%ecx, %eax
+# CHECK-NEXT: [1,4]     .   DPPPPPPeER .    .    .  .   cmpl	$1025, %eax
+# CHECK-NEXT: [2,0]     .    DPPPPPPeER.    .    .  .   sete	%r9b
+# CHECK-NEXT: [2,1]     .    DPPPPPeE-R.    .    .  .   movzbl	%al, %eax
+# CHECK-NEXT: [2,2]     .    .DPPPPPeE-R    .    .  .   shll	$2, %eax
+# CHECK-NEXT: [2,3]     .    .DPPPPPPeeeER  .    .  .   imull	%ecx, %eax
+# CHECK-NEXT: [2,4]     .    . DPPPPPPPPeER .    .  .   cmpl	$1025, %eax
+# CHECK-NEXT: [3,0]     .    . DPPPPPPPPPeER.    .  .   sete	%r9b
+# CHECK-NEXT: [3,1]     .    .  DPPPPPPPeE-R.    .  .   movzbl	%al, %eax
+# CHECK-NEXT: [3,2]     .    .  DPPPPPPPPeE-R    .  .   shll	$2, %eax
+# CHECK-NEXT: [3,3]     .    .   DPPPPPPPPeeeER  .  .   imull	%ecx, %eax
+# CHECK-NEXT: [3,4]     .    .   DPPPPPPPPPPPeER .  .   cmpl	$1025, %eax
+# CHECK-NEXT: [4,0]     .    .    DPPPPPPPPPPPeER.  .   sete	%r9b
+# CHECK-NEXT: [4,1]     .    .    DPPPPPPPPPPeE-R.  .   movzbl	%al, %eax
+# CHECK-NEXT: [4,2]     .    .    .DPPPPPPPPPPeE-R  .   shll	$2, %eax
+# CHECK-NEXT: [4,3]     .    .    .DPPPPPPPPPPPeeeER.   imull	%ecx, %eax
+# CHECK-NEXT: [4,4]     .    .    . DPPPPPPPPPPPPPeER   cmpl	$1025, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update.s b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update.s
index c44ca83efb7fe..640c25d9d345e 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/partial-reg-update.s
@@ -29,11 +29,12 @@ add  %ecx, %ebx
 # CHECK-NEXT:  1      1     0.50                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   imulw	%ax, %cx
-# CHECK-NEXT: [0,1]     D===eER.   addb	%al, %cl
-# CHECK-NEXT: [0,2]     .D===eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPeER.   addb	%al, %cl
+# CHECK-NEXT: [0,2]     .DPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/pipes-fpu.s b/llvm/test/tools/llvm-mca/X86/BtVer2/pipes-fpu.s
index 55755d74f51e5..79a7dcecfeba2 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/pipes-fpu.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/pipes-fpu.s
@@ -77,6 +77,7 @@ vsqrtps     %ymm0, %ymm2
 # CHECK-NEXT:  -      -      -      -     42.00   -     2.00    -      -      -      -      -      -      -     vsqrtps	%ymm0, %ymm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/pr37790.s b/llvm/test/tools/llvm-mca/X86/BtVer2/pr37790.s
index d91de1a399035..8692b496e1e1c 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/pr37790.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/pr37790.s
@@ -27,6 +27,7 @@ stmxcsr (%rsp)
 # CHECK-NEXT:  1      1     1.00           *      U     stmxcsr	(%rsp)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789          0123456789          0123
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/rank.s b/llvm/test/tools/llvm-mca/X86/BtVer2/rank.s
index 9962ca41021d8..73a2fae945d45 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/rank.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/rank.s
@@ -70,6 +70,7 @@ add %ebx, %eax
 # CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -     addl	%ebx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
@@ -80,23 +81,23 @@ add %ebx, %eax
 # CHECK-NEXT: [0,4]     . DeER    .    . .   addl	%ebx, %eax
 # CHECK-NEXT: [0,5]     . DeER    .    . .   addl	%edx, %esi
 # CHECK-NEXT: [0,6]     .  DeER   .    . .   addl	%ebx, %eax
-# CHECK-NEXT: [0,7]     .  D=eER  .    . .   addl	%ebx, %eax
-# CHECK-NEXT: [1,0]     .   D=eER .    . .   addl	%eax, %ecx
-# CHECK-NEXT: [1,1]     .   D=eER .    . .   addl	%eax, %edx
+# CHECK-NEXT: [0,7]     .  DPeER  .    . .   addl	%ebx, %eax
+# CHECK-NEXT: [1,0]     .   DPeER .    . .   addl	%eax, %ecx
+# CHECK-NEXT: [1,1]     .   DPeER .    . .   addl	%eax, %edx
 # CHECK-NEXT: [1,2]     .    D=eER.    . .   addl	%eax, %ebx
-# CHECK-NEXT: [1,3]     .    D=eER.    . .   addl	%edx, %esi
-# CHECK-NEXT: [1,4]     .    .D=eER    . .   addl	%ebx, %eax
-# CHECK-NEXT: [1,5]     .    .D=eER    . .   addl	%edx, %esi
-# CHECK-NEXT: [1,6]     .    . D=eER   . .   addl	%ebx, %eax
-# CHECK-NEXT: [1,7]     .    . D==eER  . .   addl	%ebx, %eax
-# CHECK-NEXT: [2,0]     .    .  D==eER . .   addl	%eax, %ecx
-# CHECK-NEXT: [2,1]     .    .  D==eER . .   addl	%eax, %edx
-# CHECK-NEXT: [2,2]     .    .   D==eER. .   addl	%eax, %ebx
-# CHECK-NEXT: [2,3]     .    .   D==eER. .   addl	%edx, %esi
-# CHECK-NEXT: [2,4]     .    .    D==eER .   addl	%ebx, %eax
-# CHECK-NEXT: [2,5]     .    .    D==eER .   addl	%edx, %esi
-# CHECK-NEXT: [2,6]     .    .    .D==eER.   addl	%ebx, %eax
-# CHECK-NEXT: [2,7]     .    .    .D===eER   addl	%ebx, %eax
+# CHECK-NEXT: [1,3]     .    DPeER.    . .   addl	%edx, %esi
+# CHECK-NEXT: [1,4]     .    .DPeER    . .   addl	%ebx, %eax
+# CHECK-NEXT: [1,5]     .    .DPeER    . .   addl	%edx, %esi
+# CHECK-NEXT: [1,6]     .    . DPeER   . .   addl	%ebx, %eax
+# CHECK-NEXT: [1,7]     .    . DPPeER  . .   addl	%ebx, %eax
+# CHECK-NEXT: [2,0]     .    .  DPPeER . .   addl	%eax, %ecx
+# CHECK-NEXT: [2,1]     .    .  DPPeER . .   addl	%eax, %edx
+# CHECK-NEXT: [2,2]     .    .   DP=eER. .   addl	%eax, %ebx
+# CHECK-NEXT: [2,3]     .    .   DPPeER. .   addl	%edx, %esi
+# CHECK-NEXT: [2,4]     .    .    DPPeER .   addl	%ebx, %eax
+# CHECK-NEXT: [2,5]     .    .    DPPeER .   addl	%edx, %esi
+# CHECK-NEXT: [2,6]     .    .    .DPPeER.   addl	%ebx, %eax
+# CHECK-NEXT: [2,7]     .    .    .DPPPeER   addl	%ebx, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-1.s
index f61bce125f588..1869f3e7babf9 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-1.s
@@ -31,6 +31,7 @@ vmulps  (%rdi), %xmm1, %xmm2
 # CHECK-NEXT:  1      7     1.00    *                   vmulps	(%rdi), %xmm1, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER   .   vaddps	%xmm0, %xmm0, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-2.s
index 8b922644b7326..1c01f5be972af 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-2.s
@@ -30,6 +30,7 @@
 # CHECK-NEXT:  2      6     2.00    *                   imull	(%rdi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-3.s b/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-3.s
index 6a4bad2aa7f47..995b5e271b53f 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/read-advance-3.s
@@ -29,6 +29,7 @@
 # CHECK-NEXT:  1      1     0.50                        addq	%rdx, %r8
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DeER ..   addq	%rdi, %rsi
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-1.s
index 4788f8c46aa78..487da80d7777e 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-1.s
@@ -76,6 +76,7 @@ vaddps %xmm1, %xmm1, %xmm2
 # CHECK-NEXT:  -      -      -     1.00    -     1.00    -      -      -      -      -      -      -      -     vaddps	%xmm1, %xmm1, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DR   .   .   vxorps	%xmm0, %xmm0, %xmm0
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-2.s
index 2182118a712ac..1f614aabb87aa 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-2.s
@@ -92,6 +92,7 @@ movdqu %xmm5, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     movdqu	%xmm5, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-3.s b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-3.s
index 0d2f2160d3ecc..70ea0003af6c5 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-3.s
@@ -85,6 +85,7 @@ vmovdqu %xmm5, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovdqu	%xmm5, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-4.s b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-4.s
index d21b9815129da..6aa4b2b27042a 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-4.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-4.s
@@ -79,6 +79,7 @@ mov %edx, %eax
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     movl	%edx, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DR   .  .   xorl	%eax, %eax
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-5.s b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-5.s
index f121087250cc8..69281f76aa391 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-5.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-5.s
@@ -79,6 +79,7 @@ mov %rdx, %rax
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     movq	%rdx, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DR   .  .   xorq	%rax, %rax
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-6.s b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-6.s
index 0b6c023187090..84e0ad0c23582 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-6.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/reg-move-elimination-6.s
@@ -82,26 +82,27 @@ mov %esi, %ecx
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     movl	%esi, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DR   .    . .   xorq	%rsi, %rsi
 # CHECK-NEXT: [0,1]     DeER .    . .   addq	%rcx, %rcx
 # CHECK-NEXT: [0,2]     .DeER.    . .   addq	%rcx, %rcx
-# CHECK-NEXT: [0,3]     .D=eER    . .   addq	%rcx, %rcx
-# CHECK-NEXT: [0,4]     . D=eER   . .   addq	%rcx, %rcx
+# CHECK-NEXT: [0,3]     .DPeER    . .   addq	%rcx, %rcx
+# CHECK-NEXT: [0,4]     . DPeER   . .   addq	%rcx, %rcx
 # CHECK-NEXT: [0,5]     . D---R   . .   movl	%esi, %ecx
 # CHECK-NEXT: [1,0]     .  D---R  . .   xorq	%rsi, %rsi
 # CHECK-NEXT: [1,1]     .  DeE-R  . .   addq	%rcx, %rcx
 # CHECK-NEXT: [1,2]     .   DeE-R . .   addq	%rcx, %rcx
-# CHECK-NEXT: [1,3]     .   D=eER . .   addq	%rcx, %rcx
-# CHECK-NEXT: [1,4]     .    D=eER. .   addq	%rcx, %rcx
+# CHECK-NEXT: [1,3]     .   DPeER . .   addq	%rcx, %rcx
+# CHECK-NEXT: [1,4]     .    DPeER. .   addq	%rcx, %rcx
 # CHECK-NEXT: [1,5]     .    D---R. .   movl	%esi, %ecx
 # CHECK-NEXT: [2,0]     .    .D---R .   xorq	%rsi, %rsi
 # CHECK-NEXT: [2,1]     .    .DeE-R .   addq	%rcx, %rcx
 # CHECK-NEXT: [2,2]     .    . DeE-R.   addq	%rcx, %rcx
-# CHECK-NEXT: [2,3]     .    . D=eER.   addq	%rcx, %rcx
-# CHECK-NEXT: [2,4]     .    .  D=eER   addq	%rcx, %rcx
+# CHECK-NEXT: [2,3]     .    . DPeER.   addq	%rcx, %rcx
+# CHECK-NEXT: [2,4]     .    .  DPeER   addq	%rcx, %rcx
 # CHECK-NEXT: [2,5]     .    .  D---R   movl	%esi, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-1.s
index 2eb6dee5e99d7..4c83714edcb3a 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-1.s
@@ -68,19 +68,20 @@ vmulps %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -      -      -      -      -      -      -     vmulps	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
 # CHECK:      [0,0]     DeeeER    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D===eeER  .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,0]     .D====eeeER    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     .D=======eeER  .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [2,0]     . D========eeeER    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [2,1]     . D===========eeER  .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [3,0]     .  D============eeeER    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [3,1]     .  D===============eeER  . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [4,0]     .   D================eeeER .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [4,1]     .   D===================eeER   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPPPeeER  .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,0]     .DPPPPeeeER    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     .DPPPPPPPeeER  .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [2,0]     . DPPPPPPPPeeeER    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [2,1]     . DPPPPPPPPPPPeeER  .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [3,0]     .  DPPPPPPPPPPPPeeeER    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [3,1]     .  DPPPPPPPPPPPPPPPeeER  . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [4,0]     .   DPPPPPPPPPPPPPPPPeeeER .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [4,1]     .   DPPPPPPPPPPPPPPPPPPPeeER   vmulps	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-2.s
index 66541f9e7fad2..ece86b9be678d 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-2.s
@@ -69,19 +69,20 @@ vmulps %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -      -      -      -      -      -      -     vmulps	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
 # CHECK:      [0,0]     DeeeER    .    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D===eeER  .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,0]     .D====eeeER    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     .D=======eeER  .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [2,0]     . D========eeeER    .    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [2,1]     .    D========eeER  .    . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [3,0]     .    . D========eeeER    . .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [3,1]     .    .    D========eeER  . .   vmulps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [4,0]     .    .    . D========eeeER .   vaddps	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [4,1]     .    .    .    D========eeER   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPPPeeER  .    .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,0]     .DPPPPeeeER    .    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     .DPPPPPPPeeER  .    .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [2,0]     . DPPPPPPPPeeeER    .    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [2,1]     .    DPPPPPPPPeeER  .    . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [3,0]     .    . DPPPPPPPPeeeER    . .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [3,1]     .    .    DPPPPPPPPeeER  . .   vmulps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [4,0]     .    .    . DPPPPPPPPeeeER .   vaddps	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [4,1]     .    .    .    DPPPPPPPPeeER   vmulps	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-3.s b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-3.s
index 94a40ca24eb5c..5440fa933b349 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-3.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-3.s
@@ -77,6 +77,7 @@ idiv %eax
 # CHECK-NEXT:  -     1.00   25.00   -      -      -      -      -      -      -      -      -      -      -     idivl	%eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          01234
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-4.s b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-4.s
index 9e95042dcb5d9..47cf6482b2072 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-4.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-4.s
@@ -53,12 +53,13 @@ idiv %eax
 # CHECK-NEXT:    Max number of mappings used:      63
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeeeeeeeeeeeeER  .    .    .    .    .    .    .    .    .    . .   idivl	%eax
-# CHECK-NEXT: [1,0]     .D========================eeeeeeeeeeeeeeeeeeeeeeeeeER  .    .    .    .    . .   idivl	%eax
-# CHECK-NEXT: [2,0]     . D================================================eeeeeeeeeeeeeeeeeeeeeeeeeER   idivl	%eax
+# CHECK-NEXT: [1,0]     .DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeeeeeeeeeeeeeeER  .    .    .    .    . .   idivl	%eax
+# CHECK-NEXT: [2,0]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeeeeeeeeeeeeeeER   idivl	%eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-5.s b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-5.s
index a372b5713eb52..12b069f29f198 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-5.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/register-files-5.s
@@ -74,6 +74,7 @@
 # CHECK-NEXT:    Max number of mappings used:      0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          012345678
 
@@ -93,22 +94,22 @@
 # CHECK-NEXT: [0,13]    .    .    .  D==============eeeE--------------R   .    .    .    .  .   vaddps	%ymm0, %ymm0, %ymm14
 # CHECK-NEXT: [0,14]    .    .    .   D===============eeeE-------------R  .    .    .    .  .   vaddps	%ymm0, %ymm0, %ymm15
 # CHECK-NEXT: [0,15]    .    .    .    D======eeeE---------------------R  .    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm0
-# CHECK-NEXT: [0,16]    .    .    .    .D===============eeeE------------R .    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm3
-# CHECK-NEXT: [0,17]    .    .    .    . D================eeeE----------R .    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm4
-# CHECK-NEXT: [0,18]    .    .    .    .  D=================eeeE---------R.    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm5
-# CHECK-NEXT: [0,19]    .    .    .    .   D==================eeeE-------R.    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm6
-# CHECK-NEXT: [0,20]    .    .    .    .    D===================eeeE------R    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm7
-# CHECK-NEXT: [0,21]    .    .    .    .    .D====================eeeE----R    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm8
-# CHECK-NEXT: [0,22]    .    .    .    .    . D=====================eeeE---R   .    .    .  .   vaddps	%ymm2, %ymm0, %ymm9
-# CHECK-NEXT: [0,23]    .    .    .    .    .  D======================eeeE-R   .    .    .  .   vaddps	%ymm2, %ymm0, %ymm10
+# CHECK-NEXT: [0,16]    .    .    .    .DPPPPPPPP=======eeeE------------R .    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm3
+# CHECK-NEXT: [0,17]    .    .    .    . DPPPPPPP=========eeeE----------R .    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm4
+# CHECK-NEXT: [0,18]    .    .    .    .  DPPPPPP===========eeeE---------R.    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm5
+# CHECK-NEXT: [0,19]    .    .    .    .   DPPPPP=============eeeE-------R.    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm6
+# CHECK-NEXT: [0,20]    .    .    .    .    DPPPP===============eeeE------R    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm7
+# CHECK-NEXT: [0,21]    .    .    .    .    .DPPP=================eeeE----R    .    .    .  .   vaddps	%ymm2, %ymm0, %ymm8
+# CHECK-NEXT: [0,22]    .    .    .    .    . DPP===================eeeE---R   .    .    .  .   vaddps	%ymm2, %ymm0, %ymm9
+# CHECK-NEXT: [0,23]    .    .    .    .    .  DP=====================eeeE-R   .    .    .  .   vaddps	%ymm2, %ymm0, %ymm10
 # CHECK-NEXT: [0,24]    .    .    .    .    .   D=======================eeeER  .    .    .  .   vaddps	%ymm2, %ymm0, %ymm11
 # CHECK-NEXT: [0,25]    .    .    .    .    .    D========================eeeER.    .    .  .   vaddps	%ymm2, %ymm0, %ymm12
 # CHECK-NEXT: [0,26]    .    .    .    .    .    .D=========================eeeER   .    .  .   vaddps	%ymm2, %ymm0, %ymm13
 # CHECK-NEXT: [0,27]    .    .    .    .    .    . D==========================eeeER .    .  .   vaddps	%ymm2, %ymm0, %ymm14
 # CHECK-NEXT: [0,28]    .    .    .    .    .    .  D===========================eeeER    .  .   vaddps	%ymm2, %ymm0, %ymm15
-# CHECK-NEXT: [0,29]    .    .    .    .    .    .   D============================eeeER  .  .   vaddps	%ymm3, %ymm0, %ymm2
-# CHECK-NEXT: [0,30]    .    .    .    .    .    .    D=============================eeeER.  .   vaddps	%ymm3, %ymm0, %ymm4
-# CHECK-NEXT: [0,31]    .    .    .    .    .    .    .D==============================eeeER .   vaddps	%ymm3, %ymm0, %ymm5
+# CHECK-NEXT: [0,29]    .    .    .    .    .    .   DPPPPP=======================eeeER  .  .   vaddps	%ymm3, %ymm0, %ymm2
+# CHECK-NEXT: [0,30]    .    .    .    .    .    .    DPPPP=========================eeeER.  .   vaddps	%ymm3, %ymm0, %ymm4
+# CHECK-NEXT: [0,31]    .    .    .    .    .    .    .DPPP===========================eeeER .   vaddps	%ymm3, %ymm0, %ymm5
 # CHECK-NEXT: [0,32]    .    .    .    .    .    .    .    .    D=======================eeeER   vaddps	%ymm3, %ymm0, %ymm6
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/rmw-adc-sequence-readadvance.s b/llvm/test/tools/llvm-mca/X86/BtVer2/rmw-adc-sequence-readadvance.s
index ef25a48f4a724..4ec3658978d2b 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/rmw-adc-sequence-readadvance.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/rmw-adc-sequence-readadvance.s
@@ -52,6 +52,7 @@ adc %eax, 4(%rsp)
 # CHECK-NEXT: 2.00    -      -      -      -      -      -     1.00    -     1.00    -      -      -      -     adcl	%eax, 4(%rsp)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   addl	%eax, %eax
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/rmw-add-sequence-readadvance.s b/llvm/test/tools/llvm-mca/X86/BtVer2/rmw-add-sequence-readadvance.s
index a8da4515b315e..eca472ce20b4d 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/rmw-add-sequence-readadvance.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/rmw-add-sequence-readadvance.s
@@ -52,6 +52,7 @@ add %eax, 4(%rsp)
 # CHECK-NEXT: 1.00    -      -      -      -      -      -     1.00    -     1.00    -      -      -      -     addl	%eax, 4(%rsp)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   addl	%eax, %eax
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/stmxcsr-ldmxcsr.s b/llvm/test/tools/llvm-mca/X86/BtVer2/stmxcsr-ldmxcsr.s
index b1768957c58f4..3d1926773822f 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/stmxcsr-ldmxcsr.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/stmxcsr-ldmxcsr.s
@@ -66,26 +66,27 @@ retq
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -     1.00    -      -      -      -      -      -     retq
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345678
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    .    .  .   stmxcsr	-4(%rsp)
 # CHECK-NEXT: [0,1]     DeER .    .    .  .   movl	$-24577, %eax
 # CHECK-NEXT: [0,2]     .DeeeeER  .    .  .   andl	-4(%rsp), %eax
-# CHECK-NEXT: [0,3]     .D====eER .    .  .   movl	%eax, -8(%rsp)
-# CHECK-NEXT: [0,4]     . D===eeeER    .  .   ldmxcsr	-8(%rsp)
+# CHECK-NEXT: [0,3]     .DPPPPeER .    .  .   movl	%eax, -8(%rsp)
+# CHECK-NEXT: [0,4]     . DPPPeeeER    .  .   ldmxcsr	-8(%rsp)
 # CHECK-NEXT: [0,5]     . DeeeeE--R    .  .   retq
-# CHECK-NEXT: [1,0]     .  D=====eER   .  .   stmxcsr	-4(%rsp)
+# CHECK-NEXT: [1,0]     .  DPPPPPeER   .  .   stmxcsr	-4(%rsp)
 # CHECK-NEXT: [1,1]     .  DeE-----R   .  .   movl	$-24577, %eax
 # CHECK-NEXT: [1,2]     .   DeeeeE--R  .  .   andl	-4(%rsp), %eax
-# CHECK-NEXT: [1,3]     .   D=====eER  .  .   movl	%eax, -8(%rsp)
-# CHECK-NEXT: [1,4]     .    D====eeeER.  .   ldmxcsr	-8(%rsp)
+# CHECK-NEXT: [1,3]     .   DPPPP=eER  .  .   movl	%eax, -8(%rsp)
+# CHECK-NEXT: [1,4]     .    DPPPPeeeER.  .   ldmxcsr	-8(%rsp)
 # CHECK-NEXT: [1,5]     .    D=eeeeE--R.  .   retq
-# CHECK-NEXT: [2,0]     .    .D======eER  .   stmxcsr	-4(%rsp)
+# CHECK-NEXT: [2,0]     .    .DPPPPPPeER  .   stmxcsr	-4(%rsp)
 # CHECK-NEXT: [2,1]     .    .DeE------R  .   movl	$-24577, %eax
 # CHECK-NEXT: [2,2]     .    . DeeeeE---R .   andl	-4(%rsp), %eax
-# CHECK-NEXT: [2,3]     .    . D======eER .   movl	%eax, -8(%rsp)
-# CHECK-NEXT: [2,4]     .    .  D=====eeeER   ldmxcsr	-8(%rsp)
+# CHECK-NEXT: [2,3]     .    . DPPPPP=eER .   movl	%eax, -8(%rsp)
+# CHECK-NEXT: [2,4]     .    .  DPPPPPeeeER   ldmxcsr	-8(%rsp)
 # CHECK-NEXT: [2,5]     .    .  DeeeeE----R   retq
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/unsupported-instruction.s b/llvm/test/tools/llvm-mca/X86/BtVer2/unsupported-instruction.s
index 7d3aee5e3bf96..e4cc1b4f228b8 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/unsupported-instruction.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/unsupported-instruction.s
@@ -1,3 +1,4 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
 # RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -skip-unsupported-instructions=any -timeline %s 2>&1 | FileCheck --check-prefix=CHECK-SKIP %s
 # RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -skip-unsupported-instructions=lack-sched -timeline %s 2>&1 | FileCheck --check-prefix=CHECK-SKIP %s
 # RUN: not llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -skip-unsupported-instructions=parse-failure -timeline %s 2>&1 | FileCheck --check-prefix=CHECK-ERROR %s
@@ -6,7 +7,6 @@
 # Test checks that unsupported instructions exit with an error, unless -skip-unsupported-instructions=lack-sched is passed, in which case the remaining instructions should be analysed.
 # Additionally check that -skip-unsupported-instructions=parse-failure continues to raise the lack of scheduling information.
 
-# CHECK-SKIP: warning: found an unsupported instruction in the input assembly sequence, skipping with -skip-unsupported-instructions, note accuracy will be impacted:
 # CHECK-ERROR: error: found an unsupported instruction in the input assembly sequence, use -skip-unsupported-instructions=lack-sched to ignore these on the input.
 
 bzhi %eax, %ebx, %ecx
@@ -14,45 +14,74 @@ bzhi %eax, %ebx, %ecx
 # Supported instruction that may be analysed.
 add %eax, %eax
 
-# CHECK-SKIP: Iterations:        100
-# CHECK-SKIP: Instructions:      100
-# CHECK-SKIP: Total Cycles:      103
-# CHECK-SKIP: Total uOps:        100
-
-# CHECK-SKIP: Dispatch Width:    2
-# CHECK-SKIP: uOps Per Cycle:    0.97
-# CHECK-SKIP: IPC:               0.97
-# CHECK-SKIP: Block RThroughput: 0.5
-
-# CHECK-SKIP: Instruction Info:
-# CHECK-SKIP: [1]: #uOps
-# CHECK-SKIP: [2]: Latency
-# CHECK-SKIP: [3]: RThroughput
-# CHECK-SKIP: [4]: MayLoad
-# CHECK-SKIP: [5]: MayStore
-# CHECK-SKIP: [6]: HasSideEffects (U)
-
-# CHECK-SKIP: [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
-# CHECK-SKIP:  1      1     0.50                        addl  %eax, %eax
-
-# CHECK-SKIP: Timeline view:
-
-# CHECK-SKIP: [0,0]     DeER .    . .   addl  %eax, %eax
-# CHECK-SKIP: [1,0]     D=eER.    . .   addl  %eax, %eax
-# CHECK-SKIP: [2,0]     .D=eER    . .   addl  %eax, %eax
-# CHECK-SKIP: [3,0]     .D==eER   . .   addl  %eax, %eax
-# CHECK-SKIP: [4,0]     . D==eER  . .   addl  %eax, %eax
-# CHECK-SKIP: [5,0]     . D===eER . .   addl  %eax, %eax
-# CHECK-SKIP: [6,0]     .  D===eER. .   addl  %eax, %eax
-# CHECK-SKIP: [7,0]     .  D====eER .   addl  %eax, %eax
-# CHECK-SKIP: [8,0]     .   D====eER.   addl  %eax, %eax
-# CHECK-SKIP: [9,0]     .   D=====eER   addl  %eax, %eax
-
-# CHECK-SKIP: Average Wait times (based on the timeline view):
-# CHECK-SKIP: [0]: Executions
-# CHECK-SKIP: [1]: Average time spent waiting in a scheduler's queue
-# CHECK-SKIP: [2]: Average time spent waiting in a scheduler's queue while ready
-# CHECK-SKIP: [3]: Average time elapsed from WB until retire stage
-
-# CHECK-SKIP:       [0]    [1]    [2]    [3]
-# CHECK-SKIP: 0.     10    3.5    0.1    0.0       addl       %eax, %eax
+# CHECK-SKIP:      warning: found an unsupported instruction in the input assembly sequence, skipping with -skip-unsupported-instructions, note accuracy will be impacted:
+# CHECK-SKIP-NEXT: note: instruction: 	bzhil	%eax, %ebx, %ecx
+# CHECK-SKIP-NEXT: Iterations:        100
+# CHECK-SKIP-NEXT: Instructions:      100
+# CHECK-SKIP-NEXT: Total Cycles:      103
+# CHECK-SKIP-NEXT: Total uOps:        100
+
+# CHECK-SKIP:      Dispatch Width:    2
+# CHECK-SKIP-NEXT: uOps Per Cycle:    0.97
+# CHECK-SKIP-NEXT: IPC:               0.97
+# CHECK-SKIP-NEXT: Block RThroughput: 0.5
+
+# CHECK-SKIP:      Instruction Info:
+# CHECK-SKIP-NEXT: [1]: #uOps
+# CHECK-SKIP-NEXT: [2]: Latency
+# CHECK-SKIP-NEXT: [3]: RThroughput
+# CHECK-SKIP-NEXT: [4]: MayLoad
+# CHECK-SKIP-NEXT: [5]: MayStore
+# CHECK-SKIP-NEXT: [6]: HasSideEffects (U)
+
+# CHECK-SKIP:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-SKIP-NEXT:  1      1     0.50                        addl	%eax, %eax
+
+# CHECK-SKIP:      Resources:
+# CHECK-SKIP-NEXT: [0]   - JALU0
+# CHECK-SKIP-NEXT: [1]   - JALU1
+# CHECK-SKIP-NEXT: [2]   - JDiv
+# CHECK-SKIP-NEXT: [3]   - JFPA
+# CHECK-SKIP-NEXT: [4]   - JFPM
+# CHECK-SKIP-NEXT: [5]   - JFPU0
+# CHECK-SKIP-NEXT: [6]   - JFPU1
+# CHECK-SKIP-NEXT: [7]   - JLAGU
+# CHECK-SKIP-NEXT: [8]   - JMul
+# CHECK-SKIP-NEXT: [9]   - JSAGU
+# CHECK-SKIP-NEXT: [10]  - JSTC
+# CHECK-SKIP-NEXT: [11]  - JVALU0
+# CHECK-SKIP-NEXT: [12]  - JVALU1
+# CHECK-SKIP-NEXT: [13]  - JVIMUL
+
+# CHECK-SKIP:      Resource pressure per iteration:
+# CHECK-SKIP-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
+# CHECK-SKIP-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -
+
+# CHECK-SKIP:      Resource pressure by instruction:
+# CHECK-SKIP-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
+# CHECK-SKIP-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     addl	%eax, %eax
+
+# CHECK-SKIP:      Timeline view:
+# CHECK-SKIP-NEXT: D: Instruction dispatched
+# CHECK-SKIP-NEXT:                     012
+# CHECK-SKIP-NEXT: Index     0123456789
+
+# CHECK-SKIP:      [0,0]     DeER .    . .   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [1,0]     DPeER.    . .   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [2,0]     .DPeER    . .   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [3,0]     .DPPeER   . .   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [4,0]     . DPPeER  . .   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [5,0]     . DPPPeER . .   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [6,0]     .  DPPPeER. .   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [7,0]     .  DPPPPeER .   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [8,0]     .   DPPPPeER.   addl	%eax, %eax
+# CHECK-SKIP-NEXT: [9,0]     .   DPPPPPeER   addl	%eax, %eax
+
+# CHECK-SKIP:      Average Wait times (based on the timeline view):
+# CHECK-SKIP-NEXT: [0]: Executions
+# CHECK-SKIP-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-SKIP-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-SKIP-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK-SKIP:            [0]    [1]    [2]    [3]
+# CHECK-SKIP-NEXT: 0.     10    3.5    0.1    0.0       addl	%eax, %eax
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/vbroadcast-operand-latency.s b/llvm/test/tools/llvm-mca/X86/BtVer2/vbroadcast-operand-latency.s
index f0a40ce9af011..72d99ed91861f 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/vbroadcast-operand-latency.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/vbroadcast-operand-latency.s
@@ -52,15 +52,16 @@ vbroadcastss (%rax), %ymm0
 # CHECK-NEXT:  -      -      -     2.00   2.00   1.00   1.00   1.00    -      -      -      -      -      -     vbroadcastss	(%rax), %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    .   .   leaq	8(%rsp,%rdi,2), %rax
-# CHECK-NEXT: [0,1]     .D=eeeeeeER   .   vbroadcastss	(%rax), %ymm0
+# CHECK-NEXT: [0,1]     .DPeeeeeeER   .   vbroadcastss	(%rax), %ymm0
 # CHECK-NEXT: [1,0]     . DeeE----R   .   leaq	8(%rsp,%rdi,2), %rax
-# CHECK-NEXT: [1,1]     .  D=eeeeeeER .   vbroadcastss	(%rax), %ymm0
+# CHECK-NEXT: [1,1]     .  DPeeeeeeER .   vbroadcastss	(%rax), %ymm0
 # CHECK-NEXT: [2,0]     .   DeeE----R .   leaq	8(%rsp,%rdi,2), %rax
-# CHECK-NEXT: [2,1]     .    D=eeeeeeER   vbroadcastss	(%rax), %ymm0
+# CHECK-NEXT: [2,1]     .    DPeeeeeeER   vbroadcastss	(%rax), %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/vec-logic-read-after-ld-1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/vec-logic-read-after-ld-1.s
index 1c5c8cf2eb79e..16bd9b5ed53b5 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/vec-logic-read-after-ld-1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/vec-logic-read-after-ld-1.s
@@ -27,6 +27,7 @@ vandps (%rdi), %xmm1, %xmm2
 # CHECK-NEXT:  1      6     1.00    *                   vandps	(%rdi), %xmm1, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeER  .   vaddps	%xmm0, %xmm0, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/vec-logic-read-after-ld-2.s b/llvm/test/tools/llvm-mca/X86/BtVer2/vec-logic-read-after-ld-2.s
index 7e76fcc1df8c7..d0c2ad0770319 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/vec-logic-read-after-ld-2.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/vec-logic-read-after-ld-2.s
@@ -27,6 +27,7 @@ vandps (%rdi), %ymm1, %ymm2
 # CHECK-NEXT:  2      6     2.00    *                   vandps	(%rdi), %ymm1, %ymm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER   .   vaddps	%ymm0, %ymm0, %ymm1
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/xadd.s b/llvm/test/tools/llvm-mca/X86/BtVer2/xadd.s
index 691f530be7b07..7cc2d626929e5 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/xadd.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/xadd.s
@@ -73,19 +73,20 @@ imul %ecx, %ecx
 # CHECK-NEXT:  -     1.00    -      -      -      -      -      -     1.00    -      -      -      -      -     imull	%ecx, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123
 
