[llvm] r363774 - [NFC][X86][MCA] BdVer2: add load-store-throughput test
Roman Lebedev via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 19 01:53:28 PDT 2019
Author: lebedevri
Date: Wed Jun 19 01:53:28 2019
New Revision: 363774
URL: http://llvm.org/viewvc/llvm-project?rev=363774&view=rev
Log:
[NFC][X86][MCA] BdVer2: add load-store-throughput test
Added:
llvm/trunk/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s
Added: llvm/trunk/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s?rev=363774&view=auto
==============================================================================
--- llvm/trunk/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s (added)
+++ llvm/trunk/test/tools/llvm-mca/X86/BdVer2/load-store-throughput.s Wed Jun 19 01:53:28 2019
@@ -0,0 +1,736 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=bdver2 -scheduler-stats -dispatch-stats -iterations=100 -timeline -timeline-max-iterations=1 < %s | FileCheck %s
+
+# LLVM-MCA-BEGIN
+movb %spl, (%rax)
+movb (%rcx), %bpl
+movb (%rdx), %sil
+movb %dil, (%rbx)
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+movw %sp, (%rax)
+movw (%rcx), %bp
+movw (%rdx), %si
+movw %di, (%rbx)
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+movl %esp, (%rax)
+movl (%rcx), %ebp
+movl (%rdx), %esi
+movl %edi, (%rbx)
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+movq %rsp, (%rax)
+movq (%rcx), %rbp
+movq (%rdx), %rsi
+movq %rdi, (%rbx)
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+movd %mm0, (%rax)
+movd (%rcx), %mm1
+movd (%rdx), %mm2
+movd %mm3, (%rbx)
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+movaps %xmm0, (%rax)
+movaps (%rcx), %xmm1
+movaps (%rdx), %xmm2
+movaps %xmm3, (%rbx)
+# LLVM-MCA-END
+
+# CHECK: [0] Code Region
+
+# CHECK: Iterations: 100
+# CHECK-NEXT: Instructions: 400
+# CHECK-NEXT: Total Cycles: 306
+# CHECK-NEXT: Total uOps: 400
+
+# CHECK: Dispatch Width: 4
+# CHECK-NEXT: uOps Per Cycle: 1.31
+# CHECK-NEXT: IPC: 1.31
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# 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 1 1.00 * movb %spl, (%rax)
+# CHECK-NEXT: 1 5 1.00 * movb (%rcx), %bpl
+# CHECK-NEXT: 1 5 1.00 * movb (%rdx), %sil
+# CHECK-NEXT: 1 1 1.00 * movb %dil, (%rbx)
+
+# CHECK: Dynamic Dispatch Stall Cycles:
+# CHECK-NEXT: RAT - Register unavailable: 0
+# CHECK-NEXT: RCU - Retire tokens unavailable: 0
+# CHECK-NEXT: SCHEDQ - Scheduler full: 257 (84.0%)
+# CHECK-NEXT: LQ - Load queue full: 0
+# CHECK-NEXT: SQ - Store queue full: 0
+# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
+
+# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
+# CHECK-NEXT: [# dispatched], [# cycles]
+# CHECK-NEXT: 0, 34 (11.1%)
+# CHECK-NEXT: 1, 172 (56.2%)
+# CHECK-NEXT: 2, 86 (28.1%)
+# CHECK-NEXT: 4, 14 (4.6%)
+
+# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
+# CHECK-NEXT: [# issued], [# cycles]
+# CHECK-NEXT: 0, 5 (1.6%)
+# CHECK-NEXT: 1, 202 (66.0%)
+# CHECK-NEXT: 2, 99 (32.4%)
+
+# CHECK: Scheduler's queue usage:
+# CHECK-NEXT: [1] Resource name.
+# CHECK-NEXT: [2] Average number of used buffer entries.
+# CHECK-NEXT: [3] Maximum number of used buffer entries.