 # CHECK:      [0,0]     DeeeeeeeeeeeER .    .  .   xaddl	%ecx, (%rsp)
-# CHECK-NEXT: [0,1]     . D=eE-------R .    .  .   addl	%ecx, %ecx
-# CHECK-NEXT: [0,2]     . D==eE-------R.    .  .   addl	%ecx, %ecx
-# CHECK-NEXT: [0,3]     .  D==eeeE----R.    .  .   imull	%ecx, %ecx
-# CHECK-NEXT: [0,4]     .  D=====eeeE--R    .  .   imull	%ecx, %ecx
-# CHECK-NEXT: [1,0]     .   D====eeeeeeeeeeeER .   xaddl	%ecx, (%rsp)
-# CHECK-NEXT: [1,1]     .    .D=====eE-------R .   addl	%ecx, %ecx
-# CHECK-NEXT: [1,2]     .    .D======eE-------R.   addl	%ecx, %ecx
-# CHECK-NEXT: [1,3]     .    . D======eeeE----R.   imull	%ecx, %ecx
-# CHECK-NEXT: [1,4]     .    . D=========eeeE--R   imull	%ecx, %ecx
+# CHECK-NEXT: [0,1]     . DPeE-------R .    .  .   addl	%ecx, %ecx
+# CHECK-NEXT: [0,2]     . DPPeE-------R.    .  .   addl	%ecx, %ecx
+# CHECK-NEXT: [0,3]     .  DPPeeeE----R.    .  .   imull	%ecx, %ecx
+# CHECK-NEXT: [0,4]     .  DPPPPPeeeE--R    .  .   imull	%ecx, %ecx
+# CHECK-NEXT: [1,0]     .   DPPPPeeeeeeeeeeeER .   xaddl	%ecx, (%rsp)
+# CHECK-NEXT: [1,1]     .    .DPPPPPeE-------R .   addl	%ecx, %ecx
+# CHECK-NEXT: [1,2]     .    .DPPPPPPeE-------R.   addl	%ecx, %ecx
+# CHECK-NEXT: [1,3]     .    . DPPPPPPeeeE----R.   imull	%ecx, %ecx
+# CHECK-NEXT: [1,4]     .    . DPPPPPPPPPeeeE--R   imull	%ecx, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -157,19 +158,20 @@ imul %ecx, %ecx
 # CHECK-NEXT:  -     1.00    -      -      -      -      -      -     1.00    -      -      -      -      -     imull	%ecx, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeeeER .    .    .    . .   lock		xaddl	%ecx, (%rsp)
-# CHECK-NEXT: [0,1]     . D=========eE----R .    .    .    . .   addl	%ecx, %ecx
-# CHECK-NEXT: [0,2]     . D==========eE----R.    .    .    . .   addl	%ecx, %ecx
-# CHECK-NEXT: [0,3]     .  D==========eeeE-R.    .    .    . .   imull	%ecx, %ecx
-# CHECK-NEXT: [0,4]     .  D=============eeeER   .    .    . .   imull	%ecx, %ecx
-# CHECK-NEXT: [1,0]     .   D============eeeeeeeeeeeeeeeeER. .   lock		xaddl	%ecx, (%rsp)
-# CHECK-NEXT: [1,1]     .    .D=====================eE----R. .   addl	%ecx, %ecx
-# CHECK-NEXT: [1,2]     .    .D======================eE----R .   addl	%ecx, %ecx
-# CHECK-NEXT: [1,3]     .    . D======================eeeE-R .   imull	%ecx, %ecx
-# CHECK-NEXT: [1,4]     .    . D=========================eeeER   imull	%ecx, %ecx
+# CHECK-NEXT: [0,1]     . DPPPPPPPPPeE----R .    .    .    . .   addl	%ecx, %ecx
+# CHECK-NEXT: [0,2]     . DPPPPPPPPPPeE----R.    .    .    . .   addl	%ecx, %ecx
+# CHECK-NEXT: [0,3]     .  DPPPPPPPPPPeeeE-R.    .    .    . .   imull	%ecx, %ecx
+# CHECK-NEXT: [0,4]     .  DPPPPPPPPPPPPPeeeER   .    .    . .   imull	%ecx, %ecx
+# CHECK-NEXT: [1,0]     .   DPPPPPPPPPPPPeeeeeeeeeeeeeeeeER. .   lock		xaddl	%ecx, (%rsp)
+# CHECK-NEXT: [1,1]     .    .DPPPPPPPPPPPPPPPPPPPPPeE----R. .   addl	%ecx, %ecx
+# CHECK-NEXT: [1,2]     .    .DPPPPPPPPPPPPPPPPPPPPPPeE----R .   addl	%ecx, %ecx
+# CHECK-NEXT: [1,3]     .    . DPPPPPPPPPPPPPPPPPPPPPPeeeE-R .   imull	%ecx, %ecx
+# CHECK-NEXT: [1,4]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPeeeER   imull	%ecx, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/xchg.s b/llvm/test/tools/llvm-mca/X86/BtVer2/xchg.s
index 2620fa871be53..7388c3c0a1b06 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/xchg.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/xchg.s
@@ -61,19 +61,20 @@ imul %ecx, %ecx
 # CHECK-NEXT:  -     1.00    -      -      -      -      -      -     1.00    -      -      -      -      -     imull	%ecx, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeeeER .    .    .    . .   xchgl	%ecx, (%rsp)
-# CHECK-NEXT: [0,1]     .D==========eE----R .    .    .    . .   addl	%ecx, %ecx
-# CHECK-NEXT: [0,2]     . D==========eE----R.    .    .    . .   addl	%ecx, %ecx
-# CHECK-NEXT: [0,3]     . D===========eeeE-R.    .    .    . .   imull	%ecx, %ecx
-# CHECK-NEXT: [0,4]     .  D=============eeeER   .    .    . .   imull	%ecx, %ecx
-# CHECK-NEXT: [1,0]     .   D============eeeeeeeeeeeeeeeeER. .   xchgl	%ecx, (%rsp)
-# CHECK-NEXT: [1,1]     .    D======================eE----R. .   addl	%ecx, %ecx
-# CHECK-NEXT: [1,2]     .    .D======================eE----R .   addl	%ecx, %ecx
-# CHECK-NEXT: [1,3]     .    .D=======================eeeE-R .   imull	%ecx, %ecx
-# CHECK-NEXT: [1,4]     .    . D=========================eeeER   imull	%ecx, %ecx
+# CHECK-NEXT: [0,1]     .DPPPPPPPPPPeE----R .    .    .    . .   addl	%ecx, %ecx
+# CHECK-NEXT: [0,2]     . DPPPPPPPPPPeE----R.    .    .    . .   addl	%ecx, %ecx
+# CHECK-NEXT: [0,3]     . DPPPPPPPPPPPeeeE-R.    .    .    . .   imull	%ecx, %ecx
+# CHECK-NEXT: [0,4]     .  DPPPPPPPPPPPPPeeeER   .    .    . .   imull	%ecx, %ecx
+# CHECK-NEXT: [1,0]     .   DPPPPPPPPPPPPeeeeeeeeeeeeeeeeER. .   xchgl	%ecx, (%rsp)
+# CHECK-NEXT: [1,1]     .    DPPPPPPPPPPPPPPPPPPPPPPeE----R. .   addl	%ecx, %ecx
+# CHECK-NEXT: [1,2]     .    .DPPPPPPPPPPPPPPPPPPPPPPeE----R .   addl	%ecx, %ecx
+# CHECK-NEXT: [1,3]     .    .DPPPPPPPPPPPPPPPPPPPPPPPeeeE-R .   imull	%ecx, %ecx
+# CHECK-NEXT: [1,4]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPeeeER   imull	%ecx, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s b/llvm/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s
index b5a8bb0521b37..4ea5459229f78 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s
@@ -88,6 +88,7 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -     1.00   1.00   1.00   1.00    -      -      -      -      -      -      -     vblendps	$2, %ymm1, %ymm2, %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -165,6 +166,7 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -     1.00   1.00   1.00   1.00    -      -      -      -      -      -      -     vblendpd	$2, %ymm1, %ymm2, %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123
 # CHECK-NEXT: Index     0123456789
 
@@ -240,6 +242,7 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -      -      -      -      -      -      -     vandnps	%ymm2, %ymm2, %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER   .   vaddps	%ymm0, %ymm1, %ymm2
@@ -310,6 +313,7 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -      -      -      -      -      -      -     vandnps	%ymm2, %ymm2, %ymm3
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER   .   vaddps	%ymm0, %ymm1, %ymm2
@@ -380,6 +384,7 @@ vaddps  %ymm1, %ymm1, %ymm0
 # CHECK-NEXT:  -      -      -     2.00    -     2.00    -      -      -      -      -      -      -      -     vaddps	%ymm1, %ymm1, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/BtVer2/zero-idioms.s
index eb41f7acc9589..e15440a48e749 100644
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/zero-idioms.s
@@ -288,6 +288,7 @@ vpxor  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpxor	%xmm3, %xmm3, %xmm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456
 # CHECK-NEXT: Index     0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-1.s b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-1.s
index 9930d08cf2e1f..b0e28f8139d72 100644
--- a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-1.s
+++ b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-1.s
@@ -58,21 +58,22 @@
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps	%xmm4, %xmm5, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   vmulps	%zmm0, %zmm1, %zmm2
 # CHECK-NEXT: [0,1]     DeeeE--R  .    .    .    ..   vaddps	%xmm1, %xmm1, %xmm2
-# CHECK-NEXT: [0,2]     D===eeeeeER    .    .    ..   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [0,3]     D========eeeER .    .    ..   vaddps	%xmm4, %xmm5, %xmm6
-# CHECK-NEXT: [0,4]     .D==========eeeeeER .    ..   vmulps	%xmm6, %xmm3, %xmm4
-# CHECK-NEXT: [0,5]     .D===============eeeER   ..   vaddps	%xmm4, %xmm5, %xmm0
-# CHECK-NEXT: [1,0]     .D==================eeeeeER   vmulps	%zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [0,2]     DPPPeeeeeER    .    .    ..   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .    ..   vaddps	%xmm4, %xmm5, %xmm6
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPeeeeeER .    ..   vmulps	%xmm6, %xmm3, %xmm4
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPeeeER   ..   vaddps	%xmm4, %xmm5, %xmm0
+# CHECK-NEXT: [1,0]     .DPPPPPPPPPPPPPPPPPPeeeeeER   vmulps	%zmm0, %zmm1, %zmm2
 # CHECK-NEXT: [1,1]     .DeeeE--------------------R   vaddps	%xmm1, %xmm1, %xmm2
-# CHECK-NEXT: [1,2]     . D==eeeeeE---------------R   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [1,3]     . D=======eeeE------------R   vaddps	%xmm4, %xmm5, %xmm6
-# CHECK-NEXT: [1,4]     . D==========eeeeeE-------R   vmulps	%xmm6, %xmm3, %xmm4
-# CHECK-NEXT: [1,5]     . D===============eeeE----R   vaddps	%xmm4, %xmm5, %xmm0
+# CHECK-NEXT: [1,2]     . DPPeeeeeE---------------R   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     . DPPPPPPPeeeE------------R   vaddps	%xmm4, %xmm5, %xmm6
+# CHECK-NEXT: [1,4]     . DPPPPPPPPPPeeeeeE-------R   vmulps	%xmm6, %xmm3, %xmm4
+# CHECK-NEXT: [1,5]     . DPPPPPPPPPPPPPPPeeeE----R   vaddps	%xmm4, %xmm5, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-2.s b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-2.s
index de72dafda2fde..2dfdb907ac046 100644
--- a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-2.s
@@ -58,21 +58,22 @@
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps	%xmm4, %xmm5, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   vmulps	%zmm0, %zmm1, %zmm2
 # CHECK-NEXT: [0,1]     DeeeE--R  .    .    .    ..   vaddps	%ymm1, %ymm1, %ymm2
-# CHECK-NEXT: [0,2]     D===eeeeeER    .    .    ..   vmulps	%zmm2, %zmm3, %zmm4
-# CHECK-NEXT: [0,3]     D========eeeER .    .    ..   vaddps	%xmm4, %xmm5, %xmm6
-# CHECK-NEXT: [0,4]     .D==========eeeeeER .    ..   vmulps	%xmm6, %xmm3, %xmm4
-# CHECK-NEXT: [0,5]     .D===============eeeER   ..   vaddps	%xmm4, %xmm5, %xmm0
-# CHECK-NEXT: [1,0]     .D==================eeeeeER   vmulps	%zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [0,2]     DPPPeeeeeER    .    .    ..   vmulps	%zmm2, %zmm3, %zmm4
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .    ..   vaddps	%xmm4, %xmm5, %xmm6
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPeeeeeER .    ..   vmulps	%xmm6, %xmm3, %xmm4
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPeeeER   ..   vaddps	%xmm4, %xmm5, %xmm0
+# CHECK-NEXT: [1,0]     .DPPPPPPPPPPPPPPPPPPeeeeeER   vmulps	%zmm0, %zmm1, %zmm2
 # CHECK-NEXT: [1,1]     .DeeeE--------------------R   vaddps	%ymm1, %ymm1, %ymm2
-# CHECK-NEXT: [1,2]     . D==eeeeeE---------------R   vmulps	%zmm2, %zmm3, %zmm4
-# CHECK-NEXT: [1,3]     . D=======eeeE------------R   vaddps	%xmm4, %xmm5, %xmm6
-# CHECK-NEXT: [1,4]     . D==========eeeeeE-------R   vmulps	%xmm6, %xmm3, %xmm4
-# CHECK-NEXT: [1,5]     . D===============eeeE----R   vaddps	%xmm4, %xmm5, %xmm0
+# CHECK-NEXT: [1,2]     . DPPeeeeeE---------------R   vmulps	%zmm2, %zmm3, %zmm4
+# CHECK-NEXT: [1,3]     . DPPPPPPPeeeE------------R   vaddps	%xmm4, %xmm5, %xmm6
+# CHECK-NEXT: [1,4]     . DPPPPPPPPPPeeeeeE-------R   vmulps	%xmm6, %xmm3, %xmm4
+# CHECK-NEXT: [1,5]     . DPPPPPPPPPPPPPPPeeeE----R   vaddps	%xmm4, %xmm5, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-3.s b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-3.s
index 5495b97b3367f..cb0ff4090c382 100644
--- a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-3.s
+++ b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-3.s
@@ -58,21 +58,22 @@
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps	%xmm4, %xmm20, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   vmulps	%zmm0, %zmm1, %zmm2
 # CHECK-NEXT: [0,1]     DeeeE--R  .    .    .    ..   vaddps	%xmm16, %xmm17, %xmm2
-# CHECK-NEXT: [0,2]     D===eeeeeER    .    .    ..   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [0,3]     D========eeeER .    .    ..   vaddps	%xmm4, %xmm18, %xmm6
-# CHECK-NEXT: [0,4]     .D==========eeeeeER .    ..   vmulps	%xmm6, %xmm19, %xmm4
-# CHECK-NEXT: [0,5]     .D===============eeeER   ..   vaddps	%xmm4, %xmm20, %xmm0
-# CHECK-NEXT: [1,0]     .D==================eeeeeER   vmulps	%zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [0,2]     DPPPeeeeeER    .    .    ..   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .    ..   vaddps	%xmm4, %xmm18, %xmm6
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPeeeeeER .    ..   vmulps	%xmm6, %xmm19, %xmm4
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPeeeER   ..   vaddps	%xmm4, %xmm20, %xmm0
+# CHECK-NEXT: [1,0]     .DPPPPPPPPPPPPPPPPPPeeeeeER   vmulps	%zmm0, %zmm1, %zmm2
 # CHECK-NEXT: [1,1]     .DeeeE--------------------R   vaddps	%xmm16, %xmm17, %xmm2
-# CHECK-NEXT: [1,2]     . D==eeeeeE---------------R   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [1,3]     . D=======eeeE------------R   vaddps	%xmm4, %xmm18, %xmm6
-# CHECK-NEXT: [1,4]     . D==========eeeeeE-------R   vmulps	%xmm6, %xmm19, %xmm4
-# CHECK-NEXT: [1,5]     . D===============eeeE----R   vaddps	%xmm4, %xmm20, %xmm0
+# CHECK-NEXT: [1,2]     . DPPeeeeeE---------------R   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     . DPPPPPPPeeeE------------R   vaddps	%xmm4, %xmm18, %xmm6
+# CHECK-NEXT: [1,4]     . DPPPPPPPPPPeeeeeE-------R   vmulps	%xmm6, %xmm19, %xmm4
+# CHECK-NEXT: [1,5]     . DPPPPPPPPPPPPPPPeeeE----R   vaddps	%xmm4, %xmm20, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-1.s b/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-1.s
index 2a9ef74569f2b..0af212e6b24df 100644
--- a/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-1.s
+++ b/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-1.s
@@ -58,21 +58,22 @@
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps	%ymm4, %ymm5, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .    ..   vmulps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: [0,1]     DeeeE--R  .    .    .    ..   vfrczpd	%xmm1, %xmm2
-# CHECK-NEXT: [0,2]     D===eeeeeER    .    .    ..   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [0,3]     D========eeeER .    .    ..   vaddps	%ymm4, %ymm5, %ymm6
-# CHECK-NEXT: [0,4]     .D==========eeeeeER .    ..   vmulps	%ymm6, %ymm3, %ymm4
-# CHECK-NEXT: [0,5]     .D===============eeeER   ..   vaddps	%ymm4, %ymm5, %ymm0
-# CHECK-NEXT: [1,0]     .D==================eeeeeER   vmulps	%ymm0, %ymm1, %ymm2
+# CHECK-NEXT: [0,2]     DPPPeeeeeER    .    .    ..   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     DPPPPPPPPeeeER .    .    ..   vaddps	%ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [0,4]     .DPPPPPPPPPPeeeeeER .    ..   vmulps	%ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPPPeeeER   ..   vaddps	%ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,0]     .DPPPPPPPPPPPPPPPPPPeeeeeER   vmulps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: [1,1]     .DeeeE--------------------R   vfrczpd	%xmm1, %xmm2
-# CHECK-NEXT: [1,2]     . D==eeeeeE---------------R   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [1,3]     . D=======eeeE------------R   vaddps	%ymm4, %ymm5, %ymm6
-# CHECK-NEXT: [1,4]     . D==========eeeeeE-------R   vmulps	%ymm6, %ymm3, %ymm4
-# CHECK-NEXT: [1,5]     . D===============eeeE----R   vaddps	%ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,2]     . DPPeeeeeE---------------R   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     . DPPPPPPPeeeE------------R   vaddps	%ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [1,4]     . DPPPPPPPPPPeeeeeE-------R   vmulps	%ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [1,5]     . DPPPPPPPPPPPPPPPeeeE----R   vaddps	%ymm4, %ymm5, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-2.s b/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-2.s
index 915499f418488..2f983f5360b8d 100644
--- a/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-2.s
@@ -58,21 +58,22 @@
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps	%ymm4, %ymm5, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
 # CHECK:      [0,0]     DeeeeeER  .    .    .   .   vmulps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: [0,1]     DeE----R  .    .    .   .   vpermil2pd	$15, %xmm3, %xmm5, %xmm1, %xmm2
-# CHECK-NEXT: [0,2]     D=eeeeeER .    .    .   .   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [0,3]     D======eeeER   .    .   .   vaddps	%ymm4, %ymm5, %ymm6
-# CHECK-NEXT: [0,4]     .D========eeeeeER   .   .   vmulps	%ymm6, %ymm3, %ymm4
-# CHECK-NEXT: [0,5]     .D=============eeeER.   .   vaddps	%ymm4, %ymm5, %ymm0
-# CHECK-NEXT: [1,0]     .D================eeeeeER   vmulps	%ymm0, %ymm1, %ymm2
+# CHECK-NEXT: [0,2]     DPeeeeeER .    .    .   .   vmulps	%ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     DPPPPPPeeeER   .    .   .   vaddps	%ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [0,4]     .DPPPPPPPPeeeeeER   .   .   vmulps	%ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [0,5]     .DPPPPPPPPPPPPPeeeER.   .   vaddps	%ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,0]     .DPPPPPPPPPPPPPPPPeeeeeER   vmulps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: [1,1]     .DeE--------------------R   vpermil2pd	$15, %xmm3, %xmm5, %xmm1, %xmm2
 # CHECK-NEXT: [1,2]     . DeeeeeE---------------R   vmulps	%ymm2, %ymm3, %ymm4
-# CHECK-NEXT: [1,3]     . D=====eeeE------------R   vaddps	%ymm4, %ymm5, %ymm6
-# CHECK-NEXT: [1,4]     . D========eeeeeE-------R   vmulps	%ymm6, %ymm3, %ymm4
-# CHECK-NEXT: [1,5]     . D=============eeeE----R   vaddps	%ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,3]     . DPPPPPeeeE------------R   vaddps	%ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [1,4]     . DPPPPPPPPeeeeeE-------R   vmulps	%ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [1,5]     . DPPPPPPPPPPPPPeeeE----R   vaddps	%ymm4, %ymm5, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/adcx-adox-read-advance.s b/llvm/test/tools/llvm-mca/X86/Haswell/adcx-adox-read-advance.s
index d418b6176c993..9b1150f379c7f 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/adcx-adox-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/adcx-adox-read-advance.s
@@ -55,11 +55,12 @@ adox (%rdi), %rcx
 # CHECK-NEXT:  -      -     0.50   0.50   0.50   0.50    -     0.50   0.50    -     adcxq	(%rdi), %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER..   adcxq	(%rdi), %rcx
-# CHECK-NEXT: [1,0]     .D=eeeeeeeER   adcxq	(%rdi), %rcx
+# CHECK-NEXT: [1,0]     .DPeeeeeeeER   adcxq	(%rdi), %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -114,11 +115,12 @@ adox (%rdi), %rcx
 # CHECK-NEXT:  -      -     0.50   0.50   0.50   0.50    -     0.50   0.50    -     adoxq	(%rdi), %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER..   adoxq	(%rdi), %rcx
-# CHECK-NEXT: [1,0]     .D=eeeeeeeER   adoxq	(%rdi), %rcx
+# CHECK-NEXT: [1,0]     .DPeeeeeeeER   adoxq	(%rdi), %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/cmpxchg16b.s b/llvm/test/tools/llvm-mca/X86/Haswell/cmpxchg16b.s
index 7bd095670d671..ba5059eee59ec 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/cmpxchg16b.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/cmpxchg16b.s
@@ -60,12 +60,13 @@ cmpxchg16b (%rsi)
 # CHECK-NEXT:  -      -     2.00   6.00   0.66   0.67   1.00   4.00   4.00   0.67   cmpxchg16b	(%rsi)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          012345678
 
 # CHECK:      [0,0]     DeeeeeeeeeeeeeeeeeeeeeeER.    .    .    .    .    .    .    .    .  .   cmpxchg16b	(%rsi)
-# CHECK-NEXT: [1,0]     .    D=================eeeeeeeeeeeeeeeeeeeeeeER   .    .    .    .  .   cmpxchg16b	(%rsi)
-# CHECK-NEXT: [2,0]     .    .    D==================================eeeeeeeeeeeeeeeeeeeeeeER   cmpxchg16b	(%rsi)
+# CHECK-NEXT: [1,0]     .    DPPPPPPPPPPPPPPPPPeeeeeeeeeeeeeeeeeeeeeeER   .    .    .    .  .   cmpxchg16b	(%rsi)
+# CHECK-NEXT: [2,0]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeeeeeeeeeeeER   cmpxchg16b	(%rsi)
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/independent-load-stores.s b/llvm/test/tools/llvm-mca/X86/Haswell/independent-load-stores.s
index a5ad56b6a7496..1806f79a5b929 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/independent-load-stores.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/independent-load-stores.s
@@ -81,6 +81,7 @@
 # ALL-NEXT:       -      -     0.50    -     0.66   0.67   1.00   0.50    -     0.67   addq	$44, 640(%r14)
 
 # ALL:           Timeline view:
+# ALL-NEXT:      D: Instruction dispatched
 
 # NOALIAS-NEXT:                      012345678
 # NOALIAS-NEXT:  Index     0123456789
@@ -100,15 +101,15 @@
 # NOALIAS-NEXT:  [0,9]     .    .   DeeeeeeeER   addq	$44, 640(%r14)
 
 # YESALIAS:      [0,0]     DeeeeeeeER.    .    .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 64(%r14)
-# YESALIAS-NEXT: [0,1]     .D======eeeeeeeER   .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
-# YESALIAS-NEXT: [0,2]     . D============eeeeeeeER .    .    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
-# YESALIAS-NEXT: [0,3]     .  D==================eeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 256(%r14)
-# YESALIAS-NEXT: [0,4]     .   D========================eeeeeeeER  .    .    .    .    .    .    . .   addq	$44, 320(%r14)
-# YESALIAS-NEXT: [0,5]     .    D==============================eeeeeeeER.    .    .    .    .    . .   addq	$44, 384(%r14)
-# YESALIAS-NEXT: [0,6]     .    .D====================================eeeeeeeER   .    .    .    . .   addq	$44, 448(%r14)
-# YESALIAS-NEXT: [0,7]     .    . D==========================================eeeeeeeER .    .    . .   addq	$44, 512(%r14)
-# YESALIAS-NEXT: [0,8]     .    .  D================================================eeeeeeeER    . .   addq	$44, 576(%r14)
-# YESALIAS-NEXT: [0,9]     .    .   D======================================================eeeeeeeER   addq	$44, 640(%r14)
+# YESALIAS-NEXT: [0,1]     .DPPPPPPeeeeeeeER   .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
+# YESALIAS-NEXT: [0,2]     . DPPPPPPPPPPPPeeeeeeeER .    .    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
+# YESALIAS-NEXT: [0,3]     .  DPPPPPPPPPPPPPPPPPPeeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 256(%r14)
+# YESALIAS-NEXT: [0,4]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER  .    .    .    .    .    .    . .   addq	$44, 320(%r14)
+# YESALIAS-NEXT: [0,5]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER.    .    .    .    .    . .   addq	$44, 384(%r14)
+# YESALIAS-NEXT: [0,6]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   .    .    .    . .   addq	$44, 448(%r14)
+# YESALIAS-NEXT: [0,7]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER .    .    . .   addq	$44, 512(%r14)
+# YESALIAS-NEXT: [0,8]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   addq	$44, 576(%r14)
+# YESALIAS-NEXT: [0,9]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   addq	$44, 640(%r14)
 
 # ALL:           Average Wait times (based on the timeline view):
 # ALL-NEXT:      [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/mulx-hi-read-advance.s b/llvm/test/tools/llvm-mca/X86/Haswell/mulx-hi-read-advance.s
index 424e67a0d7f47..5375c78d53cec 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/mulx-hi-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/mulx-hi-read-advance.s
@@ -59,11 +59,12 @@ add %rax, %rax
 # CHECK-NEXT:  -      -     1.00    -      -      -      -      -      -      -     addl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeER   mulxl	(%rdi), %eax, %ecx
-# CHECK-NEXT: [0,1]     .D=======eER   addl	%eax, %eax
+# CHECK-NEXT: [0,1]     .DPPPPPPPeER   addl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -122,11 +123,12 @@ add %rax, %rax
 # CHECK-NEXT:  -      -      -      -      -      -      -     1.00    -      -     addq	%rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeER   mulxq	(%rdi), %rax, %rcx
-# CHECK-NEXT: [0,1]     .D=======eER   addq	%rax, %rax
+# CHECK-NEXT: [0,1]     .DPPPPPPPeER   addq	%rax, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/mulx-lo-reg-use.s b/llvm/test/tools/llvm-mca/X86/Haswell/mulx-lo-reg-use.s
index 180b97d688db4..cbc745a1d076b 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/mulx-lo-reg-use.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/mulx-lo-reg-use.s
@@ -53,10 +53,11 @@ mulxq %rax, %rax, %rcx
 # CHECK-NEXT:  -      -     0.50   1.00    -      -      -     0.50   1.00    -     mulxl	%eax, %eax, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   mulxl	%eax, %eax, %ecx
-# CHECK-NEXT: [1,0]     .D==eeeeER   mulxl	%eax, %eax, %ecx
+# CHECK-NEXT: [1,0]     .DPPeeeeER   mulxl	%eax, %eax, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -111,10 +112,11 @@ mulxq %rax, %rax, %rcx
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     1.00    -     mulxq	%rax, %rax, %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   mulxq	%rax, %rax, %rcx
-# CHECK-NEXT: [1,0]     .D==eeeeER   mulxq	%rax, %rax, %rcx
+# CHECK-NEXT: [1,0]     .DPPeeeeER   mulxq	%rax, %rax, %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/mulx-read-advance.s b/llvm/test/tools/llvm-mca/X86/Haswell/mulx-read-advance.s
index 8203ce27c44aa..909bf9cf2fa3f 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/mulx-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/mulx-read-advance.s
@@ -55,11 +55,12 @@ mulxq (%rdi), %rax, %rdx
 # CHECK-NEXT:  -      -     0.50   1.00   0.50   0.50    -     0.50   1.00    -     mulxl	(%rdi), %eax, %edx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .   mulxl	(%rdi), %eax, %edx
-# CHECK-NEXT: [1,0]     . D==eeeeeeeeeER   mulxl	(%rdi), %eax, %edx
+# CHECK-NEXT: [1,0]     . DPPeeeeeeeeeER   mulxl	(%rdi), %eax, %edx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -114,11 +115,12 @@ mulxq (%rdi), %rax, %rdx
 # CHECK-NEXT:  -      -      -     1.00   0.50   0.50    -      -     1.00    -     mulxq	(%rdi), %rax, %rdx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012345
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeER   .   mulxq	(%rdi), %rax, %rdx
-# CHECK-NEXT: [1,0]     .D===eeeeeeeeeER   mulxq	(%rdi), %rax, %rdx
+# CHECK-NEXT: [1,0]     .DPPPeeeeeeeeeER   mulxq	(%rdi), %rax, %rdx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/mulx-same-regs.s b/llvm/test/tools/llvm-mca/X86/Haswell/mulx-same-regs.s
index 4cd496144c4b7..2bc129ba6ce52 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/mulx-same-regs.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/mulx-same-regs.s
@@ -56,11 +56,12 @@ mulxq %rax, %rax, %rax
 # CHECK-NEXT:  -      -     0.50   1.00    -      -      -     0.50   1.00    -     mulxl	%eax, %eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   mulxl	%eax, %eax, %eax
-# CHECK-NEXT: [1,0]     .D===eeeeER   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [1,0]     .DPPPeeeeER   mulxl	%eax, %eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -115,11 +116,12 @@ mulxq %rax, %rax, %rax
 # CHECK-NEXT:  -      -      -     1.00    -      -      -      -     1.00    -     mulxq	%rax, %rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   mulxq	%rax, %rax, %rax
-# CHECK-NEXT: [1,0]     .D===eeeeER   mulxq	%rax, %rax, %rax
+# CHECK-NEXT: [1,0]     .DPPPeeeeER   mulxq	%rax, %rax, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/stmxcsr-ldmxcsr.s b/llvm/test/tools/llvm-mca/X86/Haswell/stmxcsr-ldmxcsr.s
index 011dfe61017ea..8771be302e5d5 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/stmxcsr-ldmxcsr.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/stmxcsr-ldmxcsr.s
@@ -62,26 +62,27 @@ retq
 # CHECK-NEXT:  -      -     0.23   0.30   0.50   0.50    -     0.47   1.00    -     retq
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          012
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeER.    .    .    .    .    . .   stmxcsr	-4(%rsp)
 # CHECK-NEXT: [0,1]     DeE-R.    .    .    .    .    . .   movl	$-24577, %eax
 # CHECK-NEXT: [0,2]     .DeeeeeeER.    .    .    .    . .   andl	-4(%rsp), %eax
-# CHECK-NEXT: [0,3]     .D======eER    .    .    .    . .   movl	%eax, -8(%rsp)
-# CHECK-NEXT: [0,4]     . D=====eeeeeeeER   .    .    . .   ldmxcsr	-8(%rsp)
+# CHECK-NEXT: [0,3]     .DPPPPPPeER    .    .    .    . .   movl	%eax, -8(%rsp)
+# CHECK-NEXT: [0,4]     . DPPPPPeeeeeeeER   .    .    . .   ldmxcsr	-8(%rsp)
 # CHECK-NEXT: [0,5]     .  DeeeeeeeE----R   .    .    . .   retq
-# CHECK-NEXT: [1,0]     .   D==========eeER .    .    . .   stmxcsr	-4(%rsp)
+# CHECK-NEXT: [1,0]     .   DPPPPPPPPPPeeER .    .    . .   stmxcsr	-4(%rsp)
 # CHECK-NEXT: [1,1]     .   DeE-----------R .    .    . .   movl	$-24577, %eax
 # CHECK-NEXT: [1,2]     .    DeeeeeeE-----R .    .    . .   andl	-4(%rsp), %eax
-# CHECK-NEXT: [1,3]     .    D==========eER .    .    . .   movl	%eax, -8(%rsp)
-# CHECK-NEXT: [1,4]     .    .D=========eeeeeeeER.    . .   ldmxcsr	-8(%rsp)
+# CHECK-NEXT: [1,3]     .    DPPPPPPPPP=eER .    .    . .   movl	%eax, -8(%rsp)
+# CHECK-NEXT: [1,4]     .    .DPPPPPPPPPeeeeeeeER.    . .   ldmxcsr	-8(%rsp)
 # CHECK-NEXT: [1,5]     .    . D=eeeeeeeE-------R.    . .   retq
-# CHECK-NEXT: [2,0]     .    .  D==============eeER   . .   stmxcsr	-4(%rsp)
+# CHECK-NEXT: [2,0]     .    .  DPPPPPPPPPPPPPPeeER   . .   stmxcsr	-4(%rsp)
 # CHECK-NEXT: [2,1]     .    .  DeE---------------R   . .   movl	$-24577, %eax
 # CHECK-NEXT: [2,2]     .    .   DeeeeeeE---------R   . .   andl	-4(%rsp), %eax
-# CHECK-NEXT: [2,3]     .    .   D==============eER   . .   movl	%eax, -8(%rsp)
-# CHECK-NEXT: [2,4]     .    .    D=============eeeeeeeER   ldmxcsr	-8(%rsp)
+# CHECK-NEXT: [2,3]     .    .   DPPPPPPPPPPPPP=eER   . .   movl	%eax, -8(%rsp)
+# CHECK-NEXT: [2,4]     .    .    DPPPPPPPPPPPPPeeeeeeeER   ldmxcsr	-8(%rsp)
 # CHECK-NEXT: [2,5]     .    .    .DeeeeeeeE------------R   retq
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/Haswell/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/Haswell/zero-idioms.s
index fb9b90c450364..87d35681f0ac2 100644
--- a/llvm/test/tools/llvm-mca/X86/Haswell/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/Haswell/zero-idioms.s
@@ -313,6 +313,7 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     vpxor	%ymm3, %ymm3, %ymm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -321,8 +322,8 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,2]     DR   .    .    .    .   .   xorl	%eax, %eax
 # CHECK-NEXT: [0,3]     DR   .    .    .    .   .   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     .DeER.    .    .    .   .   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     .D=eER    .    .    .   .   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D==eER   .    .    .   .   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     .DPeER    .    .    .   .   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPPeER   .    .    .   .   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .D----R   .    .    .   .   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     . D---R   .    .    .   .   pcmpgtd	%xmm2, %xmm2
 # CHECK-NEXT: [0,9]     . D---R   .    .    .   .   pcmpgtq	%xmm2, %xmm2
@@ -345,8 +346,8 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,26]    .    .DR  .    .    .   .   vpcmpgtw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,27]    .    .DeER.    .    .   .   psubb	%mm2, %mm2
 # CHECK-NEXT: [0,28]    .    . DeER    .    .   .   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,29]    .    . D=eER   .    .   .   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    . D==eER  .    .   .   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,29]    .    . DPeER   .    .   .   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    . DPPeER  .    .   .   psubw	%mm2, %mm2
 # CHECK-NEXT: [0,31]    .    . D----R  .    .   .   psubb	%xmm2, %xmm2
 # CHECK-NEXT: [0,32]    .    .  D---R  .    .   .   psubd	%xmm2, %xmm2
 # CHECK-NEXT: [0,33]    .    .  D---R  .    .   .   psubq	%xmm2, %xmm2
@@ -370,18 +371,18 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,51]    .    .    . DeER    .   .   andnps	%xmm0, %xmm0
 # CHECK-NEXT: [0,52]    .    .    .  DeER   .   .   andnpd	%xmm1, %xmm1
 # CHECK-NEXT: [0,53]    .    .    .  D=eER  .   .   vandnps	%xmm2, %xmm2, %xmm2
-# CHECK-NEXT: [0,54]    .    .    .  D==eER .   .   vandnpd	%xmm1, %xmm1, %xmm1
-# CHECK-NEXT: [0,55]    .    .    .  D===eER.   .   vandnps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,56]    .    .    .   D===eER   .   vandnpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,54]    .    .    .  DP=eER .   .   vandnpd	%xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,55]    .    .    .  DPP=eER.   .   vandnps	%ymm2, %ymm2, %ymm2
+# CHECK-NEXT: [0,56]    .    .    .   DPP=eER   .   vandnpd	%ymm1, %ymm1, %ymm1
 # CHECK-NEXT: [0,57]    .    .    .   DeE---R   .   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,58]    .    .    .   D===eER   .   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,58]    .    .    .   DPPPeER   .   pandn	%xmm2, %xmm2
 # CHECK-NEXT: [0,59]    .    .    .   DeE---R   .   vpandn	%xmm3, %xmm3, %xmm3
 # CHECK-NEXT: [0,60]    .    .    .    DeE--R   .   vpandn	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,61]    .    .    .    D===eER  .   vandnps	%xmm2, %xmm2, %xmm5
-# CHECK-NEXT: [0,62]    .    .    .    D====eER .   vandnpd	%xmm1, %xmm1, %xmm5
-# CHECK-NEXT: [0,63]    .    .    .    D=eE---R .   vpandn	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,64]    .    .    .    .D====eER.   vandnps	%ymm2, %ymm2, %ymm5
-# CHECK-NEXT: [0,65]    .    .    .    .D=====eER   vandnpd	%ymm1, %ymm1, %ymm5
+# CHECK-NEXT: [0,61]    .    .    .    DPPPeER  .   vandnps	%xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,62]    .    .    .    DPPP=eER .   vandnpd	%xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,63]    .    .    .    DPeE---R .   vpandn	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,64]    .    .    .    .DPP==eER.   vandnps	%ymm2, %ymm2, %ymm5
+# CHECK-NEXT: [0,65]    .    .    .    .DPP===eER   vandnpd	%ymm1, %ymm1, %ymm5
 # CHECK-NEXT: [0,66]    .    .    .    .DeE-----R   vpandn	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,67]    .    .    .    .D-------R   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,68]    .    .    .    . D------R   xorpd	%xmm1, %xmm1
diff --git a/llvm/test/tools/llvm-mca/X86/IceLakeServer/independent-load-stores.s b/llvm/test/tools/llvm-mca/X86/IceLakeServer/independent-load-stores.s
index 70df4681804dd..bbbf29993b32e 100644
--- a/llvm/test/tools/llvm-mca/X86/IceLakeServer/independent-load-stores.s
+++ b/llvm/test/tools/llvm-mca/X86/IceLakeServer/independent-load-stores.s
@@ -83,6 +83,7 @@
 # ALL-NEXT:       -      -     0.50    -     1.00    -     1.00   0.50    -     1.00    -      -     addq	$44, 640(%r14)
 
 # ALL:           Timeline view:
+# ALL-NEXT:      D: Instruction dispatched
 
 # NOALIAS-NEXT:                      0123
 # NOALIAS-NEXT:  Index     0123456789
@@ -102,15 +103,15 @@
 # NOALIAS-NEXT:  [0,9]     .   DeeeeeeeER   addq	$44, 640(%r14)
 
 # YESALIAS:      [0,0]     DeeeeeeeER.    .    .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 64(%r14)
-# YESALIAS-NEXT: [0,1]     D=======eeeeeeeER   .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
-# YESALIAS-NEXT: [0,2]     .D=============eeeeeeeER .    .    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
-# YESALIAS-NEXT: [0,3]     .D====================eeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 256(%r14)
-# YESALIAS-NEXT: [0,4]     . D==========================eeeeeeeER  .    .    .    .    .    .    . .   addq	$44, 320(%r14)
-# YESALIAS-NEXT: [0,5]     . D=================================eeeeeeeER.    .    .    .    .    . .   addq	$44, 384(%r14)
-# YESALIAS-NEXT: [0,6]     .  D=======================================eeeeeeeER   .    .    .    . .   addq	$44, 448(%r14)
-# YESALIAS-NEXT: [0,7]     .  D==============================================eeeeeeeER .    .    . .   addq	$44, 512(%r14)
-# YESALIAS-NEXT: [0,8]     .   D====================================================eeeeeeeER    . .   addq	$44, 576(%r14)
-# YESALIAS-NEXT: [0,9]     .   D===========================================================eeeeeeeER   addq	$44, 640(%r14)
+# YESALIAS-NEXT: [0,1]     DPPPPPPPeeeeeeeER   .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
+# YESALIAS-NEXT: [0,2]     .DPPPPPPPPPPPPPeeeeeeeER .    .    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
+# YESALIAS-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPPPPeeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 256(%r14)
+# YESALIAS-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER  .    .    .    .    .    .    . .   addq	$44, 320(%r14)
+# YESALIAS-NEXT: [0,5]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER.    .    .    .    .    . .   addq	$44, 384(%r14)
+# YESALIAS-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   .    .    .    . .   addq	$44, 448(%r14)
+# YESALIAS-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER .    .    . .   addq	$44, 512(%r14)
+# YESALIAS-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   addq	$44, 576(%r14)
+# YESALIAS-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   addq	$44, 640(%r14)
 
 # ALL:           Average Wait times (based on the timeline view):
 # ALL-NEXT:      [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/IceLakeServer/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/IceLakeServer/zero-idioms.s
index 353448606af59..0a9975bbb9782 100644
--- a/llvm/test/tools/llvm-mca/X86/IceLakeServer/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/IceLakeServer/zero-idioms.s
@@ -489,6 +489,7 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -     vpxorq	%zmm19, %zmm19, %zmm21
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
@@ -497,8 +498,8 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,2]     DR   .    .    .    .    ..   xorl	%eax, %eax
 # CHECK-NEXT: [0,3]     DR   .    .    .    .    ..   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     DeER .    .    .    .    ..   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     D=eER.    .    .    .    ..   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D=eER    .    .    .    ..   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     DPeER.    .    .    .    ..   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPeER    .    .    .    ..   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .D---R    .    .    .    ..   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     .D---R    .    .    .    ..   pcmpgtd	%xmm2, %xmm2
 # CHECK-NEXT: [0,9]     .D---R    .    .    .    ..   pcmpgtq	%xmm2, %xmm2
@@ -520,9 +521,9 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,25]    .   DR    .    .    .    ..   vpcmpgtq	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,26]    .   DR    .    .    .    ..   vpcmpgtw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,27]    .   DeER  .    .    .    ..   psubb	%mm2, %mm2
-# CHECK-NEXT: [0,28]    .   D=eER .    .    .    ..   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,29]    .   D==eER.    .    .    ..   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    D==eER    .    .    ..   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,28]    .   DPeER .    .    .    ..   psubd	%mm2, %mm2
+# CHECK-NEXT: [0,29]    .   DPPeER.    .    .    ..   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    DPPeER    .    .    ..   psubw	%mm2, %mm2
 # CHECK-NEXT: [0,31]    .    D----R    .    .    ..   psubb	%xmm2, %xmm2
 # CHECK-NEXT: [0,32]    .    D----R    .    .    ..   psubd	%xmm2, %xmm2
 # CHECK-NEXT: [0,33]    .    D----R    .    .    ..   psubq	%xmm2, %xmm2
@@ -572,33 +573,33 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,77]    .    .    . DeER    .    ..   vandnps	%xmm2, %xmm2, %xmm2
 # CHECK-NEXT: [0,78]    .    .    .  DeER   .    ..   vandnpd	%xmm1, %xmm1, %xmm1
 # CHECK-NEXT: [0,79]    .    .    .  DeER   .    ..   vandnps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,80]    .    .    .  D=eER  .    ..   vandnpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,81]    .    .    .  D=eER  .    ..   vandnps	%zmm2, %zmm2, %zmm2
-# CHECK-NEXT: [0,82]    .    .    .  D==eER .    ..   vandnpd	%zmm1, %zmm1, %zmm1
+# CHECK-NEXT: [0,80]    .    .    .  DPeER  .    ..   vandnpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,81]    .    .    .  DPeER  .    ..   vandnps	%zmm2, %zmm2, %zmm2
+# CHECK-NEXT: [0,82]    .    .    .  DPPeER .    ..   vandnpd	%zmm1, %zmm1, %zmm1
 # CHECK-NEXT: [0,83]    .    .    .  DeE--R .    ..   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,84]    .    .    .   D=eER .    ..   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,84]    .    .    .   DPeER .    ..   pandn	%xmm2, %xmm2
 # CHECK-NEXT: [0,85]    .    .    .   DeE-R .    ..   vpandn	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,86]    .    .    .   D=eER .    ..   vpandn	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,86]    .    .    .   DPeER .    ..   vpandn	%ymm3, %ymm3, %ymm3
 # CHECK-NEXT: [0,87]    .    .    .   D==eER.    ..   vpandnd	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,88]    .    .    .   D===eER    ..   vpandnq	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,89]    .    .    .   D====eER   ..   vpandnd	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,90]    .    .    .    D====eER  ..   vpandnq	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,91]    .    .    .    D=====eER ..   vpandnd	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,92]    .    .    .    D======eER..   vpandnq	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,93]    .    .    .    D=eE-----R..   vandnps	%xmm2, %xmm2, %xmm5
-# CHECK-NEXT: [0,94]    .    .    .    D=eE-----R..   vandnpd	%xmm1, %xmm1, %xmm5
-# CHECK-NEXT: [0,95]    .    .    .    D==eE----R..   vpandn	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,88]    .    .    .   DPPPeER    ..   vpandnq	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,89]    .    .    .   DPPPPeER   ..   vpandnd	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,90]    .    .    .    DPPPPeER  ..   vpandnq	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,91]    .    .    .    DPPPPPeER ..   vpandnd	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,92]    .    .    .    DPPPPPPeER..   vpandnq	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,93]    .    .    .    DPeE-----R..   vandnps	%xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,94]    .    .    .    DPeE-----R..   vandnpd	%xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,95]    .    .    .    DP=eE----R..   vpandn	%xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,96]    .    .    .    .D=eE----R..   vandnps	%ymm2, %ymm2, %ymm5
 # CHECK-NEXT: [0,97]    .    .    .    .D==eE---R..   vandnpd	%ymm1, %ymm1, %ymm5
 # CHECK-NEXT: [0,98]    .    .    .    .D==eE---R..   vpandn	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,99]    .    .    .    .D===eE--R..   vandnps	%zmm2, %zmm2, %zmm5
 # CHECK-NEXT: [0,100]   .    .    .    .D===eE--R..   vandnpd	%zmm1, %zmm1, %zmm5
-# CHECK-NEXT: [0,101]   .    .    .    .D======eER.   vpandnd	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,102]   .    .    .    . D=====eER.   vpandnq	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,103]   .    .    .    . D=====eER.   vpandnd	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,104]   .    .    .    . D======eER   vpandnq	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,105]   .    .    .    . D======eER   vpandnd	%zmm19, %zmm19, %zmm21
-# CHECK-NEXT: [0,106]   .    .    .    . D======eER   vpandnq	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,101]   .    .    .    .DPPPPPPeER.   vpandnd	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,102]   .    .    .    . DPPPPPeER.   vpandnq	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,103]   .    .    .    . DPPPPPeER.   vpandnd	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,104]   .    .    .    . DPPPPP=eER   vpandnq	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,105]   .    .    .    . DPPPPP=eER   vpandnd	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,106]   .    .    .    . DPPPPP=eER   vpandnq	%zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,107]   .    .    .    . D--------R   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,108]   .    .    .    .  D-------R   xorpd	%xmm1, %xmm1
 # CHECK-NEXT: [0,109]   .    .    .    .  D-------R   vxorps	%xmm2, %xmm2, %xmm2
diff --git a/llvm/test/tools/llvm-mca/X86/SLM/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/SLM/zero-idioms.s
index df0a26341b3b6..43c238d252fce 100644
--- a/llvm/test/tools/llvm-mca/X86/SLM/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/SLM/zero-idioms.s
@@ -160,44 +160,45 @@ pxor   %xmm2, %xmm2
 # CHECK-NEXT:  -      -      -      -     1.00    -      -      -     pxor	%xmm2, %xmm2
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeER .    .    .    .    .    .   subl	%eax, %eax
-# CHECK-NEXT: [0,1]     D=eER.    .    .    .    .    .   subq	%rax, %rax
+# CHECK-NEXT: [0,1]     DPeER.    .    .    .    .    .   subq	%rax, %rax
 # CHECK-NEXT: [0,2]     .DeER.    .    .    .    .    .   xorl	%eax, %eax
-# CHECK-NEXT: [0,3]     .D=eER    .    .    .    .    .   xorq	%rax, %rax
+# CHECK-NEXT: [0,3]     .DPeER    .    .    .    .    .   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     . DeER    .    .    .    .    .   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     . D=eER   .    .    .    .    .   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .  D=eER  .    .    .    .    .   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     . DPeER   .    .    .    .    .   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .  DPeER  .    .    .    .    .   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .  DeE-R  .    .    .    .    .   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     .   DeER  .    .    .    .    .   pcmpgtd	%xmm2, %xmm2
-# CHECK-NEXT: [0,9]     .   D=eeeeeER  .    .    .    .   pcmpgtq	%xmm2, %xmm2
-# CHECK-NEXT: [0,10]    .    D=====eER .    .    .    .   pcmpgtw	%xmm2, %xmm2
+# CHECK-NEXT: [0,9]     .   DPeeeeeER  .    .    .    .   pcmpgtq	%xmm2, %xmm2
+# CHECK-NEXT: [0,10]    .    DPPPPPeER .    .    .    .   pcmpgtw	%xmm2, %xmm2
 # CHECK-NEXT: [0,11]    .    DeE-----R .    .    .    .   psubb	%mm2, %mm2
 # CHECK-NEXT: [0,12]    .    .DeE----R .    .    .    .   psubd	%mm2, %mm2
 # CHECK-NEXT: [0,13]    .    . DeeeeER .    .    .    .   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,14]    .    .  D===eER.    .    .    .   psubw	%mm2, %mm2
-# CHECK-NEXT: [0,15]    .    .  D====eER    .    .    .   psubb	%xmm2, %xmm2
-# CHECK-NEXT: [0,16]    .    .   D====eER   .    .    .   psubd	%xmm2, %xmm2
-# CHECK-NEXT: [0,17]    .    .    D====eeeeER    .    .   psubq	%xmm2, %xmm2
-# CHECK-NEXT: [0,18]    .    .    .D=======eER   .    .   psubw	%xmm2, %xmm2
-# CHECK-NEXT: [0,19]    .    .    .D====eE---R   .    .   psubsb	%mm2, %mm2
-# CHECK-NEXT: [0,20]    .    .    . D====eE--R   .    .   psubsw	%mm2, %mm2
-# CHECK-NEXT: [0,21]    .    .    . D=======eER  .    .   psubsb	%xmm2, %xmm2
-# CHECK-NEXT: [0,22]    .    .    .  D=======eER .    .   psubsw	%xmm2, %xmm2
-# CHECK-NEXT: [0,23]    .    .    .  D====eE---R .    .   psubusb	%mm2, %mm2
-# CHECK-NEXT: [0,24]    .    .    .   D=======eER.    .   psubusw	%mm2, %mm2
-# CHECK-NEXT: [0,25]    .    .    .   D========eER    .   psubusb	%xmm2, %xmm2
-# CHECK-NEXT: [0,26]    .    .    .    D========eER   .   psubusw	%xmm2, %xmm2
+# CHECK-NEXT: [0,14]    .    .  DPPPeER.    .    .    .   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,15]    .    .  DPPP=eER    .    .    .   psubb	%xmm2, %xmm2
+# CHECK-NEXT: [0,16]    .    .   DPPPPeER   .    .    .   psubd	%xmm2, %xmm2
+# CHECK-NEXT: [0,17]    .    .    DPPPPeeeeER    .    .   psubq	%xmm2, %xmm2
+# CHECK-NEXT: [0,18]    .    .    .DPPPPPPPeER   .    .   psubw	%xmm2, %xmm2
+# CHECK-NEXT: [0,19]    .    .    .DP===eE---R   .    .   psubsb	%mm2, %mm2
+# CHECK-NEXT: [0,20]    .    .    . DPPPPeE--R   .    .   psubsw	%mm2, %mm2
+# CHECK-NEXT: [0,21]    .    .    . DPPPPPPPeER  .    .   psubsb	%xmm2, %xmm2
+# CHECK-NEXT: [0,22]    .    .    .  DPPPPPPPeER .    .   psubsw	%xmm2, %xmm2
+# CHECK-NEXT: [0,23]    .    .    .  DPPPPeE---R .    .   psubusb	%mm2, %mm2
+# CHECK-NEXT: [0,24]    .    .    .   DPPPP===eER.    .   psubusw	%mm2, %mm2
+# CHECK-NEXT: [0,25]    .    .    .   DPPPPPPP=eER    .   psubusb	%xmm2, %xmm2
+# CHECK-NEXT: [0,26]    .    .    .    DPPPPPPPPeER   .   psubusw	%xmm2, %xmm2
 # CHECK-NEXT: [0,27]    .    .    .    D=======eE-R   .   andnps	%xmm0, %xmm0
 # CHECK-NEXT: [0,28]    .    .    .    .D========eER  .   andnpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,29]    .    .    .    .D=======eE-R  .   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    .    .    . D=======eER  .   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,29]    .    .    .    .DPPPPPP=eE-R  .   pandn	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    .    .    . DPPPPPPPeER  .   pandn	%xmm2, %xmm2
 # CHECK-NEXT: [0,31]    .    .    .    . D========eER .   vpandn	%xmm3, %xmm3, %xmm3
 # CHECK-NEXT: [0,32]    .    .    .    .  D=======eER .   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,33]    .    .    .    .  D========eER.   xorpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,34]    .    .    .    .   D=======eER.   pxor	%mm2, %mm2
+# CHECK-NEXT: [0,34]    .    .    .    .   DPPPPP==eER.   pxor	%mm2, %mm2
 # CHECK-NEXT: [0,35]    .    .    .    .   D========eER   pxor	%xmm2, %xmm2
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s
index bdca772b4956c..af146fd2dc457 100644
--- a/llvm/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s
@@ -249,6 +249,7 @@ vpxor  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     vpxor	%xmm3, %xmm3, %xmm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -257,8 +258,8 @@ vpxor  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,2]     DR   .    .    .    .   .   xorl	%eax, %eax
 # CHECK-NEXT: [0,3]     DR   .    .    .    .   .   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     .DeeeER   .    .    .   .   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     .D===eeeER.    .    .   .   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D======eeeER  .    .   .   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     .DPPPeeeER.    .    .   .   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPPPPPPeeeER  .    .   .   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .D----------R  .    .   .   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     . D---------R  .    .   .   pcmpgtd	%xmm2, %xmm2
 # CHECK-NEXT: [0,9]     . D---------R  .    .   .   pcmpgtq	%xmm2, %xmm2
@@ -271,10 +272,10 @@ vpxor  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,16]    .   D-------R  .    .   .   vpcmpgtd	%xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,17]    .   D-------R  .    .   .   vpcmpgtq	%xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,18]    .   D-------R  .    .   .   vpcmpgtw	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,19]    .   D======eeeER    .   .   psubb	%mm2, %mm2
-# CHECK-NEXT: [0,20]    .    D========eeeER .   .   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,21]    .    D===========eER.   .   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,22]    .    D============eeeER .   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,19]    .   DPPPPPPeeeER    .   .   psubb	%mm2, %mm2
+# CHECK-NEXT: [0,20]    .    DPPPPPPPPeeeER .   .   psubd	%mm2, %mm2
+# CHECK-NEXT: [0,21]    .    DPPPPPPPPPPPeER.   .   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,22]    .    DPPPPPPPPPPPPeeeER .   psubw	%mm2, %mm2
 # CHECK-NEXT: [0,23]    .    D----------------R .   psubb	%xmm2, %xmm2
 # CHECK-NEXT: [0,24]    .    .D---------------R .   psubd	%xmm2, %xmm2
 # CHECK-NEXT: [0,25]    .    .D---------------R .   psubq	%xmm2, %xmm2
@@ -290,24 +291,24 @@ vpxor  %xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,35]    .    .  DeE-----------R .   andnps	%xmm0, %xmm0
 # CHECK-NEXT: [0,36]    .    .   DeE----------R .   andnpd	%xmm1, %xmm1
 # CHECK-NEXT: [0,37]    .    .   D=eE---------R .   vandnps	%xmm2, %xmm2, %xmm2
-# CHECK-NEXT: [0,38]    .    .   D===eE-------R .   vandnpd	%xmm1, %xmm1, %xmm1
-# CHECK-NEXT: [0,39]    .    .   D==eE--------R .   vandnps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,40]    .    .    D===eE------R .   vandnpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,41]    .    .    D==========eER.   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,42]    .    .    D==eE--------R.   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,38]    .    .   DP==eE-------R .   vandnpd	%xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,39]    .    .   DPPeE--------R .   vandnps	%ymm2, %ymm2, %ymm2
+# CHECK-NEXT: [0,40]    .    .    DPPPeE------R .   vandnpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,41]    .    .    DPPPPPPPPPPeER.   pandn	%mm2, %mm2
+# CHECK-NEXT: [0,42]    .    .    DPPeE--------R.   pandn	%xmm2, %xmm2
 # CHECK-NEXT: [0,43]    .    .    DeE----------R.   vpandn	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,44]    .    .    .D===eE------R.   vandnps	%xmm2, %xmm2, %xmm5
-# CHECK-NEXT: [0,45]    .    .    .D====eE-----R.   vandnpd	%xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,44]    .    .    .DPP=eE------R.   vandnps	%xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,45]    .    .    .DPPP=eE-----R.   vandnpd	%xmm1, %xmm1, %xmm5
 # CHECK-NEXT: [0,46]    .    .    .DeE---------R.   vpandn	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,47]    .    .    .D=====eE----R.   vandnps	%ymm2, %ymm2, %ymm5
-# CHECK-NEXT: [0,48]    .    .    . D=====eE---R.   vandnpd	%ymm1, %ymm1, %ymm5
+# CHECK-NEXT: [0,47]    .    .    .DPP===eE----R.   vandnps	%ymm2, %ymm2, %ymm5
+# CHECK-NEXT: [0,48]    .    .    . DPP===eE---R.   vandnpd	%ymm1, %ymm1, %ymm5
 # CHECK-NEXT: [0,49]    .    .    . D----------R.   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,50]    .    .    . D----------R.   xorpd	%xmm1, %xmm1
 # CHECK-NEXT: [0,51]    .    .    . D----------R.   vxorps	%xmm2, %xmm2, %xmm2
 # CHECK-NEXT: [0,52]    .    .    .  D---------R.   vxorpd	%xmm1, %xmm1, %xmm1
 # CHECK-NEXT: [0,53]    .    .    .  D---------R.   vxorps	%ymm2, %ymm2, %ymm2
 # CHECK-NEXT: [0,54]    .    .    .  D---------R.   vxorpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,55]    .    .    .  D========eER   pxor	%mm2, %mm2
+# CHECK-NEXT: [0,55]    .    .    .  DPPPPPPPPeER   pxor	%mm2, %mm2
 # CHECK-NEXT: [0,56]    .    .    .   D---------R   pxor	%xmm2, %xmm2
 # CHECK-NEXT: [0,57]    .    .    .   D---------R   vpxor	%xmm3, %xmm3, %xmm3
 # CHECK-NEXT: [0,58]    .    .    .   D---------R   vxorps	%xmm4, %xmm4, %xmm5
diff --git a/llvm/test/tools/llvm-mca/X86/SapphireRapids/independent-load-stores.s b/llvm/test/tools/llvm-mca/X86/SapphireRapids/independent-load-stores.s
index 08a706d4ab97a..e37e8d432df9c 100644
--- a/llvm/test/tools/llvm-mca/X86/SapphireRapids/independent-load-stores.s
+++ b/llvm/test/tools/llvm-mca/X86/SapphireRapids/independent-load-stores.s
@@ -84,6 +84,7 @@
 # ALL-NEXT:      1.00    -     0.33   0.33   1.00    -      -     1.00    -      -     0.34    -      -     addq	$44, 640(%r14)
 
 # ALL:           Timeline view:
+# ALL-NEXT:      D: Instruction dispatched
 
 # NOALIAS-NEXT:                      0123456789
 # NOALIAS-NEXT:  Index     0123456789          0123
@@ -103,11 +104,11 @@
 # NOALIAS-NEXT:  [0,9]     .    .   DeeeeeeeeeeeeER   addq	$44, 640(%r14)
 
 # YESALIAS:      [0,0]     DeeeeeeeeeeeeER.    .    .    .    .    .    .    .    .    .    .    .   .   addq	$44, 64(%r14)
-# YESALIAS-NEXT: [0,1]     .D===========eeeeeeeeeeeeER   .    .    .    .    .    .    .    .    .   .   addq	$44, 128(%r14)
-# YESALIAS-NEXT: [0,2]     . D======================eeeeeeeeeeeeER .    .    .    .    .    .    .   .   addq	$44, 192(%r14)
-# YESALIAS-NEXT: [0,3]     .  D=================================eeeeeeeeeeeeER    .    .    .    .   .   addq	$44, 256(%r14)
-# YESALIAS-NEXT: [0,4]     .   D============================================eeeeeeeeeeeeER  .    .   .   addq	$44, 320(%r14)
-# YESALIAS-NEXT: [0,5]     .    D=======================================================eeeeeeeeeeeeER   addq	$44, 384(%r14)
+# YESALIAS-NEXT: [0,1]     .DPPPPPPPPPPPeeeeeeeeeeeeER   .    .    .    .    .    .    .    .    .   .   addq	$44, 128(%r14)
+# YESALIAS-NEXT: [0,2]     . DPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeER .    .    .    .    .    .    .   .   addq	$44, 192(%r14)
+# YESALIAS-NEXT: [0,3]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeER    .    .    .    .   .   addq	$44, 256(%r14)
+# YESALIAS-NEXT: [0,4]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeER  .    .   .   addq	$44, 320(%r14)
+# YESALIAS-NEXT: [0,5]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeeeeeeER   addq	$44, 384(%r14)
 # YESALIAS-NEXT: Truncated display due to cycle limit
 
 # ALL:           Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/SapphireRapids/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/SapphireRapids/zero-idioms.s
index e11c548f5a7b6..e47511718d2a6 100644
--- a/llvm/test/tools/llvm-mca/X86/SapphireRapids/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/SapphireRapids/zero-idioms.s
@@ -490,148 +490,149 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT:  -      -      -      -      -     1.00    -      -      -      -      -      -      -     vpxorq	%zmm19, %zmm19, %zmm21
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          01
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789
 
 # CHECK:      [0,0]     DeER .    .    .    .    .    .    .    .    .    ..   subl	%eax, %eax
-# CHECK-NEXT: [0,1]     D=eER.    .    .    .    .    .    .    .    .    ..   subq	%rax, %rax
-# CHECK-NEXT: [0,2]     D==eeER   .    .    .    .    .    .    .    .    ..   xorl	%eax, %eax
-# CHECK-NEXT: [0,3]     D====eeER .    .    .    .    .    .    .    .    ..   xorq	%rax, %rax
+# CHECK-NEXT: [0,1]     DPeER.    .    .    .    .    .    .    .    .    ..   subq	%rax, %rax
+# CHECK-NEXT: [0,2]     DPPeeER   .    .    .    .    .    .    .    .    ..   xorl	%eax, %eax
+# CHECK-NEXT: [0,3]     DPPPPeeER .    .    .    .    .    .    .    .    ..   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     DeE-----R .    .    .    .    .    .    .    .    ..   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     D=eE----R .    .    .    .    .    .    .    .    ..   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D=eE---R .    .    .    .    .    .    .    .    ..   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     DPeE----R .    .    .    .    .    .    .    .    ..   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPeE---R .    .    .    .    .    .    .    .    ..   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .DeE----R .    .    .    .    .    .    .    .    ..   pcmpgtb	%xmm2, %xmm2
-# CHECK-NEXT: [0,8]     .D=eE---R .    .    .    .    .    .    .    .    ..   pcmpgtd	%xmm2, %xmm2
-# CHECK-NEXT: [0,9]     .D==eeeER .    .    .    .    .    .    .    .    ..   pcmpgtq	%xmm2, %xmm2
-# CHECK-NEXT: [0,10]    .D=====eER.    .    .    .    .    .    .    .    ..   pcmpgtw	%xmm2, %xmm2
+# CHECK-NEXT: [0,8]     .DPeE---R .    .    .    .    .    .    .    .    ..   pcmpgtd	%xmm2, %xmm2
+# CHECK-NEXT: [0,9]     .DPPeeeER .    .    .    .    .    .    .    .    ..   pcmpgtq	%xmm2, %xmm2
+# CHECK-NEXT: [0,10]    .DPPPPPeER.    .    .    .    .    .    .    .    ..   pcmpgtw	%xmm2, %xmm2
 # CHECK-NEXT: [0,11]    .D==eE---R.    .    .    .    .    .    .    .    ..   vpcmpgtb	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,12]    . D==eE--R.    .    .    .    .    .    .    .    ..   vpcmpgtd	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,13]    . D===eeeER    .    .    .    .    .    .    .    ..   vpcmpgtq	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,14]    . D======eER   .    .    .    .    .    .    .    ..   vpcmpgtw	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,15]    . D=======eER  .    .    .    .    .    .    .    ..   vpcmpgtb	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,16]    . D=======eER  .    .    .    .    .    .    .    ..   vpcmpgtd	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,17]    . D=======eeeER.    .    .    .    .    .    .    ..   vpcmpgtq	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,18]    .  D=======eE-R.    .    .    .    .    .    .    ..   vpcmpgtw	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,19]    .  D=======eE-R.    .    .    .    .    .    .    ..   vpcmpgtb	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,20]    .  D========eER.    .    .    .    .    .    .    ..   vpcmpgtd	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,21]    .  D=========eeeER  .    .    .    .    .    .    ..   vpcmpgtq	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,22]    .  D============eER .    .    .    .    .    .    ..   vpcmpgtw	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,23]    .  D=============eER.    .    .    .    .    .    ..   vpcmpgtb	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,24]    .   D============eER.    .    .    .    .    .    ..   vpcmpgtd	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,25]    .   D============eeeER   .    .    .    .    .    ..   vpcmpgtq	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,26]    .   D=============eE-R   .    .    .    .    .    ..   vpcmpgtw	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,12]    . DPPeE--R.    .    .    .    .    .    .    .    ..   vpcmpgtd	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,13]    . DPPPeeeER    .    .    .    .    .    .    .    ..   vpcmpgtq	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,14]    . DPPPPPPeER   .    .    .    .    .    .    .    ..   vpcmpgtw	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,15]    . DPPPPPPPeER  .    .    .    .    .    .    .    ..   vpcmpgtb	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,16]    . DPPPPPPPeER  .    .    .    .    .    .    .    ..   vpcmpgtd	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,17]    . DPPPPPPPeeeER.    .    .    .    .    .    .    ..   vpcmpgtq	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,18]    .  DPPPPPP=eE-R.    .    .    .    .    .    .    ..   vpcmpgtw	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,19]    .  DPPPPPP=eE-R.    .    .    .    .    .    .    ..   vpcmpgtb	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,20]    .  DPPPPPPPPeER.    .    .    .    .    .    .    ..   vpcmpgtd	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,21]    .  DPPPPPPPPPeeeER  .    .    .    .    .    .    ..   vpcmpgtq	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,22]    .  DPPPPPPPPPPPPeER .    .    .    .    .    .    ..   vpcmpgtw	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,23]    .  DPPPPPPPPPPPPPeER.    .    .    .    .    .    ..   vpcmpgtb	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,24]    .   DPPPPPPPPPPPPeER.    .    .    .    .    .    ..   vpcmpgtd	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,25]    .   DPPPPPPPPPPPPeeeER   .    .    .    .    .    ..   vpcmpgtq	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,26]    .   DPPPPPPPPPPPP=eE-R   .    .    .    .    .    ..   vpcmpgtw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,27]    .   DeE--------------R   .    .    .    .    .    ..   psubb	%mm2, %mm2
-# CHECK-NEXT: [0,28]    .   D=eE-------------R   .    .    .    .    .    ..   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,29]    .   D==eE------------R   .    .    .    .    .    ..   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    D==eE-----------R   .    .    .    .    .    ..   psubw	%mm2, %mm2
-# CHECK-NEXT: [0,31]    .    D==eE-----------R   .    .    .    .    .    ..   psubb	%xmm2, %xmm2
-# CHECK-NEXT: [0,32]    .    D===eE----------R   .    .    .    .    .    ..   psubd	%xmm2, %xmm2
-# CHECK-NEXT: [0,33]    .    D=====eE--------R   .    .    .    .    .    ..   psubq	%xmm2, %xmm2
-# CHECK-NEXT: [0,34]    .    D======eE-------R   .    .    .    .    .    ..   psubw	%xmm2, %xmm2
-# CHECK-NEXT: [0,35]    .    D============eE-R   .    .    .    .    .    ..   vpsubb	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,36]    .    .D============eER   .    .    .    .    .    ..   vpsubd	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,37]    .    .D=============eER  .    .    .    .    .    ..   vpsubq	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,38]    .    .D==============eER .    .    .    .    .    ..   vpsubw	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,39]    .    .D===============eER.    .    .    .    .    ..   vpsubb	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,40]    .    .D================eER    .    .    .    .    ..   vpsubd	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,41]    .    .D=================eER   .    .    .    .    ..   vpsubq	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,42]    .    . D=================eER  .    .    .    .    ..   vpsubw	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,43]    .    . D==================eER .    .    .    .    ..   vpsubb	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,44]    .    . D==================eER .    .    .    .    ..   vpsubd	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,45]    .    . D==================eER .    .    .    .    ..   vpsubq	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,46]    .    . D===================eER.    .    .    .    ..   vpsubw	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,47]    .    . D===================eER.    .    .    .    ..   vpsubb	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,48]    .    .  D==================eER.    .    .    .    ..   vpsubd	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,49]    .    .  D===================eER    .    .    .    ..   vpsubq	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,50]    .    .  D===================eER    .    .    .    ..   vpsubw	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,28]    .   DPeE-------------R   .    .    .    .    .    ..   psubd	%mm2, %mm2
+# CHECK-NEXT: [0,29]    .   DPPeE------------R   .    .    .    .    .    ..   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    DPPeE-----------R   .    .    .    .    .    ..   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,31]    .    DPPeE-----------R   .    .    .    .    .    ..   psubb	%xmm2, %xmm2
+# CHECK-NEXT: [0,32]    .    DPPPeE----------R   .    .    .    .    .    ..   psubd	%xmm2, %xmm2
+# CHECK-NEXT: [0,33]    .    DPPPP=eE--------R   .    .    .    .    .    ..   psubq	%xmm2, %xmm2
+# CHECK-NEXT: [0,34]    .    DPPPPPPeE-------R   .    .    .    .    .    ..   psubw	%xmm2, %xmm2
+# CHECK-NEXT: [0,35]    .    DPPPPPPPPPPP=eE-R   .    .    .    .    .    ..   vpsubb	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,36]    .    .DPPPPPPPPPPPPeER   .    .    .    .    .    ..   vpsubd	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,37]    .    .DPPPPPPPPPPPPPeER  .    .    .    .    .    ..   vpsubq	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,38]    .    .DPPPPPPPPPPPPPPeER .    .    .    .    .    ..   vpsubw	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,39]    .    .DPPPPPPPPPPPPPPPeER.    .    .    .    .    ..   vpsubb	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,40]    .    .DPPPPPPPPPPPPPPPPeER    .    .    .    .    ..   vpsubd	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,41]    .    .DPPPPPPPPPPPPPPPPPeER   .    .    .    .    ..   vpsubq	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,42]    .    . DPPPPPPPPPPPPPPPPPeER  .    .    .    .    ..   vpsubw	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,43]    .    . DPPPPPPPPPPPPPPPPPPeER .    .    .    .    ..   vpsubb	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,44]    .    . DPPPPPPPPPPPPPPPPPPeER .    .    .    .    ..   vpsubd	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,45]    .    . DPPPPPPPPPPPPPPPPPPeER .    .    .    .    ..   vpsubq	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,46]    .    . DPPPPPPPPPPPPPPPPPP=eER.    .    .    .    ..   vpsubw	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,47]    .    . DPPPPPPPPPPPPPPPPPP=eER.    .    .    .    ..   vpsubb	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,48]    .    .  DPPPPPPPPPPPPPPPPP=eER.    .    .    .    ..   vpsubd	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,49]    .    .  DPPPPPPPPPPPPPPPPP==eER    .    .    .    ..   vpsubq	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,50]    .    .  DPPPPPPPPPPPPPPPPP==eER    .    .    .    ..   vpsubw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,51]    .    .  DeE-------------------R    .    .    .    ..   vpsubb	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,52]    .    .  D===eE----------------R    .    .    .    ..   vpsubd	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,53]    .    .  D====eE---------------R    .    .    .    ..   vpsubq	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,54]    .    .   D====eE--------------R    .    .    .    ..   vpsubw	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,55]    .    .   D=====eE-------------R    .    .    .    ..   vpsubb	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,56]    .    .   D======eE------------R    .    .    .    ..   vpsubd	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,57]    .    .   D========eE----------R    .    .    .    ..   vpsubq	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,58]    .    .   D=========eE---------R    .    .    .    ..   vpsubw	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,59]    .    .   D==========eE--------R    .    .    .    ..   vpsubb	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,60]    .    .    D==========eE-------R    .    .    .    ..   vpsubd	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,61]    .    .    D===========eE------R    .    .    .    ..   vpsubq	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,62]    .    .    D============eE-----R    .    .    .    ..   vpsubw	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,63]    .    .    D=============eE----R    .    .    .    ..   vpsubb	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,64]    .    .    D=============eE----R    .    .    .    ..   vpsubd	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,65]    .    .    D==============eE---R    .    .    .    ..   vpsubq	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,66]    .    .    .D=============eE---R    .    .    .    ..   vpsubw	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,67]    .    .    .D================eER    .    .    .    ..   vpsubb	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,68]    .    .    .D=================eER   .    .    .    ..   vpsubd	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,69]    .    .    .D=================eER   .    .    .    ..   vpsubq	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,70]    .    .    .D=================eER   .    .    .    ..   vpsubw	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,71]    .    .    .D==================eER  .    .    .    ..   vpsubb	%zmm19, %zmm19, %zmm21
-# CHECK-NEXT: [0,72]    .    .    . D=================eER  .    .    .    ..   vpsubd	%zmm19, %zmm19, %zmm21
-# CHECK-NEXT: [0,73]    .    .    . D==================eER .    .    .    ..   vpsubq	%zmm19, %zmm19, %zmm21
-# CHECK-NEXT: [0,74]    .    .    . D==================eER .    .    .    ..   vpsubw	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,52]    .    .  DP==eE----------------R    .    .    .    ..   vpsubd	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,53]    .    .  DPPPPeE---------------R    .    .    .    ..   vpsubq	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,54]    .    .   DPPPPeE--------------R    .    .    .    ..   vpsubw	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,55]    .    .   DPPPPPeE-------------R    .    .    .    ..   vpsubb	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,56]    .    .   DPPPPPPeE------------R    .    .    .    ..   vpsubd	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,57]    .    .   DPPPPPPP=eE----------R    .    .    .    ..   vpsubq	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,58]    .    .   DPPPPPPPPPeE---------R    .    .    .    ..   vpsubw	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,59]    .    .   DPPPPPPPPPPeE--------R    .    .    .    ..   vpsubb	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,60]    .    .    DPPPPPPPPPPeE-------R    .    .    .    ..   vpsubd	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,61]    .    .    DPPPPPPPPPPPeE------R    .    .    .    ..   vpsubq	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,62]    .    .    DPPPPPPPPPPPPeE-----R    .    .    .    ..   vpsubw	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,63]    .    .    DPPPPPPPPPPPPPeE----R    .    .    .    ..   vpsubb	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,64]    .    .    DPPPPPPPPPPPPPeE----R    .    .    .    ..   vpsubd	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,65]    .    .    DPPPPPPPPPPPPP=eE---R    .    .    .    ..   vpsubq	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,66]    .    .    .DPPPPPPPPPPPP=eE---R    .    .    .    ..   vpsubw	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,67]    .    .    .DPPPPPPPPPPPP====eER    .    .    .    ..   vpsubb	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,68]    .    .    .DPPPPPPPPPPPP=====eER   .    .    .    ..   vpsubd	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,69]    .    .    .DPPPPPPPPPPPP=====eER   .    .    .    ..   vpsubq	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,70]    .    .    .DPPPPPPPPPPPP=====eER   .    .    .    ..   vpsubw	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,71]    .    .    .DPPPPPPPPPPPP======eER  .    .    .    ..   vpsubb	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,72]    .    .    . DPPPPPPPPPPP======eER  .    .    .    ..   vpsubd	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,73]    .    .    . DPPPPPPPPPPP=======eER .    .    .    ..   vpsubq	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,74]    .    .    . DPPPPPPPPPPP=======eER .    .    .    ..   vpsubw	%zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,75]    .    .    . DeE------------------R .    .    .    ..   andnps	%xmm0, %xmm0
 # CHECK-NEXT: [0,76]    .    .    . D=eE-----------------R .    .    .    ..   andnpd	%xmm1, %xmm1
 # CHECK-NEXT: [0,77]    .    .    . D=eE-----------------R .    .    .    ..   vandnps	%xmm2, %xmm2, %xmm2
-# CHECK-NEXT: [0,78]    .    .    .  D=eE----------------R .    .    .    ..   vandnpd	%xmm1, %xmm1, %xmm1
-# CHECK-NEXT: [0,79]    .    .    .  D=eE----------------R .    .    .    ..   vandnps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,80]    .    .    .  D==eE---------------R .    .    .    ..   vandnpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,81]    .    .    .  D=========eE--------R .    .    .    ..   vandnps	%zmm2, %zmm2, %zmm2
-# CHECK-NEXT: [0,82]    .    .    .  D=====eE------------R .    .    .    ..   vandnpd	%zmm1, %zmm1, %zmm1
+# CHECK-NEXT: [0,78]    .    .    .  DPeE----------------R .    .    .    ..   vandnpd	%xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,79]    .    .    .  DPeE----------------R .    .    .    ..   vandnps	%ymm2, %ymm2, %ymm2
+# CHECK-NEXT: [0,80]    .    .    .  DPPeE---------------R .    .    .    ..   vandnpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,81]    .    .    .  DPP=======eE--------R .    .    .    ..   vandnps	%zmm2, %zmm2, %zmm2
+# CHECK-NEXT: [0,82]    .    .    .  DPPP==eE------------R .    .    .    ..   vandnpd	%zmm1, %zmm1, %zmm1
 # CHECK-NEXT: [0,83]    .    .    .  D==================eER.    .    .    ..   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,84]    .    .    .   D===============eE--R.    .    .    ..   pandn	%xmm2, %xmm2
-# CHECK-NEXT: [0,85]    .    .    .   D================eE-R.    .    .    ..   vpandn	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,86]    .    .    .   D=================eER.    .    .    ..   vpandn	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,87]    .    .    .   D=================eER.    .    .    ..   vpandnd	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,88]    .    .    .   D==================eER    .    .    ..   vpandnq	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,89]    .    .    .   D===================eER   .    .    ..   vpandnd	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,90]    .    .    .    D===================eER  .    .    ..   vpandnq	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,91]    .    .    .    D====================eER .    .    ..   vpandnd	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,92]    .    .    .    D=====================eER.    .    ..   vpandnq	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,93]    .    .    .    D=================eE----R.    .    ..   vandnps	%xmm2, %xmm2, %xmm5
-# CHECK-NEXT: [0,94]    .    .    .    D====eE-----------------R.    .    ..   vandnpd	%xmm1, %xmm1, %xmm5
-# CHECK-NEXT: [0,95]    .    .    .    D=================eE----R.    .    ..   vpandn	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,96]    .    .    .    .D=================eE---R.    .    ..   vandnps	%ymm2, %ymm2, %ymm5
-# CHECK-NEXT: [0,97]    .    .    .    .D====eE----------------R.    .    ..   vandnpd	%ymm1, %ymm1, %ymm5
-# CHECK-NEXT: [0,98]    .    .    .    .D=================eE---R.    .    ..   vpandn	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,99]    .    .    .    .D==================eE--R.    .    ..   vandnps	%zmm2, %zmm2, %zmm5
-# CHECK-NEXT: [0,100]   .    .    .    .D===================eE-R.    .    ..   vandnpd	%zmm1, %zmm1, %zmm5
-# CHECK-NEXT: [0,101]   .    .    .    .D=====================eER    .    ..   vpandnd	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,102]   .    .    .    . D====================eER    .    ..   vpandnq	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,103]   .    .    .    . D====================eER    .    ..   vpandnd	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,104]   .    .    .    . D=====================eER   .    ..   vpandnq	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,105]   .    .    .    . D=====================eER   .    ..   vpandnd	%zmm19, %zmm19, %zmm21
-# CHECK-NEXT: [0,106]   .    .    .    . D======================eER  .    ..   vpandnq	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,84]    .    .    .   DPPPPPPPPP======eE--R.    .    .    ..   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,85]    .    .    .   DPPPPPPPPPPP=====eE-R.    .    .    ..   vpandn	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,86]    .    .    .   DPPPPPPPPPPPPPPPPPeER.    .    .    ..   vpandn	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,87]    .    .    .   DPPPPPPPPP========eER.    .    .    ..   vpandnd	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,88]    .    .    .   DPPPPPPPPPPPPPPPPPPeER    .    .    ..   vpandnq	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,89]    .    .    .   DPPPPPPPPPPPPPPPPPPPeER   .    .    ..   vpandnd	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,90]    .    .    .    DPPPPPPPPPPPPPPPPPPPeER  .    .    ..   vpandnq	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,91]    .    .    .    DPPPPPPPPPPPPPPPPPPPPeER .    .    ..   vpandnd	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,92]    .    .    .    DPPPPPPPPPPPPPPPPPPPPPeER.    .    ..   vpandnq	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,93]    .    .    .    DPPPPPPPPPPPPPPP==eE----R.    .    ..   vandnps	%xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,94]    .    .    .    DPPPPeE-----------------R.    .    ..   vandnpd	%xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,95]    .    .    .    DPPPPPPPPPPPPPPPPPeE----R.    .    ..   vpandn	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,96]    .    .    .    .DPPPPPPPPPPPPPP===eE---R.    .    ..   vandnps	%ymm2, %ymm2, %ymm5
+# CHECK-NEXT: [0,97]    .    .    .    .DPPP=eE----------------R.    .    ..   vandnpd	%ymm1, %ymm1, %ymm5
+# CHECK-NEXT: [0,98]    .    .    .    .DPPPPPPPPPPPPPPPP=eE---R.    .    ..   vpandn	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,99]    .    .    .    .DPPPPPPPPPPPPPP====eE--R.    .    ..   vandnps	%zmm2, %zmm2, %zmm5
+# CHECK-NEXT: [0,100]   .    .    .    .DPPP================eE-R.    .    ..   vandnpd	%zmm1, %zmm1, %zmm5
+# CHECK-NEXT: [0,101]   .    .    .    .DPPPPPPPPPPPPPPPPPPPPPeER    .    ..   vpandnd	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,102]   .    .    .    . DPPPPPPPPPPPPPPPPPPPPeER    .    ..   vpandnq	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,103]   .    .    .    . DPPPPPPPPPPPPPPPPPPPPeER    .    ..   vpandnd	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,104]   .    .    .    . DPPPPPPPPPPPPPPPPPPPP=eER   .    ..   vpandnq	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,105]   .    .    .    . DPPPPPPPPPPPPPPPPPPPP=eER   .    ..   vpandnd	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,106]   .    .    .    . DPPPPPPPPPPPPPPPPPPPP==eER  .    ..   vpandnq	%zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,107]   .    .    .    . D=================eE-----R  .    ..   xorps	%xmm0, %xmm0
-# CHECK-NEXT: [0,108]   .    .    .    .  D===eE------------------R  .    ..   xorpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,109]   .    .    .    .  D=================eE----R  .    ..   vxorps	%xmm2, %xmm2, %xmm2
-# CHECK-NEXT: [0,110]   .    .    .    .  D==================eE---R  .    ..   vxorpd	%xmm1, %xmm1, %xmm1
-# CHECK-NEXT: [0,111]   .    .    .    .  D==================eE---R  .    ..   vxorps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,112]   .    .    .    .  D====================eE-R  .    ..   vxorpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,113]   .    .    .    .  D======================eER .    ..   vxorps	%zmm2, %zmm2, %zmm2
-# CHECK-NEXT: [0,114]   .    .    .    .   D====================eE-R .    ..   vxorpd	%zmm1, %zmm1, %zmm1
-# CHECK-NEXT: [0,115]   .    .    .    .   D=====================eER .    ..   pxor	%mm2, %mm2
-# CHECK-NEXT: [0,116]   .    .    .    .   D======================eER.    ..   pxor	%xmm2, %xmm2
-# CHECK-NEXT: [0,117]   .    .    .    .   D====================eE--R.    ..   vpxor	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,118]   .    .    .    .   D======================eER.    ..   vpxor	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,119]   .    .    .    .   D=====================eE-R.    ..   vpxord	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,120]   .    .    .    .    D=====================eER.    ..   vpxorq	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,121]   .    .    .    .    D======================eER    ..   vpxord	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,122]   .    .    .    .    D=======================eER   ..   vpxorq	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,123]   .    .    .    .    D========================eER  ..   vpxord	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,124]   .    .    .    .    D=========================eER ..   vpxorq	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,108]   .    .    .    .  DP==eE------------------R  .    ..   xorpd	%xmm1, %xmm1
+# CHECK-NEXT: [0,109]   .    .    .    .  DPPPPPPPPPPPP=====eE----R  .    ..   vxorps	%xmm2, %xmm2, %xmm2
+# CHECK-NEXT: [0,110]   .    .    .    .  DPPPP==============eE---R  .    ..   vxorpd	%xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,111]   .    .    .    .  DPPPPPPPPPPPPPPPPPPeE---R  .    ..   vxorps	%ymm2, %ymm2, %ymm2
+# CHECK-NEXT: [0,112]   .    .    .    .  DPPPPPPPPPPPPPPPPPPP=eE-R  .    ..   vxorpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,113]   .    .    .    .  DPPPPPPPPPPPPPPPPPPP===eER .    ..   vxorps	%zmm2, %zmm2, %zmm2
+# CHECK-NEXT: [0,114]   .    .    .    .   DPPPPPPPPPPPPPPPPPPPPeE-R .    ..   vxorpd	%zmm1, %zmm1, %zmm1
+# CHECK-NEXT: [0,115]   .    .    .    .   DPPPPPPPPPPPPP========eER .    ..   pxor	%mm2, %mm2
+# CHECK-NEXT: [0,116]   .    .    .    .   DPPPPPPPPPPPPPPPPPPPPPPeER.    ..   pxor	%xmm2, %xmm2
+# CHECK-NEXT: [0,117]   .    .    .    .   DPPPPPPPPPPPPP=======eE--R.    ..   vpxor	%xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,118]   .    .    .    .   DPPPPPPPPPPPPPPPPPPPPP=eER.    ..   vpxor	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,119]   .    .    .    .   DPPPPPPPPPPPPPPPPPP===eE-R.    ..   vpxord	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,120]   .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPeER.    ..   vpxorq	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,121]   .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPeER    ..   vpxord	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,122]   .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPPeER   ..   vpxorq	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,123]   .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPPPeER  ..   vpxord	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,124]   .    .    .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPeER ..   vpxorq	%zmm19, %zmm19, %zmm19
 # CHECK-NEXT: [0,125]   .    .    .    .    D======================eE---R ..   vxorps	%xmm4, %xmm4, %xmm5
-# CHECK-NEXT: [0,126]   .    .    .    .    .D=====================eE---R ..   vxorpd	%xmm1, %xmm1, %xmm3
+# CHECK-NEXT: [0,126]   .    .    .    .    .DPPPPPPPPPPPPPPPPPPP==eE---R ..   vxorpd	%xmm1, %xmm1, %xmm3
 # CHECK-NEXT: [0,127]   .    .    .    .    .D======================eE--R ..   vxorps	%ymm4, %ymm4, %ymm5
-# CHECK-NEXT: [0,128]   .    .    .    .    .D=======================eE-R ..   vxorpd	%ymm1, %ymm1, %ymm3
+# CHECK-NEXT: [0,128]   .    .    .    .    .DPPPPPPPPPPPPPPPPPPP====eE-R ..   vxorpd	%ymm1, %ymm1, %ymm3
 # CHECK-NEXT: [0,129]   .    .    .    .    .D=======================eE-R ..   vxorps	%zmm4, %zmm4, %zmm5
-# CHECK-NEXT: [0,130]   .    .    .    .    .D======================eE--R ..   vxorpd	%zmm1, %zmm1, %zmm3
-# CHECK-NEXT: [0,131]   .    .    .    .    .D========================eER ..   vpxor	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,132]   .    .    .    .    . D=======================eER ..   vpxor	%ymm3, %ymm3, %ymm5
-# CHECK-NEXT: [0,133]   .    .    .    .    . D========================eER..   vpxord	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,134]   .    .    .    .    . D========================eER..   vpxorq	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,135]   .    .    .    .    . D========================eER..   vpxord	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,136]   .    .    .    .    . D=========================eER.   vpxorq	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,137]   .    .    .    .    . D=========================eER.   vpxord	%zmm19, %zmm19, %zmm21
-# CHECK-NEXT: [0,138]   .    .    .    .    .  D=========================eER   vpxorq	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,130]   .    .    .    .    .DPPPPPPPPPPPPPPPPPPP===eE--R ..   vxorpd	%zmm1, %zmm1, %zmm3
+# CHECK-NEXT: [0,131]   .    .    .    .    .DPPPPPPPPPPPPPPPPPPPPPPP=eER ..   vpxor	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,132]   .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPP=eER ..   vpxor	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,133]   .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPeER..   vpxord	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,134]   .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPeER..   vpxorq	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,135]   .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPeER..   vpxord	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,136]   .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPP=eER.   vpxorq	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,137]   .    .    .    .    . DPPPPPPPPPPPPPPPPPPPPPPPP=eER.   vpxord	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,138]   .    .    .    .    .  DPPPPPPPPPPPPPPPPPPPPPPP==eER   vpxorq	%zmm19, %zmm19, %zmm21
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/SkylakeClient/independent-load-stores.s b/llvm/test/tools/llvm-mca/X86/SkylakeClient/independent-load-stores.s
index 03d7bcd079a33..83bda4780ae9f 100644
--- a/llvm/test/tools/llvm-mca/X86/SkylakeClient/independent-load-stores.s
+++ b/llvm/test/tools/llvm-mca/X86/SkylakeClient/independent-load-stores.s
@@ -81,6 +81,7 @@
 # ALL-NEXT:       -      -     0.50    -     0.66   0.67   1.00   0.50    -     0.67   addq	$44, 640(%r14)
 
 # ALL:           Timeline view:
+# ALL-NEXT:      D: Instruction dispatched
 
 # NOALIAS-NEXT:                      012345678
 # NOALIAS-NEXT:  Index     0123456789
@@ -91,24 +92,24 @@
 # NOALIAS:       [0,0]     DeeeeeeeER.    .  .   addq	$44, 64(%r14)
 # NOALIAS-NEXT:  [0,1]     D=eeeeeeeER    .  .   addq	$44, 128(%r14)
 # NOALIAS-NEXT:  [0,2]     .D=eeeeeeeER   .  .   addq	$44, 192(%r14)
-# NOALIAS-NEXT:  [0,3]     .D==eeeeeeeER  .  .   addq	$44, 256(%r14)
-# NOALIAS-NEXT:  [0,4]     . D==eeeeeeeER .  .   addq	$44, 320(%r14)
-# NOALIAS-NEXT:  [0,5]     . D===eeeeeeeER.  .   addq	$44, 384(%r14)
-# NOALIAS-NEXT:  [0,6]     .  D===eeeeeeeER  .   addq	$44, 448(%r14)
-# NOALIAS-NEXT:  [0,7]     .  D====eeeeeeeER .   addq	$44, 512(%r14)
-# NOALIAS-NEXT:  [0,8]     .   D====eeeeeeeER.   addq	$44, 576(%r14)
-# NOALIAS-NEXT:  [0,9]     .   D=====eeeeeeeER   addq	$44, 640(%r14)
+# NOALIAS-NEXT:  [0,3]     .DP=eeeeeeeER  .  .   addq	$44, 256(%r14)
+# NOALIAS-NEXT:  [0,4]     . DP=eeeeeeeER .  .   addq	$44, 320(%r14)
+# NOALIAS-NEXT:  [0,5]     . DPP=eeeeeeeER.  .   addq	$44, 384(%r14)
+# NOALIAS-NEXT:  [0,6]     .  DPP=eeeeeeeER  .   addq	$44, 448(%r14)
+# NOALIAS-NEXT:  [0,7]     .  DPPP=eeeeeeeER .   addq	$44, 512(%r14)
+# NOALIAS-NEXT:  [0,8]     .   DPPP=eeeeeeeER.   addq	$44, 576(%r14)
+# NOALIAS-NEXT:  [0,9]     .   DPPPP=eeeeeeeER   addq	$44, 640(%r14)
 
 # YESALIAS:      [0,0]     DeeeeeeeER.    .    .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 64(%r14)
-# YESALIAS-NEXT: [0,1]     D=======eeeeeeeER   .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
-# YESALIAS-NEXT: [0,2]     .D=============eeeeeeeER .    .    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
-# YESALIAS-NEXT: [0,3]     .D====================eeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 256(%r14)
-# YESALIAS-NEXT: [0,4]     . D==========================eeeeeeeER  .    .    .    .    .    .    . .   addq	$44, 320(%r14)
-# YESALIAS-NEXT: [0,5]     . D=================================eeeeeeeER.    .    .    .    .    . .   addq	$44, 384(%r14)
-# YESALIAS-NEXT: [0,6]     .  D=======================================eeeeeeeER   .    .    .    . .   addq	$44, 448(%r14)
-# YESALIAS-NEXT: [0,7]     .  D==============================================eeeeeeeER .    .    . .   addq	$44, 512(%r14)
-# YESALIAS-NEXT: [0,8]     .   D====================================================eeeeeeeER    . .   addq	$44, 576(%r14)
-# YESALIAS-NEXT: [0,9]     .   D===========================================================eeeeeeeER   addq	$44, 640(%r14)
+# YESALIAS-NEXT: [0,1]     DPPPPPPPeeeeeeeER   .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
+# YESALIAS-NEXT: [0,2]     .DPPPPPPPPPPPPPeeeeeeeER .    .    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
+# YESALIAS-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPPPPeeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 256(%r14)
+# YESALIAS-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER  .    .    .    .    .    .    . .   addq	$44, 320(%r14)
+# YESALIAS-NEXT: [0,5]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER.    .    .    .    .    . .   addq	$44, 384(%r14)
+# YESALIAS-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   .    .    .    . .   addq	$44, 448(%r14)
+# YESALIAS-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER .    .    . .   addq	$44, 512(%r14)
+# YESALIAS-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   addq	$44, 576(%r14)
+# YESALIAS-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   addq	$44, 640(%r14)
 
 # ALL:           Average Wait times (based on the timeline view):
 # ALL-NEXT:      [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-hi-read-advance.s b/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-hi-read-advance.s
index b157b50cdb9c6..b0488d02facba 100644
--- a/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-hi-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-hi-read-advance.s
@@ -59,11 +59,12 @@ add %rax, %rax
 # CHECK-NEXT:  -      -     1.00    -      -      -      -      -      -      -     addl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeER   mulxl	(%rdi), %eax, %ecx
-# CHECK-NEXT: [0,1]     D========eER   addl	%eax, %eax
+# CHECK-NEXT: [0,1]     DPPPPPPPPeER   addl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -122,11 +123,12 @@ add %rax, %rax
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00    -     addq	%rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeeER   mulxq	(%rdi), %rax, %rcx
-# CHECK-NEXT: [0,1]     D========eER   addq	%rax, %rax
+# CHECK-NEXT: [0,1]     DPPPPPPPPeER   addq	%rax, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-lo-reg-use.s b/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-lo-reg-use.s
index cf200b39eeca7..93decb625d5c2 100644
--- a/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-lo-reg-use.s
+++ b/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-lo-reg-use.s
@@ -53,10 +53,11 @@ mulxq %rax, %rax, %rcx
 # CHECK-NEXT:  -      -     0.50   1.00    -      -      -     0.50   1.00    -     mulxl	%eax, %eax, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   mulxl	%eax, %eax, %ecx
-# CHECK-NEXT: [1,0]     .D==eeeeER   mulxl	%eax, %eax, %ecx
+# CHECK-NEXT: [1,0]     .DPPeeeeER   mulxl	%eax, %eax, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -111,10 +112,11 @@ mulxq %rax, %rax, %rcx
 # CHECK-NEXT:  -      -      -     1.00    -      -      -     1.00    -      -     mulxq	%rax, %rax, %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   mulxq	%rax, %rax, %rcx
-# CHECK-NEXT: [1,0]     D===eeeeER   mulxq	%rax, %rax, %rcx
+# CHECK-NEXT: [1,0]     DPPPeeeeER   mulxq	%rax, %rax, %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-same-regs.s b/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-same-regs.s
index 73ca47840c588..12fc23fa0a879 100644
--- a/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-same-regs.s
+++ b/llvm/test/tools/llvm-mca/X86/SkylakeClient/mulx-same-regs.s
@@ -56,11 +56,12 @@ mulxq %rax, %rax, %rax
 # CHECK-NEXT:  -      -     0.50   1.00    -      -      -     0.50   1.00    -     mulxl	%eax, %eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   mulxl	%eax, %eax, %eax
-# CHECK-NEXT: [1,0]     .D===eeeeER   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [1,0]     .DPPPeeeeER   mulxl	%eax, %eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -115,11 +116,12 @@ mulxq %rax, %rax, %rax
 # CHECK-NEXT:  -      -      -     1.00    -      -      -     1.00    -      -     mulxq	%rax, %rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   mulxq	%rax, %rax, %rax
-# CHECK-NEXT: [1,0]     D====eeeeER   mulxq	%rax, %rax, %rax
+# CHECK-NEXT: [1,0]     DPPPPeeeeER   mulxq	%rax, %rax, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/SkylakeClient/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/SkylakeClient/zero-idioms.s
index 0f19ef26806a9..211bd8df0338a 100644
--- a/llvm/test/tools/llvm-mca/X86/SkylakeClient/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/SkylakeClient/zero-idioms.s
@@ -313,6 +313,7 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     vpxor	%ymm3, %ymm3, %ymm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456
 # CHECK-NEXT: Index     0123456789
 
@@ -321,8 +322,8 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,2]     DR   .    .    ..   xorl	%eax, %eax
 # CHECK-NEXT: [0,3]     DR   .    .    ..   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     DeER .    .    ..   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     D=eER.    .    ..   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D=eER    .    ..   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     DPeER.    .    ..   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPeER    .    ..   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .D---R    .    ..   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     .D---R    .    ..   pcmpgtd	%xmm2, %xmm2
 # CHECK-NEXT: [0,9]     .D---R    .    ..   pcmpgtq	%xmm2, %xmm2
@@ -344,9 +345,9 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,25]    .   DR    .    ..   vpcmpgtq	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,26]    .   DR    .    ..   vpcmpgtw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,27]    .   DeER  .    ..   psubb	%mm2, %mm2
-# CHECK-NEXT: [0,28]    .   D=eER .    ..   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,29]    .   D==eER.    ..   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    D==eER    ..   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,28]    .   DPeER .    ..   psubd	%mm2, %mm2
+# CHECK-NEXT: [0,29]    .   DPPeER.    ..   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    DPPeER    ..   psubw	%mm2, %mm2
 # CHECK-NEXT: [0,31]    .    D----R    ..   psubb	%xmm2, %xmm2
 # CHECK-NEXT: [0,32]    .    D----R    ..   psubd	%xmm2, %xmm2
 # CHECK-NEXT: [0,33]    .    D----R    ..   psubq	%xmm2, %xmm2
@@ -372,17 +373,17 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,53]    .    .  DeER   ..   vandnps	%xmm2, %xmm2, %xmm2
 # CHECK-NEXT: [0,54]    .    .   DeER  ..   vandnpd	%xmm1, %xmm1, %xmm1
 # CHECK-NEXT: [0,55]    .    .   DeER  ..   vandnps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,56]    .    .   D=eER ..   vandnpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,56]    .    .   DPeER ..   vandnpd	%ymm1, %ymm1, %ymm1
 # CHECK-NEXT: [0,57]    .    .   DeE-R ..   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,58]    .    .   D=eER ..   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,58]    .    .   DPeER ..   pandn	%xmm2, %xmm2
 # CHECK-NEXT: [0,59]    .    .   D=eER ..   vpandn	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,60]    .    .    D=eER..   vpandn	%ymm3, %ymm3, %ymm3
-# CHECK-NEXT: [0,61]    .    .    D=eER..   vandnps	%xmm2, %xmm2, %xmm5
-# CHECK-NEXT: [0,62]    .    .    D=eER..   vandnpd	%xmm1, %xmm1, %xmm5
-# CHECK-NEXT: [0,63]    .    .    D==eER.   vpandn	%xmm3, %xmm3, %xmm5
-# CHECK-NEXT: [0,64]    .    .    D==eER.   vandnps	%ymm2, %ymm2, %ymm5
-# CHECK-NEXT: [0,65]    .    .    D==eER.   vandnpd	%ymm1, %ymm1, %ymm5
-# CHECK-NEXT: [0,66]    .    .    .D==eER   vpandn	%ymm3, %ymm3, %ymm5
+# CHECK-NEXT: [0,60]    .    .    DPeER..   vpandn	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,61]    .    .    DPeER..   vandnps	%xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,62]    .    .    DPeER..   vandnpd	%xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,63]    .    .    DPPeER.   vpandn	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,64]    .    .    DP=eER.   vandnps	%ymm2, %ymm2, %ymm5
+# CHECK-NEXT: [0,65]    .    .    DP=eER.   vandnpd	%ymm1, %ymm1, %ymm5
+# CHECK-NEXT: [0,66]    .    .    .DP=eER   vpandn	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,67]    .    .    .D----R   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,68]    .    .    .D----R   xorpd	%xmm1, %xmm1
 # CHECK-NEXT: [0,69]    .    .    .D----R   vxorps	%xmm2, %xmm2, %xmm2
diff --git a/llvm/test/tools/llvm-mca/X86/SkylakeServer/independent-load-stores.s b/llvm/test/tools/llvm-mca/X86/SkylakeServer/independent-load-stores.s
index 4ebdee99ad6b3..c77507810a7cd 100644
--- a/llvm/test/tools/llvm-mca/X86/SkylakeServer/independent-load-stores.s
+++ b/llvm/test/tools/llvm-mca/X86/SkylakeServer/independent-load-stores.s
@@ -81,6 +81,7 @@
 # ALL-NEXT:       -      -     0.50    -     0.66   0.67   1.00   0.50    -     0.67   addq	$44, 640(%r14)
 
 # ALL:           Timeline view:
+# ALL-NEXT:      D: Instruction dispatched
 
 # NOALIAS-NEXT:                      012345678
 # NOALIAS-NEXT:  Index     0123456789
@@ -91,24 +92,24 @@
 # NOALIAS:       [0,0]     DeeeeeeeER.    .  .   addq	$44, 64(%r14)
 # NOALIAS-NEXT:  [0,1]     D=eeeeeeeER    .  .   addq	$44, 128(%r14)
 # NOALIAS-NEXT:  [0,2]     .D=eeeeeeeER   .  .   addq	$44, 192(%r14)
-# NOALIAS-NEXT:  [0,3]     .D==eeeeeeeER  .  .   addq	$44, 256(%r14)
-# NOALIAS-NEXT:  [0,4]     . D==eeeeeeeER .  .   addq	$44, 320(%r14)
-# NOALIAS-NEXT:  [0,5]     . D===eeeeeeeER.  .   addq	$44, 384(%r14)
-# NOALIAS-NEXT:  [0,6]     .  D===eeeeeeeER  .   addq	$44, 448(%r14)
-# NOALIAS-NEXT:  [0,7]     .  D====eeeeeeeER .   addq	$44, 512(%r14)
-# NOALIAS-NEXT:  [0,8]     .   D====eeeeeeeER.   addq	$44, 576(%r14)
-# NOALIAS-NEXT:  [0,9]     .   D=====eeeeeeeER   addq	$44, 640(%r14)
+# NOALIAS-NEXT:  [0,3]     .DP=eeeeeeeER  .  .   addq	$44, 256(%r14)
+# NOALIAS-NEXT:  [0,4]     . DP=eeeeeeeER .  .   addq	$44, 320(%r14)
+# NOALIAS-NEXT:  [0,5]     . DPP=eeeeeeeER.  .   addq	$44, 384(%r14)
+# NOALIAS-NEXT:  [0,6]     .  DPP=eeeeeeeER  .   addq	$44, 448(%r14)
+# NOALIAS-NEXT:  [0,7]     .  DPPP=eeeeeeeER .   addq	$44, 512(%r14)
+# NOALIAS-NEXT:  [0,8]     .   DPPP=eeeeeeeER.   addq	$44, 576(%r14)
+# NOALIAS-NEXT:  [0,9]     .   DPPPP=eeeeeeeER   addq	$44, 640(%r14)
 
 # YESALIAS:      [0,0]     DeeeeeeeER.    .    .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 64(%r14)
-# YESALIAS-NEXT: [0,1]     D=======eeeeeeeER   .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
-# YESALIAS-NEXT: [0,2]     .D=============eeeeeeeER .    .    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
-# YESALIAS-NEXT: [0,3]     .D====================eeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 256(%r14)
-# YESALIAS-NEXT: [0,4]     . D==========================eeeeeeeER  .    .    .    .    .    .    . .   addq	$44, 320(%r14)
-# YESALIAS-NEXT: [0,5]     . D=================================eeeeeeeER.    .    .    .    .    . .   addq	$44, 384(%r14)
-# YESALIAS-NEXT: [0,6]     .  D=======================================eeeeeeeER   .    .    .    . .   addq	$44, 448(%r14)
-# YESALIAS-NEXT: [0,7]     .  D==============================================eeeeeeeER .    .    . .   addq	$44, 512(%r14)
-# YESALIAS-NEXT: [0,8]     .   D====================================================eeeeeeeER    . .   addq	$44, 576(%r14)
-# YESALIAS-NEXT: [0,9]     .   D===========================================================eeeeeeeER   addq	$44, 640(%r14)
+# YESALIAS-NEXT: [0,1]     DPPPPPPPeeeeeeeER   .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
+# YESALIAS-NEXT: [0,2]     .DPPPPPPPPPPPPPeeeeeeeER .    .    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
+# YESALIAS-NEXT: [0,3]     .DPPPPPPPPPPPPPPPPPPPPeeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 256(%r14)
+# YESALIAS-NEXT: [0,4]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER  .    .    .    .    .    .    . .   addq	$44, 320(%r14)
+# YESALIAS-NEXT: [0,5]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER.    .    .    .    .    . .   addq	$44, 384(%r14)
+# YESALIAS-NEXT: [0,6]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   .    .    .    . .   addq	$44, 448(%r14)
+# YESALIAS-NEXT: [0,7]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER .    .    . .   addq	$44, 512(%r14)
+# YESALIAS-NEXT: [0,8]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER    . .   addq	$44, 576(%r14)
+# YESALIAS-NEXT: [0,9]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeeER   addq	$44, 640(%r14)
 
 # ALL:           Average Wait times (based on the timeline view):
 # ALL-NEXT:      [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/SkylakeServer/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/SkylakeServer/zero-idioms.s
index d3f94c27641ed..79dc6c3ad0507 100644
--- a/llvm/test/tools/llvm-mca/X86/SkylakeServer/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/SkylakeServer/zero-idioms.s
@@ -487,6 +487,7 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     vpxorq	%zmm19, %zmm19, %zmm21
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
@@ -495,8 +496,8 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,2]     DR   .    .    .    .    ..   xorl	%eax, %eax
 # CHECK-NEXT: [0,3]     DR   .    .    .    .    ..   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     DeER .    .    .    .    ..   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     D=eER.    .    .    .    ..   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D=eER    .    .    .    ..   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     DPeER.    .    .    .    ..   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPeER    .    .    .    ..   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .D---R    .    .    .    ..   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     .D---R    .    .    .    ..   pcmpgtd	%xmm2, %xmm2
 # CHECK-NEXT: [0,9]     .D---R    .    .    .    ..   pcmpgtq	%xmm2, %xmm2
@@ -518,9 +519,9 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,25]    .   DR    .    .    .    ..   vpcmpgtq	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,26]    .   DR    .    .    .    ..   vpcmpgtw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,27]    .   DeER  .    .    .    ..   psubb	%mm2, %mm2
-# CHECK-NEXT: [0,28]    .   D=eER .    .    .    ..   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,29]    .   D==eER.    .    .    ..   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    D==eER    .    .    ..   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,28]    .   DPeER .    .    .    ..   psubd	%mm2, %mm2
+# CHECK-NEXT: [0,29]    .   DPPeER.    .    .    ..   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    DPPeER    .    .    ..   psubw	%mm2, %mm2
 # CHECK-NEXT: [0,31]    .    D----R    .    .    ..   psubb	%xmm2, %xmm2
 # CHECK-NEXT: [0,32]    .    D----R    .    .    ..   psubd	%xmm2, %xmm2
 # CHECK-NEXT: [0,33]    .    D----R    .    .    ..   psubq	%xmm2, %xmm2
@@ -570,33 +571,33 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,77]    .    .    . DeER    .    ..   vandnps	%xmm2, %xmm2, %xmm2
 # CHECK-NEXT: [0,78]    .    .    .  DeER   .    ..   vandnpd	%xmm1, %xmm1, %xmm1
 # CHECK-NEXT: [0,79]    .    .    .  DeER   .    ..   vandnps	%ymm2, %ymm2, %ymm2
-# CHECK-NEXT: [0,80]    .    .    .  D=eER  .    ..   vandnpd	%ymm1, %ymm1, %ymm1
-# CHECK-NEXT: [0,81]    .    .    .  D=eER  .    ..   vandnps	%zmm2, %zmm2, %zmm2
-# CHECK-NEXT: [0,82]    .    .    .  D==eER .    ..   vandnpd	%zmm1, %zmm1, %zmm1
+# CHECK-NEXT: [0,80]    .    .    .  DPeER  .    ..   vandnpd	%ymm1, %ymm1, %ymm1
+# CHECK-NEXT: [0,81]    .    .    .  DPeER  .    ..   vandnps	%zmm2, %zmm2, %zmm2
+# CHECK-NEXT: [0,82]    .    .    .  DPPeER .    ..   vandnpd	%zmm1, %zmm1, %zmm1
 # CHECK-NEXT: [0,83]    .    .    .  DeE--R .    ..   pandn	%mm2, %mm2
-# CHECK-NEXT: [0,84]    .    .    .   D=eER .    ..   pandn	%xmm2, %xmm2
+# CHECK-NEXT: [0,84]    .    .    .   DPeER .    ..   pandn	%xmm2, %xmm2
 # CHECK-NEXT: [0,85]    .    .    .   DeE-R .    ..   vpandn	%xmm3, %xmm3, %xmm3
-# CHECK-NEXT: [0,86]    .    .    .   D=eER .    ..   vpandn	%ymm3, %ymm3, %ymm3
+# CHECK-NEXT: [0,86]    .    .    .   DPeER .    ..   vpandn	%ymm3, %ymm3, %ymm3
 # CHECK-NEXT: [0,87]    .    .    .   D==eER.    ..   vpandnd	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,88]    .    .    .   D===eER    ..   vpandnq	%xmm19, %xmm19, %xmm19
-# CHECK-NEXT: [0,89]    .    .    .   D====eER   ..   vpandnd	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,90]    .    .    .    D====eER  ..   vpandnq	%ymm19, %ymm19, %ymm19
-# CHECK-NEXT: [0,91]    .    .    .    D=====eER ..   vpandnd	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,92]    .    .    .    D======eER..   vpandnq	%zmm19, %zmm19, %zmm19
-# CHECK-NEXT: [0,93]    .    .    .    D=eE-----R..   vandnps	%xmm2, %xmm2, %xmm5
-# CHECK-NEXT: [0,94]    .    .    .    D=eE-----R..   vandnpd	%xmm1, %xmm1, %xmm5
-# CHECK-NEXT: [0,95]    .    .    .    D==eE----R..   vpandn	%xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,88]    .    .    .   DPPPeER    ..   vpandnq	%xmm19, %xmm19, %xmm19
+# CHECK-NEXT: [0,89]    .    .    .   DPPPPeER   ..   vpandnd	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,90]    .    .    .    DPPPPeER  ..   vpandnq	%ymm19, %ymm19, %ymm19
+# CHECK-NEXT: [0,91]    .    .    .    DPPPPPeER ..   vpandnd	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,92]    .    .    .    DPPPPPPeER..   vpandnq	%zmm19, %zmm19, %zmm19
+# CHECK-NEXT: [0,93]    .    .    .    DPeE-----R..   vandnps	%xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,94]    .    .    .    DPeE-----R..   vandnpd	%xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,95]    .    .    .    DP=eE----R..   vpandn	%xmm3, %xmm3, %xmm5
 # CHECK-NEXT: [0,96]    .    .    .    .D=eE----R..   vandnps	%ymm2, %ymm2, %ymm5
 # CHECK-NEXT: [0,97]    .    .    .    .D==eE---R..   vandnpd	%ymm1, %ymm1, %ymm5
 # CHECK-NEXT: [0,98]    .    .    .    .D==eE---R..   vpandn	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,99]    .    .    .    .D===eE--R..   vandnps	%zmm2, %zmm2, %zmm5
 # CHECK-NEXT: [0,100]   .    .    .    .D===eE--R..   vandnpd	%zmm1, %zmm1, %zmm5
-# CHECK-NEXT: [0,101]   .    .    .    .D======eER.   vpandnd	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,102]   .    .    .    . D=====eER.   vpandnq	%xmm19, %xmm19, %xmm21
-# CHECK-NEXT: [0,103]   .    .    .    . D=====eER.   vpandnd	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,104]   .    .    .    . D======eER   vpandnq	%ymm19, %ymm19, %ymm21
-# CHECK-NEXT: [0,105]   .    .    .    . D======eER   vpandnd	%zmm19, %zmm19, %zmm21
-# CHECK-NEXT: [0,106]   .    .    .    . D======eER   vpandnq	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,101]   .    .    .    .DPPPPPPeER.   vpandnd	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,102]   .    .    .    . DPPPPPeER.   vpandnq	%xmm19, %xmm19, %xmm21
+# CHECK-NEXT: [0,103]   .    .    .    . DPPPPPeER.   vpandnd	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,104]   .    .    .    . DPPPPP=eER   vpandnq	%ymm19, %ymm19, %ymm21
+# CHECK-NEXT: [0,105]   .    .    .    . DPPPPP=eER   vpandnd	%zmm19, %zmm19, %zmm21
+# CHECK-NEXT: [0,106]   .    .    .    . DPPPPP=eER   vpandnq	%zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,107]   .    .    .    . D--------R   xorps	%xmm0, %xmm0
 # CHECK-NEXT: [0,108]   .    .    .    .  D-------R   xorpd	%xmm1, %xmm1
 # CHECK-NEXT: [0,109]   .    .    .    .  D-------R   vxorps	%xmm2, %xmm2, %xmm2
diff --git a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-2.s b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-2.s
index b921b17dea7e4..a5e9201fde187 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-2.s
@@ -29,11 +29,12 @@ add    %ecx, %ebx
 # CHECK-NEXT:  1      1     0.25                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   imulq	%rax, %rbx
-# CHECK-NEXT: [0,1]     D===eeER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D=====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPeeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-3.s b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-3.s
index d8afbacdee79a..40c4099708a87 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-3.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-3.s
@@ -56,27 +56,28 @@ xor %bx, %dx
 # CHECK-NEXT:  -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -     xorw	%bx, %dx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
 # CHECK:      [0,0]     DeER .    .    .    .   addw	%cx, %dx
-# CHECK-NEXT: [0,1]     D=eER.    .    .    .   movw	%ax, %dx
-# CHECK-NEXT: [0,2]     D==eER    .    .    .   xorw	%bx, %dx
-# CHECK-NEXT: [1,0]     D===eER   .    .    .   addw	%cx, %dx
-# CHECK-NEXT: [1,1]     .D===eER  .    .    .   movw	%ax, %dx
-# CHECK-NEXT: [1,2]     .D====eER .    .    .   xorw	%bx, %dx
-# CHECK-NEXT: [2,0]     .D=====eER.    .    .   addw	%cx, %dx
-# CHECK-NEXT: [2,1]     .D======eER    .    .   movw	%ax, %dx
-# CHECK-NEXT: [2,2]     . D======eER   .    .   xorw	%bx, %dx
-# CHECK-NEXT: [3,0]     . D=======eER  .    .   addw	%cx, %dx
-# CHECK-NEXT: [3,1]     . D========eER .    .   movw	%ax, %dx
-# CHECK-NEXT: [3,2]     . D=========eER.    .   xorw	%bx, %dx
-# CHECK-NEXT: [4,0]     .  D=========eER    .   addw	%cx, %dx
-# CHECK-NEXT: [4,1]     .  D==========eER   .   movw	%ax, %dx
-# CHECK-NEXT: [4,2]     .  D===========eER  .   xorw	%bx, %dx
-# CHECK-NEXT: [5,0]     .  D============eER .   addw	%cx, %dx
-# CHECK-NEXT: [5,1]     .   D============eER.   movw	%ax, %dx
-# CHECK-NEXT: [5,2]     .   D=============eER   xorw	%bx, %dx
+# CHECK-NEXT: [0,1]     DPeER.    .    .    .   movw	%ax, %dx
+# CHECK-NEXT: [0,2]     DPPeER    .    .    .   xorw	%bx, %dx
+# CHECK-NEXT: [1,0]     DPPPeER   .    .    .   addw	%cx, %dx
+# CHECK-NEXT: [1,1]     .DPPPeER  .    .    .   movw	%ax, %dx
+# CHECK-NEXT: [1,2]     .DPPPPeER .    .    .   xorw	%bx, %dx
+# CHECK-NEXT: [2,0]     .DPPPPPeER.    .    .   addw	%cx, %dx
+# CHECK-NEXT: [2,1]     .DPPPPPPeER    .    .   movw	%ax, %dx
+# CHECK-NEXT: [2,2]     . DPPPPPPeER   .    .   xorw	%bx, %dx
+# CHECK-NEXT: [3,0]     . DPPPPPPPeER  .    .   addw	%cx, %dx
+# CHECK-NEXT: [3,1]     . DPPPPPPPPeER .    .   movw	%ax, %dx
+# CHECK-NEXT: [3,2]     . DPPPPPPPPPeER.    .   xorw	%bx, %dx
+# CHECK-NEXT: [4,0]     .  DPPPPPPPPPeER    .   addw	%cx, %dx
+# CHECK-NEXT: [4,1]     .  DPPPPPPPPPPeER   .   movw	%ax, %dx
+# CHECK-NEXT: [4,2]     .  DPPPPPPPPPPPeER  .   xorw	%bx, %dx
+# CHECK-NEXT: [5,0]     .  DPPPPPPPPPPPPeER .   addw	%cx, %dx
+# CHECK-NEXT: [5,1]     .   DPPPPPPPPPPPPeER.   movw	%ax, %dx
+# CHECK-NEXT: [5,2]     .   DPPPPPPPPPPPPPeER   xorw	%bx, %dx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-4.s b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-4.s
index 8eb2f503fdb04..d8e2fbf5c0cae 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-4.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-4.s
@@ -56,30 +56,31 @@ add %cx, %bx
 # CHECK-NEXT:  -      -     0.33    -     0.33   0.33    -      -      -      -      -      -     addw	%cx, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [0,1]     D==eeER   .    .    .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D====eER  .    .    .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [1,0]     D=====eeeER    .    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [1,1]     .D======eeER   .    .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,2]     .D========eER  .    .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [2,0]     .D=========eeeER    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [2,1]     .D===========eeER   .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,2]     . D============eER  .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [3,0]     . D=============eeeER    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [3,1]     . D===============eeER   .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [3,2]     . D=================eER  .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [4,0]     .  D=================eeeER    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [4,1]     .  D===================eeER   .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [4,2]     .  D=====================eER  .    . .   addw	%cx, %bx
-# CHECK-NEXT: [5,0]     .  D======================eeeER    . .   imulw	%ax, %bx
-# CHECK-NEXT: [5,1]     .   D=======================eeER   . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [5,2]     .   D=========================eER  . .   addw	%cx, %bx
-# CHECK-NEXT: [6,0]     .   D==========================eeeER .   imulw	%ax, %bx
-# CHECK-NEXT: [6,1]     .   D============================eeER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [6,2]     .    D=============================eER   addw	%cx, %bx
+# CHECK-NEXT: [0,1]     DPPeeER   .    .    .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPeER  .    .    .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [1,0]     DPPPPPeeeER    .    .    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [1,1]     .DPPPPPPeeER   .    .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,2]     .DPPPPPPPPeER  .    .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [2,0]     .DPPPPPPPPPeeeER    .    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [2,1]     .DPPPPPPPPPPPeeER   .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,2]     . DPPPPPPPPPPPPeER  .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [3,0]     . DPPPPPPPPPPPPPeeeER    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [3,1]     . DPPPPPPPPPPPPPPPeeER   .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [3,2]     . DPPPPPPPPPPPPPPPPPeER  .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [4,0]     .  DPPPPPPPPPPPPPPPPPeeeER    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [4,1]     .  DPPPPPPPPPPPPPPPPPPPeeER   .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [4,2]     .  DPPPPPPPPPPPPPPPPPPPPPeER  .    . .   addw	%cx, %bx
+# CHECK-NEXT: [5,0]     .  DPPPPPPPPPPPPPPPPPPPPPPeeeER    . .   imulw	%ax, %bx
+# CHECK-NEXT: [5,1]     .   DPPPPPPPPPPPPPPPPPPPPPPPeeER   . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [5,2]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPeER  . .   addw	%cx, %bx
+# CHECK-NEXT: [6,0]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeER .   imulw	%ax, %bx
+# CHECK-NEXT: [6,1]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [6,2]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   addw	%cx, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-5.s b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-5.s
index cae250315dbc5..a63a34036e519 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-5.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-5.s
@@ -47,17 +47,18 @@ lzcnt %ax, %bx  ## partial register stall.
 # CHECK-NEXT:  -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -     lzcntw	%ax, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeER.    ..   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,0]     D=eeER    ..   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,0]     D==eeER   ..   lzcntw	%ax, %bx
-# CHECK-NEXT: [3,0]     D===eeER  ..   lzcntw	%ax, %bx
-# CHECK-NEXT: [4,0]     .D===eeER ..   lzcntw	%ax, %bx
-# CHECK-NEXT: [5,0]     .D====eeER..   lzcntw	%ax, %bx
-# CHECK-NEXT: [6,0]     .D=====eeER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [7,0]     .D======eeER   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,0]     DPeeER    ..   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,0]     DPPeeER   ..   lzcntw	%ax, %bx
+# CHECK-NEXT: [3,0]     DPPPeeER  ..   lzcntw	%ax, %bx
+# CHECK-NEXT: [4,0]     .DPPPeeER ..   lzcntw	%ax, %bx
+# CHECK-NEXT: [5,0]     .DPPPPeeER..   lzcntw	%ax, %bx
+# CHECK-NEXT: [6,0]     .DPPPPPeeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [7,0]     .DPPPPPPeeER   lzcntw	%ax, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-6.s b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-6.s
index 20fee19b54790..509d6f916607e 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-6.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-6.s
@@ -58,21 +58,22 @@ lzcnt 2(%rsp), %cx
 # CHECK-NEXT: 1.00    -     0.33    -     0.33   0.33    -      -      -      -      -      -     lzcntw	2(%rsp), %cx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .   imull	%edx, %ecx
 # CHECK-NEXT: [0,1]     DeeeeeeER .    .    .    .    .   lzcntw	(%rsp), %cx
 # CHECK-NEXT: [0,2]     .DeeeeeeER.    .    .    .    .   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [1,0]     .D======eeeER  .    .    .    .   imull	%edx, %ecx
-# CHECK-NEXT: [1,1]     . D=====eeeeeeER    .    .    .   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [1,2]     . D======eeeeeeER   .    .    .   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [2,0]     .  D===========eeeER.    .    .   imull	%edx, %ecx
-# CHECK-NEXT: [2,1]     .  D===========eeeeeeER  .    .   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [2,2]     .   D===========eeeeeeER .    .   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [3,0]     .   D=================eeeER   .   imull	%edx, %ecx
-# CHECK-NEXT: [3,1]     .    D================eeeeeeER.   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [3,2]     .    D=================eeeeeeER   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [1,0]     .DPPPPPPeeeER  .    .    .    .   imull	%edx, %ecx
+# CHECK-NEXT: [1,1]     . DPPPPPeeeeeeER    .    .    .   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [1,2]     . DPPPPPPeeeeeeER   .    .    .   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [2,0]     .  DPPPPPPPPPPPeeeER.    .    .   imull	%edx, %ecx
+# CHECK-NEXT: [2,1]     .  DPPPPPPPPPPPeeeeeeER  .    .   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [2,2]     .   DPPPPPPPPPPPeeeeeeER .    .   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [3,0]     .   DPPPPPPPPPPPPPPPPPeeeER   .   imull	%edx, %ecx
+# CHECK-NEXT: [3,1]     .    DPPPPPPPPPPPPPPPPeeeeeeER.   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [3,2]     .    DPPPPPPPPPPPPPPPPPeeeeeeER   lzcntw	2(%rsp), %cx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-7.s b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-7.s
index f3d0321b45414..f41cf1c89bf6c 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-7.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update-7.s
@@ -33,11 +33,12 @@ addq  %rcx, %rdx
 # CHECK-NEXT:  1      1     0.25                        addq	%rcx, %rdx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   imulq	%rax, %rcx
-# CHECK-NEXT: [0,1]     D====eER.   addl	%edx, %ecx
-# CHECK-NEXT: [0,2]     D=====eER   addq	%rcx, %rdx
+# CHECK-NEXT: [0,1]     DPPPPeER.   addl	%edx, %ecx
+# CHECK-NEXT: [0,2]     DPPPPPeER   addq	%rcx, %rdx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update.s b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update.s
index e2da41b06967c..1c502adbaf545 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver1/partial-reg-update.s
@@ -29,11 +29,12 @@ add  %ecx, %ebx
 # CHECK-NEXT:  1      1     0.25                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   imulw	%ax, %cx
-# CHECK-NEXT: [0,1]     D===eER.   addb	%al, %cl
-# CHECK-NEXT: [0,2]     D====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPeER.   addb	%al, %cl
+# CHECK-NEXT: [0,2]     DPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver1/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/Znver1/zero-idioms.s
index c327e4e16665b..b0dd882f166b2 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver1/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver1/zero-idioms.s
@@ -320,6 +320,7 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -     vpxor	%ymm3, %ymm3, %ymm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123
 # CHECK-NEXT: Index     0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/adcx-adox-read-advance.s b/llvm/test/tools/llvm-mca/X86/Znver2/adcx-adox-read-advance.s
index 3b2360e3237fb..2b6ee179344ea 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/adcx-adox-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/adcx-adox-read-advance.s
@@ -58,10 +58,11 @@ adox (%rdi), %rcx
 # CHECK-NEXT:  -     0.50   0.50    -      -     0.50   0.50    -      -      -      -      -      -     adcxq	(%rdi), %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeeER.   adcxq	(%rdi), %rcx
-# CHECK-NEXT: [1,0]     D=eeeeeER   adcxq	(%rdi), %rcx
+# CHECK-NEXT: [1,0]     DPeeeeeER   adcxq	(%rdi), %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -119,10 +120,11 @@ adox (%rdi), %rcx
 # CHECK-NEXT:  -     0.50   0.50    -      -     0.50   0.50    -      -      -      -      -      -     adoxq	(%rdi), %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeeER.   adoxq	(%rdi), %rcx
-# CHECK-NEXT: [1,0]     D=eeeeeER   adoxq	(%rdi), %rcx
+# CHECK-NEXT: [1,0]     DPeeeeeER   adoxq	(%rdi), %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/mulx-hi-read-advance.s b/llvm/test/tools/llvm-mca/X86/Znver2/mulx-hi-read-advance.s
index 87896d9a23d0c..8e9ff499ec42a 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/mulx-hi-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/mulx-hi-read-advance.s
@@ -62,11 +62,12 @@ add %rax, %rax
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -      -      -      -      -     addl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   mulxl	(%rdi), %eax, %ecx
-# CHECK-NEXT: [0,1]     D=======eER   addl	%eax, %eax
+# CHECK-NEXT: [0,1]     DPPPPPPPeER   addl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -128,11 +129,12 @@ add %rax, %rax
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -      -      -      -      -     addq	%rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER.   mulxq	(%rdi), %rax, %rcx
-# CHECK-NEXT: [0,1]     D=======eER   addq	%rax, %rax
+# CHECK-NEXT: [0,1]     DPPPPPPPeER   addq	%rax, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/mulx-read-advance.s b/llvm/test/tools/llvm-mca/X86/Znver2/mulx-read-advance.s
index 7dc5a954c8268..8b2b509b36b41 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/mulx-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/mulx-read-advance.s
@@ -58,11 +58,12 @@ mulxq (%rdi), %rax, %rdx
 # CHECK-NEXT:  -     0.50   0.50    -     1.00    -      -      -      -      -      -      -     2.00   mulxl	(%rdi), %eax, %edx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER. .   mulxl	(%rdi), %eax, %edx
-# CHECK-NEXT: [1,0]     D===eeeeeeeER   mulxl	(%rdi), %eax, %edx
+# CHECK-NEXT: [1,0]     DPPPeeeeeeeER   mulxl	(%rdi), %eax, %edx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -120,11 +121,12 @@ mulxq (%rdi), %rax, %rdx
 # CHECK-NEXT:  -     0.50   0.50    -     1.00    -      -      -      -      -      -      -     2.00   mulxq	(%rdi), %rax, %rdx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeER. .   mulxq	(%rdi), %rax, %rdx
-# CHECK-NEXT: [1,0]     D===eeeeeeeER   mulxq	(%rdi), %rax, %rdx
+# CHECK-NEXT: [1,0]     DPPPeeeeeeeER   mulxq	(%rdi), %rax, %rdx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-2.s b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-2.s
index 20c13ea59b4d8..34943368fd382 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-2.s
@@ -29,11 +29,12 @@ add    %ecx, %ebx
 # CHECK-NEXT:  1      1     0.25                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   imulq	%rax, %rbx
-# CHECK-NEXT: [0,1]     D====eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D=====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-3.s b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-3.s
index a491444823a2e..d4dd86aca743d 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-3.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-3.s
@@ -57,27 +57,28 @@ xor %bx, %dx
 # CHECK-NEXT:  -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -     xorw	%bx, %dx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
 # CHECK:      [0,0]     DeER .    .    .    .   addw	%cx, %dx
-# CHECK-NEXT: [0,1]     D=eER.    .    .    .   movw	%ax, %dx
-# CHECK-NEXT: [0,2]     D==eER    .    .    .   xorw	%bx, %dx
-# CHECK-NEXT: [1,0]     D===eER   .    .    .   addw	%cx, %dx
-# CHECK-NEXT: [1,1]     .D===eER  .    .    .   movw	%ax, %dx
-# CHECK-NEXT: [1,2]     .D====eER .    .    .   xorw	%bx, %dx
-# CHECK-NEXT: [2,0]     .D=====eER.    .    .   addw	%cx, %dx
-# CHECK-NEXT: [2,1]     .D======eER    .    .   movw	%ax, %dx
-# CHECK-NEXT: [2,2]     . D======eER   .    .   xorw	%bx, %dx
-# CHECK-NEXT: [3,0]     . D=======eER  .    .   addw	%cx, %dx
-# CHECK-NEXT: [3,1]     . D========eER .    .   movw	%ax, %dx
-# CHECK-NEXT: [3,2]     . D=========eER.    .   xorw	%bx, %dx
-# CHECK-NEXT: [4,0]     .  D=========eER    .   addw	%cx, %dx
-# CHECK-NEXT: [4,1]     .  D==========eER   .   movw	%ax, %dx
-# CHECK-NEXT: [4,2]     .  D===========eER  .   xorw	%bx, %dx
-# CHECK-NEXT: [5,0]     .  D============eER .   addw	%cx, %dx
-# CHECK-NEXT: [5,1]     .   D============eER.   movw	%ax, %dx
-# CHECK-NEXT: [5,2]     .   D=============eER   xorw	%bx, %dx
+# CHECK-NEXT: [0,1]     DPeER.    .    .    .   movw	%ax, %dx
+# CHECK-NEXT: [0,2]     DPPeER    .    .    .   xorw	%bx, %dx
+# CHECK-NEXT: [1,0]     DPPPeER   .    .    .   addw	%cx, %dx
+# CHECK-NEXT: [1,1]     .DPPPeER  .    .    .   movw	%ax, %dx
+# CHECK-NEXT: [1,2]     .DPPPPeER .    .    .   xorw	%bx, %dx
+# CHECK-NEXT: [2,0]     .DPPPPPeER.    .    .   addw	%cx, %dx
+# CHECK-NEXT: [2,1]     .DPPPPPPeER    .    .   movw	%ax, %dx
+# CHECK-NEXT: [2,2]     . DPPPPPPeER   .    .   xorw	%bx, %dx
+# CHECK-NEXT: [3,0]     . DPPPPPPPeER  .    .   addw	%cx, %dx
+# CHECK-NEXT: [3,1]     . DPPPPPPPPeER .    .   movw	%ax, %dx
+# CHECK-NEXT: [3,2]     . DPPPPPPPPPeER.    .   xorw	%bx, %dx
+# CHECK-NEXT: [4,0]     .  DPPPPPPPPPeER    .   addw	%cx, %dx
+# CHECK-NEXT: [4,1]     .  DPPPPPPPPPPeER   .   movw	%ax, %dx
+# CHECK-NEXT: [4,2]     .  DPPPPPPPPPPPeER  .   xorw	%bx, %dx
+# CHECK-NEXT: [5,0]     .  DPPPPPPPPPPPPeER .   addw	%cx, %dx
+# CHECK-NEXT: [5,1]     .   DPPPPPPPPPPPPeER.   movw	%ax, %dx
+# CHECK-NEXT: [5,2]     .   DPPPPPPPPPPPPPeER   xorw	%bx, %dx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-4.s b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-4.s
index 371b594681592..6eab29b9b67ea 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-4.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-4.s
@@ -57,30 +57,31 @@ add %cx, %bx
 # CHECK-NEXT:  -      -      -     0.33    -     0.33   0.33    -      -      -      -      -      -     addw	%cx, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [0,1]     D===eER   .    .    .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D====eER  .    .    .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [1,0]     D=====eeeER    .    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [1,1]     .D=======eER   .    .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,2]     .D========eER  .    .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [2,0]     .D=========eeeER    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [2,1]     .D============eER   .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,2]     . D============eER  .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [3,0]     . D=============eeeER    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [3,1]     . D================eER   .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [3,2]     . D=================eER  .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [4,0]     .  D=================eeeER    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [4,1]     .  D====================eER   .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [4,2]     .  D=====================eER  .    . .   addw	%cx, %bx
-# CHECK-NEXT: [5,0]     .  D======================eeeER    . .   imulw	%ax, %bx
-# CHECK-NEXT: [5,1]     .   D========================eER   . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [5,2]     .   D=========================eER  . .   addw	%cx, %bx
-# CHECK-NEXT: [6,0]     .   D==========================eeeER .   imulw	%ax, %bx
-# CHECK-NEXT: [6,1]     .   D=============================eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [6,2]     .    D=============================eER   addw	%cx, %bx
+# CHECK-NEXT: [0,1]     DPPPeER   .    .    .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPeER  .    .    .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [1,0]     DPPPPPeeeER    .    .    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [1,1]     .DPPPPPPPeER   .    .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,2]     .DPPPPPPPPeER  .    .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [2,0]     .DPPPPPPPPPeeeER    .    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [2,1]     .DPPPPPPPPPPPPeER   .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,2]     . DPPPPPPPPPPPPeER  .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [3,0]     . DPPPPPPPPPPPPPeeeER    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [3,1]     . DPPPPPPPPPPPPPPPPeER   .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [3,2]     . DPPPPPPPPPPPPPPPPPeER  .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [4,0]     .  DPPPPPPPPPPPPPPPPPeeeER    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [4,1]     .  DPPPPPPPPPPPPPPPPPPPPeER   .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [4,2]     .  DPPPPPPPPPPPPPPPPPPPPPeER  .    . .   addw	%cx, %bx
+# CHECK-NEXT: [5,0]     .  DPPPPPPPPPPPPPPPPPPPPPPeeeER    . .   imulw	%ax, %bx
+# CHECK-NEXT: [5,1]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeER   . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [5,2]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPeER  . .   addw	%cx, %bx
+# CHECK-NEXT: [6,0]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPeeeER .   imulw	%ax, %bx
+# CHECK-NEXT: [6,1]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [6,2]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   addw	%cx, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-5.s b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-5.s
index 4d28d60c586a3..97c4e7910d55d 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-5.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-5.s
@@ -48,17 +48,18 @@ lzcnt %ax, %bx  ## partial register stall.
 # CHECK-NEXT:  -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -     lzcntw	%ax, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    .   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,0]     D=eER.    .   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,0]     D==eER    .   lzcntw	%ax, %bx
-# CHECK-NEXT: [3,0]     D===eER   .   lzcntw	%ax, %bx
-# CHECK-NEXT: [4,0]     .D===eER  .   lzcntw	%ax, %bx
-# CHECK-NEXT: [5,0]     .D====eER .   lzcntw	%ax, %bx
-# CHECK-NEXT: [6,0]     .D=====eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [7,0]     .D======eER   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,0]     DPeER.    .   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,0]     DPPeER    .   lzcntw	%ax, %bx
+# CHECK-NEXT: [3,0]     DPPPeER   .   lzcntw	%ax, %bx
+# CHECK-NEXT: [4,0]     .DPPPeER  .   lzcntw	%ax, %bx
+# CHECK-NEXT: [5,0]     .DPPPPeER .   lzcntw	%ax, %bx
+# CHECK-NEXT: [6,0]     .DPPPPPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [7,0]     .DPPPPPPeER   lzcntw	%ax, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-6.s b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-6.s
index c4b46889e632a..e82285b22f75f 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-6.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-6.s
@@ -59,21 +59,22 @@ lzcnt 2(%rsp), %cx
 # CHECK-NEXT: 0.33   0.33   0.33   0.33    -     0.33   0.33    -      -      -      -      -      -     lzcntw	2(%rsp), %cx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeER    .    .    .    ..   imull	%edx, %ecx
 # CHECK-NEXT: [0,1]     DeeeeeER  .    .    .    ..   lzcntw	(%rsp), %cx
 # CHECK-NEXT: [0,2]     .DeeeeeER .    .    .    ..   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [1,0]     .D=====eeeER   .    .    ..   imull	%edx, %ecx
-# CHECK-NEXT: [1,1]     . D====eeeeeER .    .    ..   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [1,2]     . D=====eeeeeER.    .    ..   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [2,0]     .  D=========eeeER  .    ..   imull	%edx, %ecx
-# CHECK-NEXT: [2,1]     .  D=========eeeeeER.    ..   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [2,2]     .   D=========eeeeeER    ..   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [3,0]     .   D==============eeeER ..   imull	%edx, %ecx
-# CHECK-NEXT: [3,1]     .    D=============eeeeeER.   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [3,2]     .    D==============eeeeeER   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [1,0]     .DPPPPPeeeER   .    .    ..   imull	%edx, %ecx
+# CHECK-NEXT: [1,1]     . DPPPPeeeeeER .    .    ..   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [1,2]     . DPPPPPeeeeeER.    .    ..   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [2,0]     .  DPPPPPPPPPeeeER  .    ..   imull	%edx, %ecx
+# CHECK-NEXT: [2,1]     .  DPPPPPPPPPeeeeeER.    ..   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [2,2]     .   DPPPPPPPPPeeeeeER    ..   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [3,0]     .   DPPPPPPPPPPPPPPeeeER ..   imull	%edx, %ecx
+# CHECK-NEXT: [3,1]     .    DPPPPPPPPPPPPPeeeeeER.   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [3,2]     .    DPPPPPPPPPPPPPPeeeeeER   lzcntw	2(%rsp), %cx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-7.s b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-7.s
index a8940c3e1e59a..8cf237e7dba92 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-7.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update-7.s
@@ -33,11 +33,12 @@ addq  %rcx, %rdx
 # CHECK-NEXT:  1      1     0.25                        addq	%rcx, %rdx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeER .   imulq	%rax, %rcx
-# CHECK-NEXT: [0,1]     D====eER.   addl	%edx, %ecx
-# CHECK-NEXT: [0,2]     D=====eER   addq	%rcx, %rdx
+# CHECK-NEXT: [0,1]     DPPPPeER.   addl	%edx, %ecx
+# CHECK-NEXT: [0,2]     DPPPPPeER   addq	%rcx, %rdx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update.s b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update.s
index 4da239da59e48..8b22a49414c9c 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/partial-reg-update.s
@@ -29,11 +29,12 @@ add  %ecx, %ebx
 # CHECK-NEXT:  1      1     0.25                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   imulw	%ax, %cx
-# CHECK-NEXT: [0,1]     D===eER.   addb	%al, %cl
-# CHECK-NEXT: [0,2]     D====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPeER.   addb	%al, %cl
+# CHECK-NEXT: [0,2]     DPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver2/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/Znver2/zero-idioms.s
index 37319e834ea50..cabd80b169d62 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver2/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver2/zero-idioms.s
@@ -321,6 +321,7 @@ vpxor  %ymm3, %ymm3, %ymm5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -     1.00    -      -      -     vpxor	%ymm3, %ymm3, %ymm5
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/dependency-breaking-gpr.s b/llvm/test/tools/llvm-mca/X86/Znver3/dependency-breaking-gpr.s
index 349abec66457c..308e5cf73d104 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/dependency-breaking-gpr.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/dependency-breaking-gpr.s
@@ -94,12 +94,13 @@ cmovael %eax, %ecx
 # CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxl	%eax, %eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   sbbl	%eax, %eax
-# CHECK-NEXT: [0,1]     D=eeeeER.   mulxl	%eax, %eax, %eax
-# CHECK-NEXT: [1,0]     D=eE---R.   sbbl	%eax, %eax
-# CHECK-NEXT: [1,1]     D==eeeeER   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [0,1]     DPeeeeER.   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [1,0]     DPeE---R.   sbbl	%eax, %eax
+# CHECK-NEXT: [1,1]     DPPeeeeER   mulxl	%eax, %eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -171,12 +172,13 @@ cmovael %eax, %ecx
 # CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxq	%rax, %rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeER .  .   sbbq	%rax, %rax
-# CHECK-NEXT: [0,1]     D=eeeeER.   mulxq	%rax, %rax, %rax
-# CHECK-NEXT: [1,0]     D=eE---R.   sbbq	%rax, %rax
-# CHECK-NEXT: [1,1]     D==eeeeER   mulxq	%rax, %rax, %rax
+# CHECK-NEXT: [0,1]     DPeeeeER.   mulxq	%rax, %rax, %rax
+# CHECK-NEXT: [1,0]     DPeE---R.   sbbq	%rax, %rax
+# CHECK-NEXT: [1,1]     DPPeeeeER   mulxq	%rax, %rax, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -250,15 +252,16 @@ cmovael %eax, %ecx
 # CHECK-NEXT:  -      -      -     0.50    -      -     0.50    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     cmovael	%eax, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   mulxl	%eax, %eax, %eax
 # CHECK-NEXT: [0,1]     D-----R   ..   cmpl	%eax, %eax
-# CHECK-NEXT: [0,2]     D====eER  ..   cmovael	%eax, %ecx
-# CHECK-NEXT: [1,0]     D====eeeeER.   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [0,2]     DPPPPeER  ..   cmovael	%eax, %ecx
+# CHECK-NEXT: [1,0]     DPPPPeeeeER.   mulxl	%eax, %eax, %eax
 # CHECK-NEXT: [1,1]     .D--------R.   cmpl	%eax, %eax
-# CHECK-NEXT: [1,2]     .D=======eER   cmovael	%eax, %ecx
+# CHECK-NEXT: [1,2]     .DPPPPPPPeER   cmovael	%eax, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -333,15 +336,16 @@ cmovael %eax, %ecx
 # CHECK-NEXT:  -      -      -     0.50    -      -     0.50    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     cmovaeq	%rax, %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   mulxq	%rax, %rax, %rax
 # CHECK-NEXT: [0,1]     D-----R   ..   cmpq	%rax, %rax
-# CHECK-NEXT: [0,2]     D====eER  ..   cmovaeq	%rax, %rcx
-# CHECK-NEXT: [1,0]     D====eeeeER.   mulxq	%rax, %rax, %rax
+# CHECK-NEXT: [0,2]     DPPPPeER  ..   cmovaeq	%rax, %rcx
+# CHECK-NEXT: [1,0]     DPPPPeeeeER.   mulxq	%rax, %rax, %rax
 # CHECK-NEXT: [1,1]     .D--------R.   cmpq	%rax, %rax
-# CHECK-NEXT: [1,2]     .D=======eER   cmovaeq	%rax, %rcx
+# CHECK-NEXT: [1,2]     .DPPPPPPPeER   cmovaeq	%rax, %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -416,15 +420,16 @@ cmovael %eax, %ecx
 # CHECK-NEXT:  -      -      -     0.50    -      -     0.50    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     cmovael	%eax, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   mulxl	%eax, %eax, %eax
 # CHECK-NEXT: [0,1]     D-----R   ..   cmpw	%ax, %ax
-# CHECK-NEXT: [0,2]     D====eER  ..   cmovael	%eax, %ecx
-# CHECK-NEXT: [1,0]     D====eeeeER.   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [0,2]     DPPPPeER  ..   cmovael	%eax, %ecx
+# CHECK-NEXT: [1,0]     DPPPPeeeeER.   mulxl	%eax, %eax, %eax
 # CHECK-NEXT: [1,1]     .D--------R.   cmpw	%ax, %ax
-# CHECK-NEXT: [1,2]     .D=======eER   cmovael	%eax, %ecx
+# CHECK-NEXT: [1,2]     .DPPPPPPPeER   cmovael	%eax, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -499,15 +504,16 @@ cmovael %eax, %ecx
 # CHECK-NEXT:  -      -      -     0.50    -      -     0.50    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     cmovael	%eax, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   ..   mulxl	%eax, %eax, %eax
 # CHECK-NEXT: [0,1]     D-----R   ..   cmpb	%al, %al
-# CHECK-NEXT: [0,2]     D====eER  ..   cmovael	%eax, %ecx
-# CHECK-NEXT: [1,0]     D====eeeeER.   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [0,2]     DPPPPeER  ..   cmovael	%eax, %ecx
+# CHECK-NEXT: [1,0]     DPPPPeeeeER.   mulxl	%eax, %eax, %eax
 # CHECK-NEXT: [1,1]     .D--------R.   cmpb	%al, %al
-# CHECK-NEXT: [1,2]     .D=======eER   cmovael	%eax, %ecx
+# CHECK-NEXT: [1,2]     .DPPPPPPPeER   cmovael	%eax, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-hi-read-advance.s b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-hi-read-advance.s
index 0fcd6f5074326..b74da79c93c2b 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-hi-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-hi-read-advance.s
@@ -72,11 +72,12 @@ add %rax, %rax
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   mulxl	(%rdi), %eax, %ecx
-# CHECK-NEXT: [0,1]     D=======eER   addl	%eax, %eax
+# CHECK-NEXT: [0,1]     DPPPPPPPeER   addl	%eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -148,11 +149,12 @@ add %rax, %rax
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addq	%rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   mulxq	(%rdi), %rax, %rcx
-# CHECK-NEXT: [0,1]     D=======eER   addq	%rax, %rax
+# CHECK-NEXT: [0,1]     DPPPPPPPeER   addq	%rax, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-lo-reg-use.s b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-lo-reg-use.s
index cd427bb5912e3..514b8b133490c 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-lo-reg-use.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-lo-reg-use.s
@@ -66,10 +66,11 @@ mulxq %rax, %rax, %rcx
 # CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxl	%eax, %eax, %ecx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   mulxl	%eax, %eax, %ecx
-# CHECK-NEXT: [1,0]     D===eeeeER   mulxl	%eax, %eax, %ecx
+# CHECK-NEXT: [1,0]     DPPPeeeeER   mulxl	%eax, %eax, %ecx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -137,10 +138,11 @@ mulxq %rax, %rax, %rcx
 # CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxq	%rax, %rax, %rcx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER  .   mulxq	%rax, %rax, %rcx
-# CHECK-NEXT: [1,0]     D===eeeeER   mulxq	%rax, %rax, %rcx
+# CHECK-NEXT: [1,0]     DPPPeeeeER   mulxq	%rax, %rax, %rcx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-read-advance.s b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-read-advance.s
index bf82486cf737f..8ff74299ceaf7 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-read-advance.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-read-advance.s
@@ -68,11 +68,12 @@ mulxq (%rdi), %rax, %rdx
 # CHECK-NEXT:  -     0.50   0.50    -     1.00    -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -     0.50   0.50    -      -     mulxl	(%rdi), %eax, %edx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   mulxl	(%rdi), %eax, %edx
-# CHECK-NEXT: [1,0]     D====eeeeeeeeER   mulxl	(%rdi), %eax, %edx
+# CHECK-NEXT: [1,0]     DPPPPeeeeeeeeER   mulxl	(%rdi), %eax, %edx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -140,11 +141,12 @@ mulxq (%rdi), %rax, %rdx
 # CHECK-NEXT:  -     0.50   0.50    -     1.00    -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -     0.50   0.50    -      -     mulxq	(%rdi), %rax, %rdx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     01234
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   mulxq	(%rdi), %rax, %rdx
-# CHECK-NEXT: [1,0]     D====eeeeeeeeER   mulxq	(%rdi), %rax, %rdx
+# CHECK-NEXT: [1,0]     DPPPPeeeeeeeeER   mulxq	(%rdi), %rax, %rdx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-same-regs.s b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-same-regs.s
index 8a5a0148cf589..5175166225c0a 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-same-regs.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-same-regs.s
@@ -69,11 +69,12 @@ mulxq %rax, %rax, %rax
 # CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxl	%eax, %eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   mulxl	%eax, %eax, %eax
-# CHECK-NEXT: [1,0]     D====eeeeER   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [1,0]     DPPPPeeeeER   mulxl	%eax, %eax, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -141,11 +142,12 @@ mulxq %rax, %rax, %rax
 # CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxq	%rax, %rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeeER   .   mulxq	%rax, %rax, %rax
-# CHECK-NEXT: [1,0]     D====eeeeER   mulxq	%rax, %rax, %rax
+# CHECK-NEXT: [1,0]     DPPPPeeeeER   mulxq	%rax, %rax, %rax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-avx-xmm.s b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-avx-xmm.s
index f0e16a8d8b99c..5a9a386575b4d 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-avx-xmm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-avx-xmm.s
@@ -94,12 +94,13 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     vpaddb	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpcmpeqb	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   vpaddb	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   vpaddb	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   vpcmpeqb	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   vpaddb	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   vpaddb	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -185,12 +186,13 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     vpaddw	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpcmpeqw	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   vpaddw	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   vpaddw	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   vpcmpeqw	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   vpaddw	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   vpaddw	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -276,12 +278,13 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     vpaddd	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpcmpeqd	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   vpaddd	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   vpaddd	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   vpcmpeqd	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   vpaddd	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   vpaddd	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -367,12 +370,13 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpaddq	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpcmpeqq	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   vpaddq	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   vpaddq	%xmm0, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   vpcmpeqq	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   vpaddq	%xmm0, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   vpaddq	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-avx-ymm.s b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-avx-ymm.s
index 97f6a34acac19..7275219fc06df 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-avx-ymm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-avx-ymm.s
@@ -94,12 +94,13 @@ vpaddq %ymm0, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     vpaddb	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpcmpeqb	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D=eER   vpaddb	%ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPeER   vpaddb	%ymm0, %ymm0, %ymm0
 # CHECK-NEXT: [1,0]     DeE-R   vpcmpeqb	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=eER   vpaddb	%ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPeER   vpaddb	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -185,12 +186,13 @@ vpaddq %ymm0, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     vpaddw	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpcmpeqw	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D=eER   vpaddw	%ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPeER   vpaddw	%ymm0, %ymm0, %ymm0
 # CHECK-NEXT: [1,0]     DeE-R   vpcmpeqw	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=eER   vpaddw	%ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPeER   vpaddw	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -276,12 +278,13 @@ vpaddq %ymm0, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     vpaddd	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpcmpeqd	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D=eER   vpaddd	%ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPeER   vpaddd	%ymm0, %ymm0, %ymm0
 # CHECK-NEXT: [1,0]     DeE-R   vpcmpeqd	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=eER   vpaddd	%ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPeER   vpaddd	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -367,12 +370,13 @@ vpaddq %ymm0, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpaddq	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpcmpeqq	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D=eER   vpaddq	%ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPeER   vpaddq	%ymm0, %ymm0, %ymm0
 # CHECK-NEXT: [1,0]     DeE-R   vpcmpeqq	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=eER   vpaddq	%ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPeER   vpaddq	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-mmx.s b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-mmx.s
index c733f639819be..aaa42afa980a3 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-mmx.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-mmx.s
@@ -89,12 +89,13 @@ paddd %mm0, %mm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddb	%mm0, %mm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpeqb	%mm0, %mm0
-# CHECK-NEXT: [0,1]     D=eER   paddb	%mm0, %mm0
+# CHECK-NEXT: [0,1]     DPeER   paddb	%mm0, %mm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpeqb	%mm0, %mm0
-# CHECK-NEXT: [1,1]     D=eER   paddb	%mm0, %mm0
+# CHECK-NEXT: [1,1]     DPeER   paddb	%mm0, %mm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -180,12 +181,13 @@ paddd %mm0, %mm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddw	%mm0, %mm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpeqw	%mm0, %mm0
-# CHECK-NEXT: [0,1]     D=eER   paddw	%mm0, %mm0
+# CHECK-NEXT: [0,1]     DPeER   paddw	%mm0, %mm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpeqw	%mm0, %mm0
-# CHECK-NEXT: [1,1]     D=eER   paddw	%mm0, %mm0
+# CHECK-NEXT: [1,1]     DPeER   paddw	%mm0, %mm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -271,12 +273,13 @@ paddd %mm0, %mm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddd	%mm0, %mm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpeqd	%mm0, %mm0
-# CHECK-NEXT: [0,1]     D=eER   paddd	%mm0, %mm0
+# CHECK-NEXT: [0,1]     DPeER   paddd	%mm0, %mm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpeqd	%mm0, %mm0
-# CHECK-NEXT: [1,1]     D=eER   paddd	%mm0, %mm0
+# CHECK-NEXT: [1,1]     DPeER   paddd	%mm0, %mm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-sse-xmm.s b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-sse-xmm.s
index 63df99e56f8cd..f0ef44a1e1a1e 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-sse-xmm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-sse-xmm.s
@@ -94,12 +94,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddb	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpeqb	%xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   paddb	%xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   paddb	%xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpeqb	%xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   paddb	%xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   paddb	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -185,12 +186,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddw	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpeqw	%xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   paddw	%xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   paddw	%xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpeqw	%xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   paddw	%xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   paddw	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -276,12 +278,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddd	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpeqd	%xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   paddd	%xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   paddd	%xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpeqd	%xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   paddd	%xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   paddd	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -367,12 +370,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddq	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpeqq	%xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   paddq	%xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   paddq	%xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpeqq	%xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   paddq	%xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   paddq	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-2.s b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-2.s
index 150fa7cbd875e..0f3497d2cfbda 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-2.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-2.s
@@ -29,11 +29,12 @@ add    %ecx, %ebx
 # CHECK-NEXT:  1      1     0.25                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   imulq	%rax, %rbx
-# CHECK-NEXT: [0,1]     D===eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-3.s b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-3.s
index 66c1322fa7902..d1a7f544d6969 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-3.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-3.s
@@ -67,27 +67,28 @@ xor %bx, %dx
 # CHECK-NEXT:  -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     xorw	%bx, %dx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0
 
 # CHECK:      [0,0]     DeER .    .    .    .   addw	%cx, %dx
-# CHECK-NEXT: [0,1]     D=eER.    .    .    .   movw	%ax, %dx
-# CHECK-NEXT: [0,2]     D==eER    .    .    .   xorw	%bx, %dx
-# CHECK-NEXT: [1,0]     D===eER   .    .    .   addw	%cx, %dx
-# CHECK-NEXT: [1,1]     D====eER  .    .    .   movw	%ax, %dx
-# CHECK-NEXT: [1,2]     D=====eER .    .    .   xorw	%bx, %dx
-# CHECK-NEXT: [2,0]     .D=====eER.    .    .   addw	%cx, %dx
-# CHECK-NEXT: [2,1]     .D======eER    .    .   movw	%ax, %dx
-# CHECK-NEXT: [2,2]     .D=======eER   .    .   xorw	%bx, %dx
-# CHECK-NEXT: [3,0]     .D========eER  .    .   addw	%cx, %dx
-# CHECK-NEXT: [3,1]     .D=========eER .    .   movw	%ax, %dx
-# CHECK-NEXT: [3,2]     .D==========eER.    .   xorw	%bx, %dx
-# CHECK-NEXT: [4,0]     . D==========eER    .   addw	%cx, %dx
-# CHECK-NEXT: [4,1]     . D===========eER   .   movw	%ax, %dx
-# CHECK-NEXT: [4,2]     . D============eER  .   xorw	%bx, %dx
-# CHECK-NEXT: [5,0]     . D=============eER .   addw	%cx, %dx
-# CHECK-NEXT: [5,1]     . D==============eER.   movw	%ax, %dx
-# CHECK-NEXT: [5,2]     . D===============eER   xorw	%bx, %dx
+# CHECK-NEXT: [0,1]     DPeER.    .    .    .   movw	%ax, %dx
+# CHECK-NEXT: [0,2]     DPPeER    .    .    .   xorw	%bx, %dx
+# CHECK-NEXT: [1,0]     DPPPeER   .    .    .   addw	%cx, %dx
+# CHECK-NEXT: [1,1]     DPPPPeER  .    .    .   movw	%ax, %dx
+# CHECK-NEXT: [1,2]     DPPPPPeER .    .    .   xorw	%bx, %dx
+# CHECK-NEXT: [2,0]     .DPPPPPeER.    .    .   addw	%cx, %dx
+# CHECK-NEXT: [2,1]     .DPPPPPPeER    .    .   movw	%ax, %dx
+# CHECK-NEXT: [2,2]     .DPPPPPPPeER   .    .   xorw	%bx, %dx
+# CHECK-NEXT: [3,0]     .DPPPPPPPPeER  .    .   addw	%cx, %dx
+# CHECK-NEXT: [3,1]     .DPPPPPPPPPeER .    .   movw	%ax, %dx
+# CHECK-NEXT: [3,2]     .DPPPPPPPPPPeER.    .   xorw	%bx, %dx
+# CHECK-NEXT: [4,0]     . DPPPPPPPPPPeER    .   addw	%cx, %dx
+# CHECK-NEXT: [4,1]     . DPPPPPPPPPPPeER   .   movw	%ax, %dx
+# CHECK-NEXT: [4,2]     . DPPPPPPPPPPPPeER  .   xorw	%bx, %dx
+# CHECK-NEXT: [5,0]     . DPPPPPPPPPPPPPeER .   addw	%cx, %dx
+# CHECK-NEXT: [5,1]     . DPPPPPPPPPPPPPPeER.   movw	%ax, %dx
+# CHECK-NEXT: [5,2]     . DPPPPPPPPPPPPPPPeER   xorw	%bx, %dx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-4.s b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-4.s
index 4ed529ee14465..f56b13f16c5e7 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-4.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-4.s
@@ -67,30 +67,31 @@ add %cx, %bx
 # CHECK-NEXT:  -      -      -     0.33    -     0.33   0.33    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addw	%cx, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          01234567
 # CHECK-NEXT: Index     0123456789          0123456789
 
 # CHECK:      [0,0]     DeeeER    .    .    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [0,1]     D===eER   .    .    .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [0,2]     D====eER  .    .    .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [1,0]     D=====eeeER    .    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [1,1]     D========eER   .    .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,2]     D=========eER  .    .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [2,0]     .D=========eeeER    .    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [2,1]     .D============eER   .    .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,2]     .D=============eER  .    .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [3,0]     .D==============eeeER    .    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [3,1]     .D=================eER   .    .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [3,2]     .D==================eER  .    .    . .   addw	%cx, %bx
-# CHECK-NEXT: [4,0]     . D==================eeeER    .    . .   imulw	%ax, %bx
-# CHECK-NEXT: [4,1]     . D=====================eER   .    . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [4,2]     . D======================eER  .    . .   addw	%cx, %bx
-# CHECK-NEXT: [5,0]     . D=======================eeeER    . .   imulw	%ax, %bx
-# CHECK-NEXT: [5,1]     . D==========================eER   . .   lzcntw	%ax, %bx
-# CHECK-NEXT: [5,2]     . D===========================eER  . .   addw	%cx, %bx
-# CHECK-NEXT: [6,0]     .  D===========================eeeER .   imulw	%ax, %bx
-# CHECK-NEXT: [6,1]     .  D==============================eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [6,2]     .  D===============================eER   addw	%cx, %bx
+# CHECK-NEXT: [0,1]     DPPPeER   .    .    .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [0,2]     DPPPPeER  .    .    .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [1,0]     DPPPPPeeeER    .    .    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [1,1]     DPPPPPPPPeER   .    .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,2]     DPPPPPPPPPeER  .    .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [2,0]     .DPPPPPPPPPeeeER    .    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [2,1]     .DPPPPPPPPPPPPeER   .    .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,2]     .DPPPPPPPPPPPPPeER  .    .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [3,0]     .DPPPPPPPPPPPPPPeeeER    .    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [3,1]     .DPPPPPPPPPPPPPPPPPeER   .    .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [3,2]     .DPPPPPPPPPPPPPPPPPPeER  .    .    . .   addw	%cx, %bx
+# CHECK-NEXT: [4,0]     . DPPPPPPPPPPPPPPPPPPeeeER    .    . .   imulw	%ax, %bx
+# CHECK-NEXT: [4,1]     . DPPPPPPPPPPPPPPPPPPPPPeER   .    . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [4,2]     . DPPPPPPPPPPPPPPPPPPPPPPeER  .    . .   addw	%cx, %bx
+# CHECK-NEXT: [5,0]     . DPPPPPPPPPPPPPPPPPPPPPPPeeeER    . .   imulw	%ax, %bx
+# CHECK-NEXT: [5,1]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPeER   . .   lzcntw	%ax, %bx
+# CHECK-NEXT: [5,2]     . DPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  . .   addw	%cx, %bx
+# CHECK-NEXT: [6,0]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeER .   imulw	%ax, %bx
+# CHECK-NEXT: [6,1]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [6,2]     .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   addw	%cx, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-5.s b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-5.s
index 58941116d31f0..8222843c3308b 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-5.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-5.s
@@ -58,17 +58,18 @@ lzcnt %ax, %bx  ## partial register stall.
 # CHECK-NEXT:  -      -      -     1.00   1.00   1.00   1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     lzcntw	%ax, %bx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    .   lzcntw	%ax, %bx
-# CHECK-NEXT: [1,0]     D=eER.    .   lzcntw	%ax, %bx
-# CHECK-NEXT: [2,0]     D==eER    .   lzcntw	%ax, %bx
-# CHECK-NEXT: [3,0]     D===eER   .   lzcntw	%ax, %bx
-# CHECK-NEXT: [4,0]     D====eER  .   lzcntw	%ax, %bx
-# CHECK-NEXT: [5,0]     D=====eER .   lzcntw	%ax, %bx
-# CHECK-NEXT: [6,0]     .D=====eER.   lzcntw	%ax, %bx
-# CHECK-NEXT: [7,0]     .D======eER   lzcntw	%ax, %bx
+# CHECK-NEXT: [1,0]     DPeER.    .   lzcntw	%ax, %bx
+# CHECK-NEXT: [2,0]     DPPeER    .   lzcntw	%ax, %bx
+# CHECK-NEXT: [3,0]     DPPPeER   .   lzcntw	%ax, %bx
+# CHECK-NEXT: [4,0]     DPPPPeER  .   lzcntw	%ax, %bx
+# CHECK-NEXT: [5,0]     DPPPPPeER .   lzcntw	%ax, %bx
+# CHECK-NEXT: [6,0]     .DPPPPPeER.   lzcntw	%ax, %bx
+# CHECK-NEXT: [7,0]     .DPPPPPPeER   lzcntw	%ax, %bx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-6.s b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-6.s
index fdbf4d99fbf6e..1e1b72ae7c080 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-6.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-6.s
@@ -69,21 +69,22 @@ lzcnt 2(%rsp), %cx
 # CHECK-NEXT: 0.33   0.33   0.33   0.33    -     0.33   0.33    -      -      -      -      -      -      -      -     0.33   0.33   0.33   0.33   0.33   0.33    -      -     lzcntw	2(%rsp), %cx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          0123456
 
 # CHECK:      [0,0]     DeeeER    .    .    .    ..   imull	%edx, %ecx
 # CHECK-NEXT: [0,1]     DeeeeeER  .    .    .    ..   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [0,2]     D=eeeeeER .    .    .    ..   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [1,0]     D======eeeER   .    .    ..   imull	%edx, %ecx
-# CHECK-NEXT: [1,1]     D======eeeeeER .    .    ..   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [1,2]     D=======eeeeeER.    .    ..   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [2,0]     .D===========eeeER  .    ..   imull	%edx, %ecx
-# CHECK-NEXT: [2,1]     .D===========eeeeeER.    ..   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [2,2]     .D============eeeeeER    ..   lzcntw	2(%rsp), %cx
-# CHECK-NEXT: [3,0]     .D=================eeeER ..   imull	%edx, %ecx
-# CHECK-NEXT: [3,1]     .D=================eeeeeER.   lzcntw	(%rsp), %cx
-# CHECK-NEXT: [3,2]     .D==================eeeeeER   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [0,2]     DPeeeeeER .    .    .    ..   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [1,0]     DPPPPPPeeeER   .    .    ..   imull	%edx, %ecx
+# CHECK-NEXT: [1,1]     DPPPPPPeeeeeER .    .    ..   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [1,2]     DPPPPPPPeeeeeER.    .    ..   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [2,0]     .DPPPPPPPPPPPeeeER  .    ..   imull	%edx, %ecx
+# CHECK-NEXT: [2,1]     .DPPPPPPPPPPPeeeeeER.    ..   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [2,2]     .DPPPPPPPPPPPPeeeeeER    ..   lzcntw	2(%rsp), %cx
+# CHECK-NEXT: [3,0]     .DPPPPPPPPPPPPPPPPPeeeER ..   imull	%edx, %ecx
+# CHECK-NEXT: [3,1]     .DPPPPPPPPPPPPPPPPPeeeeeER.   lzcntw	(%rsp), %cx
+# CHECK-NEXT: [3,2]     .DPPPPPPPPPPPPPPPPPPeeeeeER   lzcntw	2(%rsp), %cx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-7.s b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-7.s
index d782e5dd59783..ee0e16a3cc0b6 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-7.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update-7.s
@@ -33,11 +33,12 @@ addq  %rcx, %rdx
 # CHECK-NEXT:  1      1     0.25                        addq	%rcx, %rdx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   imulq	%rax, %rcx
-# CHECK-NEXT: [0,1]     D===eER.   addl	%edx, %ecx
-# CHECK-NEXT: [0,2]     D====eER   addq	%rcx, %rdx
+# CHECK-NEXT: [0,1]     DPPPeER.   addl	%edx, %ecx
+# CHECK-NEXT: [0,2]     DPPPPeER   addq	%rcx, %rdx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update.s b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update.s
index 2dd1b4b337eee..f7bddc506ecde 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/partial-reg-update.s
@@ -29,11 +29,12 @@ add  %ecx, %ebx
 # CHECK-NEXT:  1      1     0.25                        addl	%ecx, %ebx
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234567
 
 # CHECK:      [0,0]     DeeeER .   imulw	%ax, %cx
-# CHECK-NEXT: [0,1]     D===eER.   addb	%al, %cl
-# CHECK-NEXT: [0,2]     D====eER   addl	%ecx, %ebx
+# CHECK-NEXT: [0,1]     DPPPeER.   addb	%al, %cl
+# CHECK-NEXT: [0,2]     DPPPPeER   addl	%ecx, %ebx
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-avx-xmm.s b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-avx-xmm.s
index f3e515ce7e210..eb7b589b1e8aa 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-avx-xmm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-avx-xmm.s
@@ -220,6 +220,7 @@ vmovdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovaps	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -514,6 +515,7 @@ vmovdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovups	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -808,6 +810,7 @@ vmovdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovapd	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1102,6 +1105,7 @@ vmovdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovupd	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1396,6 +1400,7 @@ vmovdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovdqa	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1690,6 +1695,7 @@ vmovdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovdqu	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-avx-ymm.s b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-avx-ymm.s
index a484a7562fdcb..965f8ce1b89f5 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-avx-ymm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-avx-ymm.s
@@ -220,6 +220,7 @@ vmovdqu %ymm15, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovaps	%ymm15, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -514,6 +515,7 @@ vmovdqu %ymm15, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovups	%ymm15, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -808,6 +810,7 @@ vmovdqu %ymm15, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovapd	%ymm15, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1102,6 +1105,7 @@ vmovdqu %ymm15, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovupd	%ymm15, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1396,6 +1400,7 @@ vmovdqu %ymm15, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovdqa	%ymm15, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1690,6 +1695,7 @@ vmovdqu %ymm15, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vmovdqu	%ymm15, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-gpr.s b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-gpr.s
index eb20d13e8c944..0f598e8b5eeac 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-gpr.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-gpr.s
@@ -172,6 +172,7 @@ xchgq %r15, %rax
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movl	%r15d, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -440,6 +441,7 @@ xchgq %r15, %rax
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movq	%r15, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -708,6 +710,7 @@ xchgq %r15, %rax
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     xchgl	%r15d, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234567
 
@@ -976,6 +979,7 @@ xchgq %r15, %rax
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     xchgq	%r15, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          01234567
 
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-mmx.s b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-mmx.s
index e17d6717e1366..f5147a3c93eb4 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-mmx.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-mmx.s
@@ -93,86 +93,87 @@ movq %mm7, %mm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -     movq	%mm7, %mm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789
 
 # CHECK:      [0,0]     DeER .    .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [0,1]     D=eER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [0,2]     D==eER    .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [0,3]     D===eER   .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [0,4]     D====eER  .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [0,5]     D=====eER .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [0,6]     .D=====eER.    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [0,7]     .D======eER    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm7, %mm0
-# CHECK-NEXT: [1,0]     .D=======eER   .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [1,1]     .D========eER  .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [1,2]     .D=========eER .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [1,3]     .D==========eER.    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [1,4]     . D==========eER    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [1,5]     . D===========eER   .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [1,6]     . D============eER  .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [1,7]     . D=============eER .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm7, %mm0
-# CHECK-NEXT: [2,0]     . D==============eER.    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [2,1]     . D===============eER    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [2,2]     .  D===============eER   .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [2,3]     .  D================eER  .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [2,4]     .  D=================eER .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [2,5]     .  D==================eER.    .    .    .    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [2,6]     .  D===================eER    .    .    .    .    .    .    .    .    .    .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [2,7]     .  D====================eER   .    .    .    .    .    .    .    .    .    .   .   movq	%mm7, %mm0
-# CHECK-NEXT: [3,0]     .   D====================eER  .    .    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [3,1]     .   D=====================eER .    .    .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [3,2]     .   D======================eER.    .    .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [3,3]     .   D=======================eER    .    .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [3,4]     .   D========================eER   .    .    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [3,5]     .   D=========================eER  .    .    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [3,6]     .    D=========================eER .    .    .    .    .    .    .    .    .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [3,7]     .    D==========================eER.    .    .    .    .    .    .    .    .   .   movq	%mm7, %mm0
-# CHECK-NEXT: [4,0]     .    D===========================eER    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [4,1]     .    D============================eER   .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [4,2]     .    D=============================eER  .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [4,3]     .    D==============================eER .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [4,4]     .    .D==============================eER.    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [4,5]     .    .D===============================eER    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [4,6]     .    .D================================eER   .    .    .    .    .    .    .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [4,7]     .    .D=================================eER  .    .    .    .    .    .    .   .   movq	%mm7, %mm0
-# CHECK-NEXT: [5,0]     .    .D==================================eER .    .    .    .    .    .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [5,1]     .    .D===================================eER.    .    .    .    .    .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [5,2]     .    . D===================================eER    .    .    .    .    .    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [5,3]     .    . D====================================eER   .    .    .    .    .    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [5,4]     .    . D=====================================eER  .    .    .    .    .    .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [5,5]     .    . D======================================eER .    .    .    .    .    .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [5,6]     .    . D=======================================eER.    .    .    .    .    .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [5,7]     .    . D========================================eER    .    .    .    .    .   .   movq	%mm7, %mm0
-# CHECK-NEXT: [6,0]     .    .  D========================================eER   .    .    .    .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [6,1]     .    .  D=========================================eER  .    .    .    .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [6,2]     .    .  D==========================================eER .    .    .    .    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [6,3]     .    .  D===========================================eER.    .    .    .    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [6,4]     .    .  D============================================eER    .    .    .    .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [6,5]     .    .  D=============================================eER   .    .    .    .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [6,6]     .    .   D=============================================eER  .    .    .    .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [6,7]     .    .   D==============================================eER .    .    .    .   .   movq	%mm7, %mm0
-# CHECK-NEXT: [7,0]     .    .   D===============================================eER.    .    .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [7,1]     .    .   D================================================eER    .    .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [7,2]     .    .   D=================================================eER   .    .    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [7,3]     .    .   D==================================================eER  .    .    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [7,4]     .    .    D==================================================eER .    .    .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [7,5]     .    .    D===================================================eER.    .    .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [7,6]     .    .    D====================================================eER    .    .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [7,7]     .    .    D=====================================================eER   .    .   .   movq	%mm7, %mm0
-# CHECK-NEXT: [8,0]     .    .    D======================================================eER  .    .   .   movq	%mm0, %mm1
-# CHECK-NEXT: [8,1]     .    .    D=======================================================eER .    .   .   movq	%mm1, %mm2
-# CHECK-NEXT: [8,2]     .    .    .D=======================================================eER.    .   .   movq	%mm2, %mm3
-# CHECK-NEXT: [8,3]     .    .    .D========================================================eER    .   .   movq	%mm3, %mm4
-# CHECK-NEXT: [8,4]     .    .    .D=========================================================eER   .   .   movq	%mm4, %mm5
-# CHECK-NEXT: [8,5]     .    .    .D==========================================================eER  .   .   movq	%mm5, %mm6
-# CHECK-NEXT: [8,6]     .    .    .D===========================================================eER .   .   movq	%mm6, %mm7
-# CHECK-NEXT: [8,7]     .    .    .D============================================================eER.   .   movq	%mm7, %mm0
-# CHECK-NEXT: [9,0]     .    .    . D============================================================eER   .   movq	%mm0, %mm1
-# CHECK-NEXT: [9,1]     .    .    . D=============================================================eER  .   movq	%mm1, %mm2
-# CHECK-NEXT: [9,2]     .    .    . D==============================================================eER .   movq	%mm2, %mm3
-# CHECK-NEXT: [9,3]     .    .    . D===============================================================eER.   movq	%mm3, %mm4
-# CHECK-NEXT: [9,4]     .    .    .  D===============================================================eER   movq	%mm4, %mm5
+# CHECK-NEXT: [0,1]     DPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [0,2]     DPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [0,3]     DPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [0,4]     DPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [0,5]     DPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [0,6]     .DPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [0,7]     .DPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm7, %mm0
+# CHECK-NEXT: [1,0]     .DPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
+# CHECK-NEXT: [1,1]     .DPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [1,2]     .DPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [1,3]     .DPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [1,4]     . DPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [1,5]     . DPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [1,6]     . DPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [1,7]     . DPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm7, %mm0
+# CHECK-NEXT: [2,0]     . DPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
+# CHECK-NEXT: [2,1]     . DPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [2,2]     .  DPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [2,3]     .  DPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [2,4]     .  DPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [2,5]     .  DPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [2,6]     .  DPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .    .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [2,7]     .  DPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .    .   .   movq	%mm7, %mm0
+# CHECK-NEXT: [3,0]     .   DPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
+# CHECK-NEXT: [3,1]     .   DPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [3,2]     .   DPPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [3,3]     .   DPPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [3,4]     .   DPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [3,5]     .   DPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [3,6]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .    .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [3,7]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .    .   .   movq	%mm7, %mm0
+# CHECK-NEXT: [4,0]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .    .   .   movq	%mm0, %mm1
+# CHECK-NEXT: [4,1]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [4,2]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [4,3]     .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [4,4]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .    .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [4,5]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .    .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [4,6]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .    .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [4,7]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .    .   .   movq	%mm7, %mm0
+# CHECK-NEXT: [5,0]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .    .   .   movq	%mm0, %mm1
+# CHECK-NEXT: [5,1]     .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [5,2]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [5,3]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [5,4]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .    .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [5,5]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .    .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [5,6]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .    .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [5,7]     .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .    .   .   movq	%mm7, %mm0
+# CHECK-NEXT: [6,0]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .    .   .   movq	%mm0, %mm1
+# CHECK-NEXT: [6,1]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [6,2]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [6,3]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [6,4]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .    .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [6,5]     .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .    .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [6,6]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .    .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [6,7]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .    .    .    .   .   movq	%mm7, %mm0
+# CHECK-NEXT: [7,0]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.    .    .    .   .   movq	%mm0, %mm1
+# CHECK-NEXT: [7,1]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .    .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [7,2]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [7,3]     .    .   DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [7,4]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .    .    .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [7,5]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.    .    .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [7,6]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .    .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [7,7]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .    .   .   movq	%mm7, %mm0
+# CHECK-NEXT: [8,0]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .    .   .   movq	%mm0, %mm1
+# CHECK-NEXT: [8,1]     .    .    DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .    .   .   movq	%mm1, %mm2
+# CHECK-NEXT: [8,2]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.    .   .   movq	%mm2, %mm3
+# CHECK-NEXT: [8,3]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER    .   .   movq	%mm3, %mm4
+# CHECK-NEXT: [8,4]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .   .   movq	%mm4, %mm5
+# CHECK-NEXT: [8,5]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .   .   movq	%mm5, %mm6
+# CHECK-NEXT: [8,6]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .   .   movq	%mm6, %mm7
+# CHECK-NEXT: [8,7]     .    .    .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.   .   movq	%mm7, %mm0
+# CHECK-NEXT: [9,0]     .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   .   movq	%mm0, %mm1
+# CHECK-NEXT: [9,1]     .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER  .   movq	%mm1, %mm2
+# CHECK-NEXT: [9,2]     .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER .   movq	%mm2, %mm3
+# CHECK-NEXT: [9,3]     .    .    . DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER.   movq	%mm3, %mm4
+# CHECK-NEXT: [9,4]     .    .    .  DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeER   movq	%mm4, %mm5
 # CHECK-NEXT: Truncated display due to cycle limit
 
 # CHECK:      Average Wait times (based on the timeline view):
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-sse-xmm.s b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-sse-xmm.s
index b45fd172bd555..489f65ca7dfef 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-sse-xmm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-sse-xmm.s
@@ -220,6 +220,7 @@ movdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movaps	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -514,6 +515,7 @@ movdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movups	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -808,6 +810,7 @@ movdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movapd	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1102,6 +1105,7 @@ movdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movupd	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1396,6 +1400,7 @@ movdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movdqa	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
@@ -1690,6 +1695,7 @@ movdqu %xmm15, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     movdqu	%xmm15, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234567
 
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-x87.s b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-x87.s
index 0465d413a854b..b9ef2e8457ee8 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-x87.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/reg-move-elimination-x87.s
@@ -100,6 +100,7 @@ fxch %st(0)
 # CHECK-NEXT:  -      -      -     1.00   1.00   1.00   1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     fxch	%st(0)
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789          0123456789          0123456789          0123456789
 # CHECK-NEXT: Index     0123456789          0123456789          0123456789          0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s
index ed4e8f90dd7b0..cdc9f667e2cf3 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s
@@ -164,6 +164,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vxorps	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vxorps	%xmm0, %xmm0, %xmm0
@@ -255,6 +256,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vxorpd	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vxorpd	%xmm0, %xmm0, %xmm0
@@ -346,6 +348,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vandnps	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vandnps	%xmm0, %xmm0, %xmm0
@@ -437,6 +440,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vandnpd	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vandnpd	%xmm0, %xmm0, %xmm0
@@ -528,6 +532,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpxor	%xmm0, %xmm0, %xmm0
@@ -619,6 +624,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpandn	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpandn	%xmm0, %xmm0, %xmm0
@@ -710,6 +716,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpsubb	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpsubb	%xmm0, %xmm0, %xmm0
@@ -801,6 +808,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpsubw	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpsubw	%xmm0, %xmm0, %xmm0
@@ -892,6 +900,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpsubd	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpsubd	%xmm0, %xmm0, %xmm0
@@ -983,6 +992,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpsubq	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpsubq	%xmm0, %xmm0, %xmm0
@@ -1074,12 +1084,13 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpsubsb	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   vpxor	%xmm1, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   vpxor	%xmm1, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   vpsubsb	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   vpxor	%xmm1, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1165,12 +1176,13 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpsubsw	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   vpxor	%xmm1, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   vpxor	%xmm1, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   vpsubsw	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   vpxor	%xmm1, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1256,12 +1268,13 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpsubusb	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   vpxor	%xmm1, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   vpxor	%xmm1, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   vpsubusb	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   vpxor	%xmm1, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1347,12 +1360,13 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpsubusw	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   vpxor	%xmm1, %xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   vpxor	%xmm1, %xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   vpsubusw	%xmm0, %xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   vpxor	%xmm1, %xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   vpxor	%xmm1, %xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1438,6 +1452,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpaddb	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpcmpgtb	%xmm0, %xmm0, %xmm0
@@ -1529,6 +1544,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpaddw	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpcmpgtw	%xmm0, %xmm0, %xmm0
@@ -1620,6 +1636,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpaddd	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpcmpgtd	%xmm0, %xmm0, %xmm0
@@ -1711,6 +1728,7 @@ vpaddq %xmm0, %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpaddq	%xmm0, %xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpcmpgtq	%xmm0, %xmm0, %xmm0
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-ymm.s b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-ymm.s
index 24043369c6f14..b4c9ae0ab5613 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-ymm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-ymm.s
@@ -174,6 +174,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vxorps	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vxorps	%ymm0, %ymm0, %ymm0
@@ -265,6 +266,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vxorpd	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vxorpd	%ymm0, %ymm0, %ymm0
@@ -356,6 +358,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vandnps	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vandnps	%ymm0, %ymm0, %ymm0
@@ -447,6 +450,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vandnpd	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vandnpd	%ymm0, %ymm0, %ymm0
@@ -538,6 +542,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpxor	%ymm0, %ymm0, %ymm0
@@ -629,6 +634,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpandn	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpandn	%ymm0, %ymm0, %ymm0
@@ -720,6 +726,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpsubb	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpsubb	%ymm0, %ymm0, %ymm0
@@ -811,6 +818,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpsubw	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpsubw	%ymm0, %ymm0, %ymm0
@@ -902,6 +910,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpsubd	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpsubd	%ymm0, %ymm0, %ymm0
@@ -993,6 +1002,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpsubq	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpsubq	%ymm0, %ymm0, %ymm0
@@ -1084,12 +1094,13 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpsubsb	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D=eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPeER   vpxor	%ymm1, %ymm0, %ymm0
 # CHECK-NEXT: [1,0]     DeE-R   vpsubsb	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPeER   vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1175,12 +1186,13 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpsubsw	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D=eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPeER   vpxor	%ymm1, %ymm0, %ymm0
 # CHECK-NEXT: [1,0]     DeE-R   vpsubsw	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPeER   vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1266,12 +1278,13 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpsubusb	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D=eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPeER   vpxor	%ymm1, %ymm0, %ymm0
 # CHECK-NEXT: [1,0]     DeE-R   vpsubusb	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPeER   vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1357,12 +1370,13 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   vpsubusw	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D=eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPeER   vpxor	%ymm1, %ymm0, %ymm0
 # CHECK-NEXT: [1,0]     DeE-R   vpsubusw	%ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPeER   vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1448,6 +1462,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpaddb	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpcmpgtb	%ymm0, %ymm0, %ymm0
@@ -1539,6 +1554,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpaddw	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpcmpgtw	%ymm0, %ymm0, %ymm0
@@ -1630,6 +1646,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpaddd	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpcmpgtd	%ymm0, %ymm0, %ymm0
@@ -1721,6 +1738,7 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     vpaddq	%ymm0, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123
 
 # CHECK:      [0,0]     DR .   vpcmpgtq	%ymm0, %ymm0, %ymm0
@@ -1812,13 +1830,14 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.33    -     0.33   0.33    -      -      -      -      -      -      -      -      -      -      -     vxorps	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .   vperm2f128	$136, %ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D===eER   .   vxorps	%ymm1, %ymm0, %ymm0
-# CHECK-NEXT: [1,0]     D====eeeER.   vperm2f128	$136, %ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=======eER   vxorps	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPPPeER   .   vxorps	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [1,0]     DPPPPeeeER.   vperm2f128	$136, %ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPPPPPPPeER   vxorps	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1904,13 +1923,14 @@ vpxor %ymm1, %ymm0, %ymm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.33    -     0.33   0.33    -      -      -      -      -      -      -      -      -      -      -     vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeeeER    .   vperm2i128	$136, %ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [0,1]     D===eER   .   vpxor	%ymm1, %ymm0, %ymm0
-# CHECK-NEXT: [1,0]     D====eeeER.   vperm2i128	$136, %ymm0, %ymm0, %ymm0
-# CHECK-NEXT: [1,1]     D=======eER   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [0,1]     DPPPeER   .   vpxor	%ymm1, %ymm0, %ymm0
+# CHECK-NEXT: [1,0]     DPPPPeeeER.   vperm2i128	$136, %ymm0, %ymm0, %ymm0
+# CHECK-NEXT: [1,1]     DPPPPPPPeER   vpxor	%ymm1, %ymm0, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-gpr.s b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-gpr.s
index 4d648f7fb9dea..5f8d1e5c692fd 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-gpr.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-gpr.s
@@ -94,6 +94,7 @@ addq %rax, %rax
 # CHECK-NEXT:  -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DR   ..   xorl	%eax, %eax
@@ -201,6 +202,7 @@ addq %rax, %rax
 # CHECK-NEXT:  -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addq	%rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DR   ..   xorq	%rax, %rax
@@ -308,6 +310,7 @@ addq %rax, %rax
 # CHECK-NEXT:  -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addl	%eax, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DR   ..   subl	%eax, %eax
@@ -415,6 +418,7 @@ addq %rax, %rax
 # CHECK-NEXT:  -      -      -     0.25   0.25   0.25   0.25    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     addq	%rax, %rax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     0123456
 
 # CHECK:      [0,0]     DR   ..   subq	%rax, %rax
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-sse-xmm.s b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-sse-xmm.s
index aca39c52f36e5..abe7d933de1b4 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-sse-xmm.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-sse-xmm.s
@@ -164,12 +164,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     xorps	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   xorps	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   xorps	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   xorps	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   xorps	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   xorps	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   xorps	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -255,12 +256,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     xorpd	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   xorpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   xorpd	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   xorpd	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   xorpd	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   xorpd	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   xorpd	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -346,12 +348,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     andnps	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   andnps	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   andnps	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   andnps	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   andnps	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   andnps	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   andnps	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -437,12 +440,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     andnpd	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   andnpd	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   andnpd	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   andnpd	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   andnpd	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   andnpd	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   andnpd	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -528,12 +532,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     pxor	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pxor	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   pxor	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   pxor	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   pxor	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -619,12 +624,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     pandn	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pandn	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   pandn	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   pandn	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   pandn	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   pandn	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   pandn	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -710,12 +716,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     psubb	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   psubb	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   psubb	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   psubb	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   psubb	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   psubb	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   psubb	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -801,12 +808,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     psubw	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   psubw	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   psubw	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   psubw	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   psubw	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   psubw	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   psubw	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -892,12 +900,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     psubd	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   psubd	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   psubd	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   psubd	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   psubd	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   psubd	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   psubd	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -983,12 +992,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50    -     0.25   0.25    -      -      -      -      -      -      -      -      -      -      -     psubq	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   psubq	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   psubq	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   psubq	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   psubq	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   psubq	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   psubq	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1074,12 +1084,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     pxor	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   psubsb	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   pxor	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   psubsb	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   pxor	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1165,12 +1176,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     pxor	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   psubsw	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   pxor	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   psubsw	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   pxor	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1256,12 +1268,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     pxor	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   psubusb	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   pxor	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   psubusb	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   pxor	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1347,12 +1360,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -      -      -      -     pxor	%xmm0, %xmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   psubusw	%xmm1, %xmm1
-# CHECK-NEXT: [0,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DPeER   pxor	%xmm0, %xmm1
 # CHECK-NEXT: [1,0]     DeE-R   psubusw	%xmm1, %xmm1
-# CHECK-NEXT: [1,1]     D=eER   pxor	%xmm0, %xmm1
+# CHECK-NEXT: [1,1]     DPeER   pxor	%xmm0, %xmm1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1438,12 +1452,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddb	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpgtb	%xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   paddb	%xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   paddb	%xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpgtb	%xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   paddb	%xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   paddb	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1529,12 +1544,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddw	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpgtw	%xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   paddw	%xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   paddw	%xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpgtw	%xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   paddw	%xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   paddw	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1620,12 +1636,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddd	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpgtd	%xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   paddd	%xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   paddd	%xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpgtd	%xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   paddd	%xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   paddd	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1711,12 +1728,13 @@ paddq %xmm0, %xmm0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.25   0.25    -     0.50    -      -      -      -      -      -      -      -      -      -      -     paddq	%xmm0, %xmm0
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     01234
 
 # CHECK:      [0,0]     DeER.   pcmpgtq	%xmm0, %xmm0
-# CHECK-NEXT: [0,1]     D=eER   paddq	%xmm0, %xmm0
+# CHECK-NEXT: [0,1]     DPeER   paddq	%xmm0, %xmm0
 # CHECK-NEXT: [1,0]     DeE-R   pcmpgtq	%xmm0, %xmm0
-# CHECK-NEXT: [1,1]     D=eER   paddq	%xmm0, %xmm0
+# CHECK-NEXT: [1,1]     DPeER   paddq	%xmm0, %xmm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver4/independent-load-stores.s b/llvm/test/tools/llvm-mca/X86/Znver4/independent-load-stores.s
index 1b487e6b1b9c7..3c228b66a777b 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver4/independent-load-stores.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver4/independent-load-stores.s
@@ -94,6 +94,7 @@
 # ALL-NEXT:      0.66   0.66   0.68   0.50    -     0.50    -      -      -      -      -      -      -      -      -     0.66   0.66   0.68   0.33   0.33   0.34   1.00    -     addq	$44, 640(%r14)
 
 # ALL:           Timeline view:
+# ALL-NEXT:      D: Instruction dispatched
 
 # NOALIAS-NEXT:                      01234
 # NOALIAS-NEXT:  Index     0123456789
@@ -104,24 +105,24 @@
 # NOALIAS:       [0,0]     DeeeeeeER .   .   addq	$44, 64(%r14)
 # NOALIAS-NEXT:  [0,1]     DeeeeeeER .   .   addq	$44, 128(%r14)
 # NOALIAS-NEXT:  [0,2]     D=eeeeeeER.   .   addq	$44, 192(%r14)
-# NOALIAS-NEXT:  [0,3]     D==eeeeeeER   .   addq	$44, 256(%r14)
-# NOALIAS-NEXT:  [0,4]     D==eeeeeeER   .   addq	$44, 320(%r14)
-# NOALIAS-NEXT:  [0,5]     D===eeeeeeER  .   addq	$44, 384(%r14)
-# NOALIAS-NEXT:  [0,6]     .D===eeeeeeER .   addq	$44, 448(%r14)
-# NOALIAS-NEXT:  [0,7]     .D===eeeeeeER .   addq	$44, 512(%r14)
-# NOALIAS-NEXT:  [0,8]     .D====eeeeeeER.   addq	$44, 576(%r14)
-# NOALIAS-NEXT:  [0,9]     .D=====eeeeeeER   addq	$44, 640(%r14)
+# NOALIAS-NEXT:  [0,3]     DP=eeeeeeER   .   addq	$44, 256(%r14)
+# NOALIAS-NEXT:  [0,4]     DPPeeeeeeER   .   addq	$44, 320(%r14)
+# NOALIAS-NEXT:  [0,5]     DPP=eeeeeeER  .   addq	$44, 384(%r14)
+# NOALIAS-NEXT:  [0,6]     .DPP=eeeeeeER .   addq	$44, 448(%r14)
+# NOALIAS-NEXT:  [0,7]     .DPPPeeeeeeER .   addq	$44, 512(%r14)
+# NOALIAS-NEXT:  [0,8]     .DPPP=eeeeeeER.   addq	$44, 576(%r14)
+# NOALIAS-NEXT:  [0,9]     .DPPPP=eeeeeeER   addq	$44, 640(%r14)
 
 # YESALIAS:      [0,0]     DeeeeeeER .    .    .    .    .    .    .    .    .    .    . .   addq	$44, 64(%r14)
-# YESALIAS-NEXT: [0,1]     D======eeeeeeER.    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
-# YESALIAS-NEXT: [0,2]     D============eeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
-# YESALIAS-NEXT: [0,3]     D==================eeeeeeER   .    .    .    .    .    .    . .   addq	$44, 256(%r14)
-# YESALIAS-NEXT: [0,4]     D========================eeeeeeER  .    .    .    .    .    . .   addq	$44, 320(%r14)
-# YESALIAS-NEXT: [0,5]     D==============================eeeeeeER .    .    .    .    . .   addq	$44, 384(%r14)
-# YESALIAS-NEXT: [0,6]     .D===================================eeeeeeER.    .    .    . .   addq	$44, 448(%r14)
-# YESALIAS-NEXT: [0,7]     .D=========================================eeeeeeER    .    . .   addq	$44, 512(%r14)
-# YESALIAS-NEXT: [0,8]     .D===============================================eeeeeeER   . .   addq	$44, 576(%r14)
-# YESALIAS-NEXT: [0,9]     .D=====================================================eeeeeeER   addq	$44, 640(%r14)
+# YESALIAS-NEXT: [0,1]     DPPPPPPeeeeeeER.    .    .    .    .    .    .    .    .    . .   addq	$44, 128(%r14)
+# YESALIAS-NEXT: [0,2]     DPPPPPPPPPPPPeeeeeeER    .    .    .    .    .    .    .    . .   addq	$44, 192(%r14)
+# YESALIAS-NEXT: [0,3]     DPPPPPPPPPPPPPPPPPPeeeeeeER   .    .    .    .    .    .    . .   addq	$44, 256(%r14)
+# YESALIAS-NEXT: [0,4]     DPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER  .    .    .    .    .    . .   addq	$44, 320(%r14)
+# YESALIAS-NEXT: [0,5]     DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER .    .    .    .    . .   addq	$44, 384(%r14)
+# YESALIAS-NEXT: [0,6]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER.    .    .    . .   addq	$44, 448(%r14)
+# YESALIAS-NEXT: [0,7]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER    .    . .   addq	$44, 512(%r14)
+# YESALIAS-NEXT: [0,8]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER   . .   addq	$44, 576(%r14)
+# YESALIAS-NEXT: [0,9]     .DPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPeeeeeeER   addq	$44, 640(%r14)
 
 # ALL:           Average Wait times (based on the timeline view):
 # ALL-NEXT:      [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/Znver4/partially-overlapping-group-resources.s b/llvm/test/tools/llvm-mca/X86/Znver4/partially-overlapping-group-resources.s
index 7705c900ddff1..5645c7db2e498 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver4/partially-overlapping-group-resources.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver4/partially-overlapping-group-resources.s
@@ -72,6 +72,7 @@ vpxord zmm1, zmm1, zmm1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpxord	zmm1, zmm1, zmm1
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT: Index     012345678
 
 # CHECK:      [0,0]     DeeeeeeER   vpconflictd	zmm0, zmm3
diff --git a/llvm/test/tools/llvm-mca/X86/Znver4/zero-idioms.s b/llvm/test/tools/llvm-mca/X86/Znver4/zero-idioms.s
index 30df2ed0a926d..fd27c89f57a4f 100644
--- a/llvm/test/tools/llvm-mca/X86/Znver4/zero-idioms.s
+++ b/llvm/test/tools/llvm-mca/X86/Znver4/zero-idioms.s
@@ -504,6 +504,7 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpxorq	%zmm19, %zmm19, %zmm21
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     0123456789
 # CHECK-NEXT: Index     0123456789          01234
 
@@ -512,8 +513,8 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,2]     DR   .    .    .    .   .   xorl	%eax, %eax
 # CHECK-NEXT: [0,3]     DR   .    .    .    .   .   xorq	%rax, %rax
 # CHECK-NEXT: [0,4]     DeER .    .    .    .   .   pcmpgtb	%mm2, %mm2
-# CHECK-NEXT: [0,5]     D=eER.    .    .    .   .   pcmpgtd	%mm2, %mm2
-# CHECK-NEXT: [0,6]     .D=eER    .    .    .   .   pcmpgtw	%mm2, %mm2
+# CHECK-NEXT: [0,5]     DPeER.    .    .    .   .   pcmpgtd	%mm2, %mm2
+# CHECK-NEXT: [0,6]     .DPeER    .    .    .   .   pcmpgtw	%mm2, %mm2
 # CHECK-NEXT: [0,7]     .DeE-R    .    .    .   .   pcmpgtb	%xmm2, %xmm2
 # CHECK-NEXT: [0,8]     .DeE-R    .    .    .   .   pcmpgtd	%xmm2, %xmm2
 # CHECK-NEXT: [0,9]     .DeE-R    .    .    .   .   pcmpgtq	%xmm2, %xmm2
@@ -535,9 +536,9 @@ vpxorq  %zmm19, %zmm19, %zmm21
 # CHECK-NEXT: [0,25]    .   D--R  .    .    .   .   vpcmpgtq	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,26]    .   D--R  .    .    .   .   vpcmpgtw	%ymm3, %ymm3, %ymm5
 # CHECK-NEXT: [0,27]    .   DeER  .    .    .   .   psubb	%mm2, %mm2
-# CHECK-NEXT: [0,28]    .   D=eER .    .    .   .   psubd	%mm2, %mm2
-# CHECK-NEXT: [0,29]    .   D==eER.    .    .   .   psubq	%mm2, %mm2
-# CHECK-NEXT: [0,30]    .    D==eER    .    .   .   psubw	%mm2, %mm2
+# CHECK-NEXT: [0,28]    .   DPeER .    .    .   .   psubd	%mm2, %mm2
+# CHECK-NEXT: [0,29]    .   DPPeER.    .    .   .   psubq	%mm2, %mm2
+# CHECK-NEXT: [0,30]    .    DPPeER    .    .   .   psubw	%mm2, %mm2
 # CHECK-NEXT: [0,31]    .    DeE--R    .    .   .   psubb	%xmm2, %xmm2
 # CHECK-NEXT: [0,32]    .    DeE--R    .    .   .   psubd	%xmm2, %xmm2
 # CHECK-NEXT: [0,33]    .    DeE--R    .    .   .   psubq	%xmm2, %xmm2
diff --git a/llvm/test/tools/llvm-mca/X86/bextr-read-after-ld.s b/llvm/test/tools/llvm-mca/X86/bextr-read-after-ld.s
index 25f943f7d98b9..40da28f82ac17 100644
--- a/llvm/test/tools/llvm-mca/X86/bextr-read-after-ld.s
+++ b/llvm/test/tools/llvm-mca/X86/bextr-read-after-ld.s
@@ -102,6 +102,7 @@ bextrl	%esi, (%rdi), %eax
 # ZNVER2-NEXT:   2      5     0.33    *                   bextrl	%esi, (%rdi), %eax
 
 # ALL:          Timeline view:
+# ALL-NEXT:     D: Instruction dispatched
 
 # BDVER2-NEXT:  Index     012345678
 # BDWELL-NEXT:  Index     0123456789
diff --git a/llvm/test/tools/llvm-mca/X86/bzhi-read-after-ld.s b/llvm/test/tools/llvm-mca/X86/bzhi-read-after-ld.s
index 281a5a34a5c6b..22ed32f2e0559 100644
--- a/llvm/test/tools/llvm-mca/X86/bzhi-read-after-ld.s
+++ b/llvm/test/tools/llvm-mca/X86/bzhi-read-after-ld.s
@@ -63,6 +63,7 @@ bzhil	%esi, (%rdi), %eax
 # ZNVER2-NEXT:   2      5     0.33    *                   bzhil	%esi, (%rdi), %eax
 
 # ALL:          Timeline view:
+# ALL-NEXT:     D: Instruction dispatched
 
 # BDWELL-NEXT:  Index     012345678
 # HASWELL-NEXT: Index     012345678
diff --git a/llvm/test/tools/llvm-mca/X86/fma3-read-after-ld-1.s b/llvm/test/tools/llvm-mca/X86/fma3-read-after-ld-1.s
index 09a47e7747e44..c6523a8e54c0c 100644
--- a/llvm/test/tools/llvm-mca/X86/fma3-read-after-ld-1.s
+++ b/llvm/test/tools/llvm-mca/X86/fma3-read-after-ld-1.s
@@ -50,6 +50,7 @@ vfmadd213ps (%rdi), %xmm1, %xmm2
 # ZNVER1-NEXT:  Block RThroughput: 0.5
 
 # ALL:          Timeline view:
+# ALL-NEXT:     D: Instruction dispatched
 
 # BDWELL-NEXT:                      012
 # HASWELL-NEXT:                     0123
diff --git a/llvm/test/tools/llvm-mca/X86/fma3-read-after-ld-2.s b/llvm/test/tools/llvm-mca/X86/fma3-read-after-ld-2.s
index cf1d6847384df..5a7cddd544e11 100644
--- a/llvm/test/tools/llvm-mca/X86/fma3-read-after-ld-2.s
+++ b/llvm/test/tools/llvm-mca/X86/fma3-read-after-ld-2.s
@@ -50,6 +50,7 @@ vfmadd213ps (%rdi), %xmm1, %xmm2
 # ZNVER1-NEXT:  Block RThroughput: 0.5
 
 # ALL:          Timeline view:
+# ALL-NEXT:     D: Instruction dispatched
 
 # BDWELL-NEXT:                      012
 # HASWELL-NEXT:                     0123
diff --git a/llvm/test/tools/llvm-mca/X86/option-all-views-1.s b/llvm/test/tools/llvm-mca/X86/option-all-views-1.s
index c8a108882d1e8..e7e4458d8e9ea 100644
--- a/llvm/test/tools/llvm-mca/X86/option-all-views-1.s
+++ b/llvm/test/tools/llvm-mca/X86/option-all-views-1.s
@@ -128,19 +128,20 @@ add %eax, %eax
 # DEFAULTREPORT-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     addl	%eax, %eax
 
 # FULLREPORT:         Timeline view:
+# FULLREPORT-NEXT:    D: Instruction dispatched
 # FULLREPORT-NEXT:                        012
 # FULLREPORT-NEXT:    Index     0123456789
 
 # FULLREPORT:         [0,0]     DeER .    . .   addl	%eax, %eax
-# FULLREPORT-NEXT:    [1,0]     D=eER.    . .   addl	%eax, %eax
-# FULLREPORT-NEXT:    [2,0]     .D=eER    . .   addl	%eax, %eax
-# FULLREPORT-NEXT:    [3,0]     .D==eER   . .   addl	%eax, %eax
-# FULLREPORT-NEXT:    [4,0]     . D==eER  . .   addl	%eax, %eax
-# FULLREPORT-NEXT:    [5,0]     . D===eER . .   addl	%eax, %eax
-# FULLREPORT-NEXT:    [6,0]     .  D===eER. .   addl	%eax, %eax
-# FULLREPORT-NEXT:    [7,0]     .  D====eER .   addl	%eax, %eax
-# FULLREPORT-NEXT:    [8,0]     .   D====eER.   addl	%eax, %eax
-# FULLREPORT-NEXT:    [9,0]     .   D=====eER   addl	%eax, %eax
+# FULLREPORT-NEXT:    [1,0]     DPeER.    . .   addl	%eax, %eax
+# FULLREPORT-NEXT:    [2,0]     .DPeER    . .   addl	%eax, %eax
+# FULLREPORT-NEXT:    [3,0]     .DPPeER   . .   addl	%eax, %eax
+# FULLREPORT-NEXT:    [4,0]     . DPPeER  . .   addl	%eax, %eax
+# FULLREPORT-NEXT:    [5,0]     . DPPPeER . .   addl	%eax, %eax
+# FULLREPORT-NEXT:    [6,0]     .  DPPPeER. .   addl	%eax, %eax
+# FULLREPORT-NEXT:    [7,0]     .  DPPPPeER .   addl	%eax, %eax
+# FULLREPORT-NEXT:    [8,0]     .   DPPPPeER.   addl	%eax, %eax
+# FULLREPORT-NEXT:    [9,0]     .   DPPPPPeER   addl	%eax, %eax
 
 # FULLREPORT:         Average Wait times (based on the timeline view):
 # FULLREPORT-NEXT:    [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/option-all-views-2.s b/llvm/test/tools/llvm-mca/X86/option-all-views-2.s
index 6c7ba1666b7bc..e21250082884c 100644
--- a/llvm/test/tools/llvm-mca/X86/option-all-views-2.s
+++ b/llvm/test/tools/llvm-mca/X86/option-all-views-2.s
@@ -127,19 +127,20 @@ add %eax, %eax
 # FULLREPORT-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     addl	%eax, %eax
 
 # ALL:             Timeline view:
+# ALL-NEXT:        D: Instruction dispatched
 # ALL-NEXT:                            012
 # ALL-NEXT:        Index     0123456789
 
 # ALL:             [0,0]     DeER .    . .   addl	%eax, %eax
-# ALL-NEXT:        [1,0]     D=eER.    . .   addl	%eax, %eax
-# ALL-NEXT:        [2,0]     .D=eER    . .   addl	%eax, %eax
-# ALL-NEXT:        [3,0]     .D==eER   . .   addl	%eax, %eax
-# ALL-NEXT:        [4,0]     . D==eER  . .   addl	%eax, %eax
-# ALL-NEXT:        [5,0]     . D===eER . .   addl	%eax, %eax
-# ALL-NEXT:        [6,0]     .  D===eER. .   addl	%eax, %eax
-# ALL-NEXT:        [7,0]     .  D====eER .   addl	%eax, %eax
-# ALL-NEXT:        [8,0]     .   D====eER.   addl	%eax, %eax
-# ALL-NEXT:        [9,0]     .   D=====eER   addl	%eax, %eax
+# ALL-NEXT:        [1,0]     DPeER.    . .   addl	%eax, %eax
+# ALL-NEXT:        [2,0]     .DPeER    . .   addl	%eax, %eax
+# ALL-NEXT:        [3,0]     .DPPeER   . .   addl	%eax, %eax
+# ALL-NEXT:        [4,0]     . DPPeER  . .   addl	%eax, %eax
+# ALL-NEXT:        [5,0]     . DPPPeER . .   addl	%eax, %eax
+# ALL-NEXT:        [6,0]     .  DPPPeER. .   addl	%eax, %eax
+# ALL-NEXT:        [7,0]     .  DPPPPeER .   addl	%eax, %eax
+# ALL-NEXT:        [8,0]     .   DPPPPeER.   addl	%eax, %eax
+# ALL-NEXT:        [9,0]     .   DPPPPPeER   addl	%eax, %eax
 
 # ALL:             Average Wait times (based on the timeline view):
 # ALL-NEXT:        [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/option-no-stats-1.s b/llvm/test/tools/llvm-mca/X86/option-no-stats-1.s
index d505dd9bc3e2a..c483e259f5b7b 100644
--- a/llvm/test/tools/llvm-mca/X86/option-no-stats-1.s
+++ b/llvm/test/tools/llvm-mca/X86/option-no-stats-1.s
@@ -71,19 +71,20 @@ add %edi, %eax
 # CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     addl	%edi, %eax
 
 # CHECK:      Timeline view:
+# CHECK-NEXT: D: Instruction dispatched
 # CHECK-NEXT:                     012
 # CHECK-NEXT: Index     0123456789
 
 # CHECK:      [0,0]     DeER .    . .   addl	%edi, %eax
-# CHECK-NEXT: [1,0]     D=eER.    . .   addl	%edi, %eax
-# CHECK-NEXT: [2,0]     .D=eER    . .   addl	%edi, %eax
-# CHECK-NEXT: [3,0]     .D==eER   . .   addl	%edi, %eax
-# CHECK-NEXT: [4,0]     . D==eER  . .   addl	%edi, %eax
-# CHECK-NEXT: [5,0]     . D===eER . .   addl	%edi, %eax
-# CHECK-NEXT: [6,0]     .  D===eER. .   addl	%edi, %eax
-# CHECK-NEXT: [7,0]     .  D====eER .   addl	%edi, %eax
-# CHECK-NEXT: [8,0]     .   D====eER.   addl	%edi, %eax
-# CHECK-NEXT: [9,0]     .   D=====eER   addl	%edi, %eax
+# CHECK-NEXT: [1,0]     DPeER.    . .   addl	%edi, %eax
+# CHECK-NEXT: [2,0]     .DPeER    . .   addl	%edi, %eax
+# CHECK-NEXT: [3,0]     .DPPeER   . .   addl	%edi, %eax
+# CHECK-NEXT: [4,0]     . DPPeER  . .   addl	%edi, %eax
+# CHECK-NEXT: [5,0]     . DPPPeER . .   addl	%edi, %eax
+# CHECK-NEXT: [6,0]     .  DPPPeER. .   addl	%edi, %eax
+# CHECK-NEXT: [7,0]     .  DPPPPeER .   addl	%edi, %eax
+# CHECK-NEXT: [8,0]     .   DPPPPeER.   addl	%edi, %eax
+# CHECK-NEXT: [9,0]     .   DPPPPPeER   addl	%edi, %eax
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/read-after-ld-1.s b/llvm/test/tools/llvm-mca/X86/read-after-ld-1.s
index 7b9fb758320ec..db809bcd3983b 100644
--- a/llvm/test/tools/llvm-mca/X86/read-after-ld-1.s
+++ b/llvm/test/tools/llvm-mca/X86/read-after-ld-1.s
@@ -107,6 +107,7 @@ vaddps  (%rax), %xmm1, %xmm1
 # ZNVER4-NEXT:    Block RThroughput: 3.0
 
 # ALL:            Timeline view:
+# ALL-NEXT:       D: Instruction dispatched
 
 # BARCELONA-NEXT:                     0123456789
 # BARCELONA-NEXT: Index     0123456789
@@ -142,37 +143,37 @@ vaddps  (%rax), %xmm1, %xmm1
 # ZNVER4-NEXT:    Index     0123456789
 
 # BARCELONA:      [0,0]     DeeeeeeeeeeeeeeER  .   vdivps	%xmm0, %xmm1, %xmm1
-# BARCELONA-NEXT: [0,1]     D========eeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# BARCELONA-NEXT: [0,1]     DPPPPPPPPeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # BDVER2:         [0,0]     DeeeeeeeeeER   ..   vdivps	%xmm0, %xmm1, %xmm1
-# BDVER2-NEXT:    [0,1]     D====eeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# BDVER2-NEXT:    [0,1]     DPPPPeeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # BDWELL:         [0,0]     DeeeeeeeeeeeER ..   vdivps	%xmm0, %xmm1, %xmm1
-# BDWELL-NEXT:    [0,1]     D======eeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# BDWELL-NEXT:    [0,1]     DPPPPPPeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # BTVER2:         [0,0]     DeeeeeeeeeeeeeeeeeeeER  .   vdivps	%xmm0, %xmm1, %xmm1
-# BTVER2-NEXT:    [0,1]     D==============eeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# BTVER2-NEXT:    [0,1]     DPPPPPPPPPPPPPPeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # HASWELL:        [0,0]     DeeeeeeeeeeeeeER  .   vdivps	%xmm0, %xmm1, %xmm1
-# HASWELL-NEXT:   [0,1]     D=======eeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# HASWELL-NEXT:   [0,1]     DPPPPPPPeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # SANDY:          [0,0]     DeeeeeeeeeeeeeeER  .   vdivps	%xmm0, %xmm1, %xmm1
-# SANDY-NEXT:     [0,1]     D========eeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# SANDY-NEXT:     [0,1]     DPPPPPPPPeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # SKYLAKE:        [0,0]     DeeeeeeeeeeeER . .   vdivps	%xmm0, %xmm1, %xmm1
-# SKYLAKE-NEXT:   [0,1]     D=====eeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# SKYLAKE-NEXT:   [0,1]     DPPPPPeeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # ZNVER1:         [0,0]     DeeeeeeeeeeER .   vdivps	%xmm0, %xmm1, %xmm1
-# ZNVER1-NEXT:    [0,1]     D==eeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# ZNVER1-NEXT:    [0,1]     DPPeeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # ZNVER2:         [0,0]     DeeeeeeeeeeER  .   vdivps	%xmm0, %xmm1, %xmm1
-# ZNVER2-NEXT:    [0,1]     D===eeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# ZNVER2-NEXT:    [0,1]     DPPPeeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # ZNVER3:         [0,0]     DeeeeeeeeeeeER ..   vdivps	%xmm0, %xmm1, %xmm1
-# ZNVER3-NEXT:    [0,1]     D====eeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# ZNVER3-NEXT:    [0,1]     DPPPPeeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # ZNVER4:         [0,0]     DeeeeeeeeeeeER ..   vdivps	%xmm0, %xmm1, %xmm1
-# ZNVER4-NEXT:    [0,1]     D====eeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
+# ZNVER4-NEXT:    [0,1]     DPPPPeeeeeeeeeeER   vaddps	(%rax), %xmm1, %xmm1
 
 # ALL:            Average Wait times (based on the timeline view):
 # ALL-NEXT:       [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/read-after-ld-2.s b/llvm/test/tools/llvm-mca/X86/read-after-ld-2.s
index fc6a825af347e..63dd74d4f4cbd 100644
--- a/llvm/test/tools/llvm-mca/X86/read-after-ld-2.s
+++ b/llvm/test/tools/llvm-mca/X86/read-after-ld-2.s
@@ -62,6 +62,7 @@ cmp     %edi, %edx
 # ZNVER2-NEXT:  Block RThroughput: 1.0
 
 # ALL:          Timeline view:
+# ALL-NEXT:     D: Instruction dispatched
 
 # BDWELL-NEXT:                      0123456789
 # BDWELL-NEXT:  Index     0123456789          01
@@ -163,43 +164,43 @@ cmp     %edi, %edx
 # SKYLAKE:      [0,0]     DeER .    .    .   .   addl	$1, %edx
 # SKYLAKE-NEXT: [0,1]     DeeeeeeeeER    .   .   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [0,2]     DeE-------R    .   .   addq	$32, %r8
-# SKYLAKE-NEXT: [0,3]     D=eE------R    .   .   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [1,0]     D=eE------R    .   .   addl	$1, %edx
+# SKYLAKE-NEXT: [0,3]     DPeE------R    .   .   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [1,0]     DPeE------R    .   .   addl	$1, %edx
 # SKYLAKE-NEXT: [1,1]     .DeeeeeeeeER   .   .   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [1,2]     .DeE-------R   .   .   addq	$32, %r8
-# SKYLAKE-NEXT: [1,3]     .D=eE------R   .   .   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [2,0]     .D=eE------R   .   .   addl	$1, %edx
+# SKYLAKE-NEXT: [1,3]     .DPeE------R   .   .   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [2,0]     .DPeE------R   .   .   addl	$1, %edx
 # SKYLAKE-NEXT: [2,1]     . DeeeeeeeeER  .   .   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [2,2]     . DeE-------R  .   .   addq	$32, %r8
-# SKYLAKE-NEXT: [2,3]     . D=eE------R  .   .   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [3,0]     . D=eE------R  .   .   addl	$1, %edx
+# SKYLAKE-NEXT: [2,3]     . DPeE------R  .   .   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [3,0]     . DPeE------R  .   .   addl	$1, %edx
 # SKYLAKE-NEXT: [3,1]     .  DeeeeeeeeER .   .   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [3,2]     .  DeE-------R .   .   addq	$32, %r8
-# SKYLAKE-NEXT: [3,3]     .  D=eE------R .   .   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [4,0]     .  D=eE------R .   .   addl	$1, %edx
+# SKYLAKE-NEXT: [3,3]     .  DPeE------R .   .   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [4,0]     .  DPeE------R .   .   addl	$1, %edx
 # SKYLAKE-NEXT: [4,1]     .   DeeeeeeeeER.   .   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [4,2]     .   DeE-------R.   .   addq	$32, %r8
-# SKYLAKE-NEXT: [4,3]     .   D=eE------R.   .   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [5,0]     .   D=eE------R.   .   addl	$1, %edx
+# SKYLAKE-NEXT: [4,3]     .   DPeE------R.   .   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [5,0]     .   DPeE------R.   .   addl	$1, %edx
 # SKYLAKE-NEXT: [5,1]     .    DeeeeeeeeER   .   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [5,2]     .    DeE-------R   .   addq	$32, %r8
-# SKYLAKE-NEXT: [5,3]     .    D=eE------R   .   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [6,0]     .    D=eE------R   .   addl	$1, %edx
+# SKYLAKE-NEXT: [5,3]     .    DPeE------R   .   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [6,0]     .    DPeE------R   .   addl	$1, %edx
 # SKYLAKE-NEXT: [6,1]     .    .DeeeeeeeeER  .   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [6,2]     .    .DeE-------R  .   addq	$32, %r8
-# SKYLAKE-NEXT: [6,3]     .    .D=eE------R  .   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [7,0]     .    .D=eE------R  .   addl	$1, %edx
+# SKYLAKE-NEXT: [6,3]     .    .DPeE------R  .   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [7,0]     .    .DPeE------R  .   addl	$1, %edx
 # SKYLAKE-NEXT: [7,1]     .    . DeeeeeeeeER .   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [7,2]     .    . DeE-------R .   addq	$32, %r8
-# SKYLAKE-NEXT: [7,3]     .    . D=eE------R .   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [8,0]     .    . D=eE------R .   addl	$1, %edx
+# SKYLAKE-NEXT: [7,3]     .    . DPeE------R .   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [8,0]     .    . DPeE------R .   addl	$1, %edx
 # SKYLAKE-NEXT: [8,1]     .    .  DeeeeeeeeER.   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [8,2]     .    .  DeE-------R.   addq	$32, %r8
-# SKYLAKE-NEXT: [8,3]     .    .  D=eE------R.   cmpl	%edi, %edx
-# SKYLAKE-NEXT: [9,0]     .    .  D=eE------R.   addl	$1, %edx
+# SKYLAKE-NEXT: [8,3]     .    .  DPeE------R.   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [9,0]     .    .  DPeE------R.   addl	$1, %edx
 # SKYLAKE-NEXT: [9,1]     .    .   DeeeeeeeeER   vpaddd	(%r8), %ymm0, %ymm0
 # SKYLAKE-NEXT: [9,2]     .    .   DeE-------R   addq	$32, %r8
-# SKYLAKE-NEXT: [9,3]     .    .   D=eE------R   cmpl	%edi, %edx
+# SKYLAKE-NEXT: [9,3]     .    .   DPeE------R   cmpl	%edi, %edx
 
 # ZNVER1:       [0,0]     DeER .    .    .    . .   addl	$1, %edx
 # ZNVER1-NEXT:  [0,1]     DeeeeeeeeER    .    . .   vpaddd	(%r8), %ymm0, %ymm0
@@ -245,43 +246,43 @@ cmp     %edi, %edx
 # ZNVER2:       [0,0]     DeER .    .    .   .   addl	$1, %edx
 # ZNVER2-NEXT:  [0,1]     DeeeeeeeeER    .   .   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [0,2]     DeE-------R    .   .   addq	$32, %r8
-# ZNVER2-NEXT:  [0,3]     D=eE------R    .   .   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [0,3]     DPeE------R    .   .   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [1,0]     .DeE------R    .   .   addl	$1, %edx
 # ZNVER2-NEXT:  [1,1]     .DeeeeeeeeER   .   .   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [1,2]     .DeE-------R   .   .   addq	$32, %r8
-# ZNVER2-NEXT:  [1,3]     .D=eE------R   .   .   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [1,3]     .DPeE------R   .   .   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [2,0]     . DeE------R   .   .   addl	$1, %edx
 # ZNVER2-NEXT:  [2,1]     . DeeeeeeeeER  .   .   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [2,2]     . DeE-------R  .   .   addq	$32, %r8
-# ZNVER2-NEXT:  [2,3]     . D=eE------R  .   .   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [2,3]     . DPeE------R  .   .   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [3,0]     .  DeE------R  .   .   addl	$1, %edx
 # ZNVER2-NEXT:  [3,1]     .  DeeeeeeeeER .   .   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [3,2]     .  DeE-------R .   .   addq	$32, %r8
-# ZNVER2-NEXT:  [3,3]     .  D=eE------R .   .   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [3,3]     .  DPeE------R .   .   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [4,0]     .   DeE------R .   .   addl	$1, %edx
 # ZNVER2-NEXT:  [4,1]     .   DeeeeeeeeER.   .   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [4,2]     .   DeE-------R.   .   addq	$32, %r8
-# ZNVER2-NEXT:  [4,3]     .   D=eE------R.   .   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [4,3]     .   DPeE------R.   .   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [5,0]     .    DeE------R.   .   addl	$1, %edx
 # ZNVER2-NEXT:  [5,1]     .    DeeeeeeeeER   .   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [5,2]     .    DeE-------R   .   addq	$32, %r8
-# ZNVER2-NEXT:  [5,3]     .    D=eE------R   .   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [5,3]     .    DPeE------R   .   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [6,0]     .    .DeE------R   .   addl	$1, %edx
 # ZNVER2-NEXT:  [6,1]     .    .DeeeeeeeeER  .   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [6,2]     .    .DeE-------R  .   addq	$32, %r8
-# ZNVER2-NEXT:  [6,3]     .    .D=eE------R  .   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [6,3]     .    .DPeE------R  .   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [7,0]     .    . DeE------R  .   addl	$1, %edx
 # ZNVER2-NEXT:  [7,1]     .    . DeeeeeeeeER .   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [7,2]     .    . DeE-------R .   addq	$32, %r8
-# ZNVER2-NEXT:  [7,3]     .    . D=eE------R .   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [7,3]     .    . DPeE------R .   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [8,0]     .    .  DeE------R .   addl	$1, %edx
 # ZNVER2-NEXT:  [8,1]     .    .  DeeeeeeeeER.   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [8,2]     .    .  DeE-------R.   addq	$32, %r8
-# ZNVER2-NEXT:  [8,3]     .    .  D=eE------R.   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [8,3]     .    .  DPeE------R.   cmpl	%edi, %edx
 # ZNVER2-NEXT:  [9,0]     .    .   DeE------R.   addl	$1, %edx
 # ZNVER2-NEXT:  [9,1]     .    .   DeeeeeeeeER   vpaddd	(%r8), %ymm0, %ymm0
 # ZNVER2-NEXT:  [9,2]     .    .   DeE-------R   addq	$32, %r8
-# ZNVER2-NEXT:  [9,3]     .    .   D=eE------R   cmpl	%edi, %edx
+# ZNVER2-NEXT:  [9,3]     .    .   DPeE------R   cmpl	%edi, %edx
 
 # ALL:          Average Wait times (based on the timeline view):
 # ALL-NEXT:     [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/read-after-ld-3.s b/llvm/test/tools/llvm-mca/X86/read-after-ld-3.s
index 7abeadee39925..1f690b7757152 100644
--- a/llvm/test/tools/llvm-mca/X86/read-after-ld-3.s
+++ b/llvm/test/tools/llvm-mca/X86/read-after-ld-3.s
@@ -35,6 +35,7 @@ addl    (%rdi), %esi
 # SKYLAKE-NEXT: Block RThroughput: 0.5
 
 # ALL:          Timeline view:
+# ALL-NEXT:     D: Instruction dispatched
 # ALL-NEXT:     Index     012345678
 
 # ALL:          [0,0]     DeER .  .   addl	%edi, %esi
diff --git a/llvm/test/tools/llvm-mca/X86/sqrt-rsqrt-rcp-memop.s b/llvm/test/tools/llvm-mca/X86/sqrt-rsqrt-rcp-memop.s
index abf01cb0b10f9..bea988f26c3c0 100644
--- a/llvm/test/tools/llvm-mca/X86/sqrt-rsqrt-rcp-memop.s
+++ b/llvm/test/tools/llvm-mca/X86/sqrt-rsqrt-rcp-memop.s
@@ -32,6 +32,7 @@ rcpss (%rax), %xmm1
 # ALL:            [0] Code Region - test_sqrtss
 
 # ALL:            Timeline view:
+# ALL-NEXT:       D: Instruction dispatched
 
 # BARCELONA-NEXT:                     0123456789
 # BARCELONA-NEXT: Index     0123456789          0123
@@ -58,28 +59,28 @@ rcpss (%rax), %xmm1
 # ZNVER2-NEXT:    Index     0123456789          01234
 
 # BARCELONA:      [0,0]     DeER .    .    .    .  .   leaq	8(%rsp,%rdi,2), %rax
-# BARCELONA-NEXT: [0,1]     D=eeeeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
+# BARCELONA-NEXT: [0,1]     DPeeeeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
 
 # BDVER2:         [0,0]     DeeER.    .    .  .   leaq	8(%rsp,%rdi,2), %rax
-# BDVER2-NEXT:    [0,1]     D==eeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
+# BDVER2-NEXT:    [0,1]     DPPeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
 
 # BROADWELL:      [0,0]     DeER .    .    .   .   leaq	8(%rsp,%rdi,2), %rax
-# BROADWELL-NEXT: [0,1]     D=eeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
+# BROADWELL-NEXT: [0,1]     DPeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
 
 # BTVER2:         [0,0]     DeeER.    .    .    .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# BTVER2-NEXT:    [0,1]     D==eeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
+# BTVER2-NEXT:    [0,1]     DPPeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
 
 # HASWELL:        [0,0]     DeER .    .    .   .   leaq	8(%rsp,%rdi,2), %rax
-# HASWELL-NEXT:   [0,1]     D=eeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
+# HASWELL-NEXT:   [0,1]     DPeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
 
 # SKYLAKE:        [0,0]     DeER .    .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# SKYLAKE-NEXT:   [0,1]     D=eeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
+# SKYLAKE-NEXT:   [0,1]     DPeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
 
 # ZNVER1:         [0,0]     DeER .    .    .    .   .   leaq	8(%rsp,%rdi,2), %rax
-# ZNVER1-NEXT:    [0,1]     D=eeeeeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
+# ZNVER1-NEXT:    [0,1]     DPeeeeeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
 
 # ZNVER2:         [0,0]     DeER .    .    .    .   .   leaq	8(%rsp,%rdi,2), %rax
-# ZNVER2-NEXT:    [0,1]     D=eeeeeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
+# ZNVER2-NEXT:    [0,1]     DPeeeeeeeeeeeeeeeeeeeeeER   sqrtss	(%rax), %xmm1
 
 # ALL:            Average Wait times (based on the timeline view):
 # ALL-NEXT:       [0]: Executions
@@ -117,6 +118,7 @@ rcpss (%rax), %xmm1
 # ALL:            [1] Code Region - test_sqrtsd
 
 # ALL:            Timeline view:
+# ALL-NEXT:       D: Instruction dispatched
 
 # BARCELONA-NEXT:                     0123456789          0
 # BARCELONA-NEXT: Index     0123456789          0123456789
@@ -143,28 +145,28 @@ rcpss (%rax), %xmm1
 # ZNVER2-NEXT:    Index     0123456789          0123456789
 
 # BARCELONA:      [0,0]     DeER .    .    .    .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# BARCELONA-NEXT: [0,1]     D=eeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
+# BARCELONA-NEXT: [0,1]     DPeeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
 
 # BDVER2:         [0,0]     DeeER.    .    .  .   leaq	8(%rsp,%rdi,2), %rax
-# BDVER2-NEXT:    [0,1]     D==eeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
+# BDVER2-NEXT:    [0,1]     DPPeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
 
 # BROADWELL:      [0,0]     DeER .    .    .    .   .   leaq	8(%rsp,%rdi,2), %rax
-# BROADWELL-NEXT: [0,1]     D=eeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
+# BROADWELL-NEXT: [0,1]     DPeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
 
 # BTVER2:         [0,0]     DeeER.    .    .    .    .    .    ..   leaq	8(%rsp,%rdi,2), %rax
-# BTVER2-NEXT:    [0,1]     D==eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
+# BTVER2-NEXT:    [0,1]     DPPeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
 
 # HASWELL:        [0,0]     DeER .    .    .    .   .   leaq	8(%rsp,%rdi,2), %rax
-# HASWELL-NEXT:   [0,1]     D=eeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
+# HASWELL-NEXT:   [0,1]     DPeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
 
 # SKYLAKE:        [0,0]     DeER .    .    .    .    ..   leaq	8(%rsp,%rdi,2), %rax
-# SKYLAKE-NEXT:   [0,1]     D=eeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
+# SKYLAKE-NEXT:   [0,1]     DPeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
 
 # ZNVER1:         [0,0]     DeER .    .    .    .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# ZNVER1-NEXT:    [0,1]     D=eeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
+# ZNVER1-NEXT:    [0,1]     DPeeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
 
 # ZNVER2:         [0,0]     DeER .    .    .    .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# ZNVER2-NEXT:    [0,1]     D=eeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
+# ZNVER2-NEXT:    [0,1]     DPeeeeeeeeeeeeeeeeeeeeeeeeeeeER   sqrtsd	(%rax), %xmm1
 
 # ALL:            Average Wait times (based on the timeline view):
 # ALL-NEXT:       [0]: Executions
@@ -202,6 +204,7 @@ rcpss (%rax), %xmm1
 # ALL:            [2] Code Region - test_rsqrtss
 
 # ALL:            Timeline view:
+# ALL-NEXT:       D: Instruction dispatched
 
 # BARCELONA-NEXT:                     01234
 # BDVER2-NEXT:                        01234
@@ -215,28 +218,28 @@ rcpss (%rax), %xmm1
 # ALL-NEXT:       Index     0123456789
 
 # BARCELONA:      [0,0]     DeER .    .   .   leaq	8(%rsp,%rdi,2), %rax
-# BARCELONA-NEXT: [0,1]     D=eeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
+# BARCELONA-NEXT: [0,1]     DPeeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
 
 # BDVER2:         [0,0]     DeeER.    .   .   leaq	8(%rsp,%rdi,2), %rax
-# BDVER2-NEXT:    [0,1]     D==eeeeeeeeeeER   rsqrtss	(%rax), %xmm1
+# BDVER2-NEXT:    [0,1]     DPPeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
 
 # BROADWELL:      [0,0]     DeER .    .  .   leaq	8(%rsp,%rdi,2), %rax
-# BROADWELL-NEXT: [0,1]     D=eeeeeeeeeeER   rsqrtss	(%rax), %xmm1
+# BROADWELL-NEXT: [0,1]     DPeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
 
 # BTVER2:         [0,0]     DeeER.    ..   leaq	8(%rsp,%rdi,2), %rax
-# BTVER2-NEXT:    [0,1]     D==eeeeeeeER   rsqrtss	(%rax), %xmm1
+# BTVER2-NEXT:    [0,1]     DPPeeeeeeeER   rsqrtss	(%rax), %xmm1
 
 # HASWELL:        [0,0]     DeER .    .  .   leaq	8(%rsp,%rdi,2), %rax
-# HASWELL-NEXT:   [0,1]     D=eeeeeeeeeeER   rsqrtss	(%rax), %xmm1
+# HASWELL-NEXT:   [0,1]     DPeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
 
 # SKYLAKE:        [0,0]     DeER .    . .   leaq	8(%rsp,%rdi,2), %rax
-# SKYLAKE-NEXT:   [0,1]     D=eeeeeeeeeER   rsqrtss	(%rax), %xmm1
+# SKYLAKE-NEXT:   [0,1]     DPeeeeeeeeeER   rsqrtss	(%rax), %xmm1
 
 # ZNVER1:         [0,0]     DeER .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# ZNVER1-NEXT:    [0,1]     D=eeeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
+# ZNVER1-NEXT:    [0,1]     DPeeeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
 
 # ZNVER2:         [0,0]     DeER .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# ZNVER2-NEXT:    [0,1]     D=eeeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
+# ZNVER2-NEXT:    [0,1]     DPeeeeeeeeeeeeER   rsqrtss	(%rax), %xmm1
 
 # ALL:            Average Wait times (based on the timeline view):
 # ALL-NEXT:       [0]: Executions
@@ -274,6 +277,7 @@ rcpss (%rax), %xmm1
 # ALL:            [3] Code Region - test_rcp
 
 # ALL:            Timeline view:
+# ALL-NEXT:       D: Instruction dispatched
 
 # BARCELONA-NEXT:                     01234
 # BDVER2-NEXT:                        01234
@@ -287,28 +291,28 @@ rcpss (%rax), %xmm1
 # ALL-NEXT:       Index     0123456789
 
 # BARCELONA:      [0,0]     DeER .    .   .   leaq	8(%rsp,%rdi,2), %rax
-# BARCELONA-NEXT: [0,1]     D=eeeeeeeeeeeER   rcpss	(%rax), %xmm1
+# BARCELONA-NEXT: [0,1]     DPeeeeeeeeeeeER   rcpss	(%rax), %xmm1
 
 # BDVER2:         [0,0]     DeeER.    .   .   leaq	8(%rsp,%rdi,2), %rax
-# BDVER2-NEXT:    [0,1]     D==eeeeeeeeeeER   rcpss	(%rax), %xmm1
+# BDVER2-NEXT:    [0,1]     DPPeeeeeeeeeeER   rcpss	(%rax), %xmm1
 
 # BROADWELL:      [0,0]     DeER .    .  .   leaq	8(%rsp,%rdi,2), %rax
-# BROADWELL-NEXT: [0,1]     D=eeeeeeeeeeER   rcpss	(%rax), %xmm1
+# BROADWELL-NEXT: [0,1]     DPeeeeeeeeeeER   rcpss	(%rax), %xmm1
 
 # BTVER2:         [0,0]     DeeER.    ..   leaq	8(%rsp,%rdi,2), %rax
-# BTVER2-NEXT:    [0,1]     D==eeeeeeeER   rcpss	(%rax), %xmm1
+# BTVER2-NEXT:    [0,1]     DPPeeeeeeeER   rcpss	(%rax), %xmm1
 
 # HASWELL:        [0,0]     DeER .    .  .   leaq	8(%rsp,%rdi,2), %rax
-# HASWELL-NEXT:   [0,1]     D=eeeeeeeeeeER   rcpss	(%rax), %xmm1
+# HASWELL-NEXT:   [0,1]     DPeeeeeeeeeeER   rcpss	(%rax), %xmm1
 
 # SKYLAKE:        [0,0]     DeER .    . .   leaq	8(%rsp,%rdi,2), %rax
-# SKYLAKE-NEXT:   [0,1]     D=eeeeeeeeeER   rcpss	(%rax), %xmm1
+# SKYLAKE-NEXT:   [0,1]     DPeeeeeeeeeER   rcpss	(%rax), %xmm1
 
 # ZNVER1:         [0,0]     DeER .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# ZNVER1-NEXT:    [0,1]     D=eeeeeeeeeeeeER   rcpss	(%rax), %xmm1
+# ZNVER1-NEXT:    [0,1]     DPeeeeeeeeeeeeER   rcpss	(%rax), %xmm1
 
 # ZNVER2:         [0,0]     DeER .    .    .   leaq	8(%rsp,%rdi,2), %rax
-# ZNVER2-NEXT:    [0,1]     D=eeeeeeeeeeeeER   rcpss	(%rax), %xmm1
+# ZNVER2-NEXT:    [0,1]     DPeeeeeeeeeeeeER   rcpss	(%rax), %xmm1
 
 # ALL:            Average Wait times (based on the timeline view):
 # ALL-NEXT:       [0]: Executions
diff --git a/llvm/test/tools/llvm-mca/X86/variable-blend-read-after-ld-1.s b/llvm/test/tools/llvm-mca/X86/variable-blend-read-after-ld-1.s
index cdf13271722ef..f854f14e19844 100644
--- a/llvm/test/tools/llvm-mca/X86/variable-blend-read-after-ld-1.s
+++ b/llvm/test/tools/llvm-mca/X86/variable-blend-read-after-ld-1.s
@@ -98,36 +98,45 @@ vblendvps %xmm1, (%rdi), %xmm2, %xmm3
 # ZNVER2-NEXT:  Block RThroughput: 0.5
 
 # BDVER2:       Timeline view:
+# BDVER2-NEXT:  D: Instruction dispatched
 # BDVER2-NEXT:  Index     0123456789
 
 # BDWELL:       Timeline view:
+# BDWELL-NEXT:  D: Instruction dispatched
 # BDWELL-NEXT:  Index     0123456789
 
 # BTVER2:       Timeline view:
+# BTVER2-NEXT:  D: Instruction dispatched
 # BTVER2-NEXT:                      0
 # BTVER2-NEXT:  Index     0123456789
 
 # HASWELL:      Timeline view:
+# HASWELL-NEXT: D: Instruction dispatched
 # HASWELL-NEXT:                     0
 # HASWELL-NEXT: Index     0123456789
 
 # IVY:          Timeline view:
+# IVY-NEXT:     D: Instruction dispatched
 # IVY-NEXT:                         0
 # IVY-NEXT:     Index     0123456789
 
 # SANDY:        Timeline view:
+# SANDY-NEXT:   D: Instruction dispatched
 # SANDY-NEXT:                       0
 # SANDY-NEXT:   Index     0123456789
 
 # SKYLAKE:      Timeline view:
+# SKYLAKE-NEXT: D: Instruction dispatched
 # SKYLAKE-NEXT:                     0
 # SKYLAKE-NEXT: Index     0123456789
 
 # ZNVER1:       Timeline view:
+# ZNVER1-NEXT:  D: Instruction dispatched
 # ZNVER1-NEXT:                      0
 # ZNVER1-NEXT:  Index     0123456789
 
 # ZNVER2:       Timeline view:
+# ZNVER2-NEXT:  D: Instruction dispatched
 # ZNVER2-NEXT:                      0
 # ZNVER2-NEXT:  Index     0123456789
 
diff --git a/llvm/test/tools/llvm-mca/X86/variable-blend-read-after-ld-2.s b/llvm/test/tools/llvm-mca/X86/variable-blend-read-after-ld-2.s
index 46cf892796a78..1dc7fe4d929b2 100644
--- a/llvm/test/tools/llvm-mca/X86/variable-blend-read-after-ld-2.s
+++ b/llvm/test/tools/llvm-mca/X86/variable-blend-read-after-ld-2.s
@@ -98,36 +98,45 @@ vblendvps %xmm1, (%rdi), %xmm2, %xmm3
 # ZNVER2-NEXT:  Block RThroughput: 0.5
 
 # BDVER2:       Timeline view:
+# BDVER2-NEXT:  D: Instruction dispatched
 # BDVER2-NEXT:  Index     0123456789
 
 # BDWELL:       Timeline view:
+# BDWELL-NEXT:  D: Instruction dispatched
 # BDWELL-NEXT:  Index     0123456789
 
 # BTVER2:       Timeline view:
+# BTVER2-NEXT:  D: Instruction dispatched
 # BTVER2-NEXT:                      0
 # BTVER2-NEXT:  Index     0123456789
 
 # HASWELL:      Timeline view:
+# HASWELL-NEXT: D: Instruction dispatched
 # HASWELL-NEXT:                     0
 # HASWELL-NEXT: Index     0123456789
 
 # IVY:          Timeline view:
+# IVY-NEXT:     D: Instruction dispatched
 # IVY-NEXT:                         0
 # IVY-NEXT:     Index     0123456789
 
 # SANDY:        Timeline view:
+# SANDY-NEXT:   D: Instruction dispatched
 # SANDY-NEXT:                       0
 # SANDY-NEXT:   Index     0123456789
 
 # SKYLAKE:      Timeline view:
+# SKYLAKE-NEXT: D: Instruction dispatched
 # SKYLAKE-NEXT:                     0
 # SKYLAKE-NEXT: Index     0123456789
 
 # ZNVER1:       Timeline view:
+# ZNVER1-NEXT:  D: Instruction dispatched
 # ZNVER1-NEXT:                      0
 # ZNVER1-NEXT:  Index     0123456789
 
 # ZNVER2:       Timeline view:
+# ZNVER2-NEXT:  D: Instruction dispatched
 # ZNVER2-NEXT:                      0
 # ZNVER2-NEXT:  Index     0123456789
 
diff --git a/llvm/tools/llvm-mca/Views/TimelineView.cpp b/llvm/tools/llvm-mca/Views/TimelineView.cpp
index 2eca48aadfd70..16534328b0e8b 100644
--- a/llvm/tools/llvm-mca/Views/TimelineView.cpp
+++ b/llvm/tools/llvm-mca/Views/TimelineView.cpp
@@ -99,6 +99,10 @@ void TimelineView::onEvent(const HWInstructionEvent &Event) {
     if (Timeline[Index].CycleDispatched == -1)
       Timeline[Index].CycleDispatched = static_cast<int>(CurrentCycle);
     break;
+  case HWInstructionEvent::Pending: {
+    Timeline[Index].CyclePending = CurrentCycle;
+    break;
+  }
   default:
     return;
   }
@@ -231,7 +235,11 @@ void TimelineView::printTimelineViewEntry(formatted_raw_ostream &OS,
     // Zero latency instructions have the same value for CycleDispatched,
     // CycleIssued and CycleExecuted.
     for (unsigned I = CycleDispatched + 1, E = Entry.CycleIssued; I < E; ++I)
-      OS << TimelineView::DisplayChar::Waiting;
+      if (I >= Entry.CycleReady) 
+        OS << TimelineView::DisplayChar::Waiting;
+      else 
+        OS << TimelineView::DisplayChar::Pending;
+
     if (Entry.CycleIssued == Entry.CycleExecuted)
       OS << TimelineView::DisplayChar::DisplayChar::Executed;
     else {
@@ -255,7 +263,14 @@ void TimelineView::printTimelineViewEntry(formatted_raw_ostream &OS,
 }
 
 static void printTimelineHeader(formatted_raw_ostream &OS, unsigned Cycles) {
-  OS << "\n\nTimeline view:\n";
+  OS << "\n\nTimeline view:\n"
+        "D: Instruction dispatched\n";
+        "e: Instruction executing\n";
+        "E: Instruction executed (write-back stage)\n";
+        "P: Instruction waiting for data dependency\n";
+        "=: Instruction waiting for available HW resource\n";
+        "-: Instruction executed, waiting to retire in order.\n";
+        '\n';
   if (Cycles >= 10) {
     OS.PadToColumn(10);
     for (unsigned I = 0; I <= Cycles; ++I) {
diff --git a/llvm/tools/llvm-mca/Views/TimelineView.h b/llvm/tools/llvm-mca/Views/TimelineView.h
index 81be8244b779d..918b57f832f01 100644
--- a/llvm/tools/llvm-mca/Views/TimelineView.h
+++ b/llvm/tools/llvm-mca/Views/TimelineView.h
@@ -126,6 +126,7 @@ class TimelineView : public InstructionView {
 
   struct TimelineViewEntry {
     int CycleDispatched; // A negative value is an "invalid cycle".
+    unsigned CyclePending;
     unsigned CycleReady;
     unsigned CycleIssued;
     unsigned CycleExecuted;
@@ -156,6 +157,7 @@ class TimelineView : public InstructionView {
     static const char Dispatched = 'D';
     static const char Executed = 'E';
     static const char Retired = 'R';
+    static const char Pending = 'P';
     static const char Waiting = '='; // Instruction is waiting in the scheduler.
     static const char Executing = 'e';
     static const char RetireLag = '-'; // The instruction is waiting to retire.



More information about the llvm-commits mailing list