+# CHECK-NEXT: [4] Total number of buffer entries.
+
+# CHECK: [1] [2] [3] [4]
+# CHECK-NEXT: PdEX 36 40 40
+# CHECK-NEXT: PdFPU 0 0 64
+# CHECK-NEXT: PdLoad 19 22 40
+# CHECK-NEXT: PdStore 20 23 24
+
+# CHECK: Resources:
+# CHECK-NEXT: [0.0] - PdAGLU01
+# CHECK-NEXT: [0.1] - PdAGLU01
+# CHECK-NEXT: [1] - PdBranch
+# CHECK-NEXT: [2] - PdCount
+# CHECK-NEXT: [3] - PdDiv
+# CHECK-NEXT: [4] - PdEX0
+# CHECK-NEXT: [5] - PdEX1
+# CHECK-NEXT: [6] - PdFPCVT
+# CHECK-NEXT: [7.0] - PdFPFMA
+# CHECK-NEXT: [7.1] - PdFPFMA
+# CHECK-NEXT: [8.0] - PdFPMAL
+# CHECK-NEXT: [8.1] - PdFPMAL
+# CHECK-NEXT: [9] - PdFPMMA
+# CHECK-NEXT: [10] - PdFPSTO
+# CHECK-NEXT: [11] - PdFPU0
+# CHECK-NEXT: [12] - PdFPU1
+# CHECK-NEXT: [13] - PdFPU2
+# CHECK-NEXT: [14] - PdFPU3
+# CHECK-NEXT: [15] - PdFPXBR
+# CHECK-NEXT: [16.0] - PdLoad
+# CHECK-NEXT: [16.1] - PdLoad
+# CHECK-NEXT: [17] - PdMul
+# CHECK-NEXT: [18] - PdStore
+
+# CHECK: Resource pressure per iteration:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18]
+# CHECK-NEXT: 3.00 3.00 - - - - - - - - - - - - - - - - - 2.00 2.00 - 2.00
+
+# CHECK: Resource pressure by instruction:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18] Instructions:
+# CHECK-NEXT: 0.96 0.04 - - - - - - - - - - - - - - - - - - - - 1.00 movb %spl, (%rax)
+# CHECK-NEXT: 2.00 - - - - - - - - - - - - - - - - - - - 2.00 - - movb (%rcx), %bpl
+# CHECK-NEXT: - 2.00 - - - - - - - - - - - - - - - - - 2.00 - - - movb (%rdx), %sil
+# CHECK-NEXT: 0.04 0.96 - - - - - - - - - - - - - - - - - - - - 1.00 movb %dil, (%rbx)
+
+# CHECK: Timeline view:
+# CHECK-NEXT: Index 0123456789
+
+# 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======eER movb %dil, (%rbx)
+
+# 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 movb %spl, (%rax)
+# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movb (%rcx), %bpl
+# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movb (%rdx), %sil
+# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movb %dil, (%rbx)
+
+# CHECK: [1] Code Region
+
+# CHECK: Iterations: 100
+# CHECK-NEXT: Instructions: 400
+# CHECK-NEXT: Total Cycles: 306
+# CHECK-NEXT: Total uOps: 400
+
+# CHECK: Dispatch Width: 4
+# CHECK-NEXT: uOps Per Cycle: 1.31
+# CHECK-NEXT: IPC: 1.31
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# 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 1 1.00 * movw %sp, (%rax)
+# CHECK-NEXT: 1 5 1.00 * movw (%rcx), %bp
+# CHECK-NEXT: 1 5 1.00 * movw (%rdx), %si
+# CHECK-NEXT: 1 1 1.00 * movw %di, (%rbx)
+
+# CHECK: Dynamic Dispatch Stall Cycles:
+# CHECK-NEXT: RAT - Register unavailable: 0
+# CHECK-NEXT: RCU - Retire tokens unavailable: 0
+# CHECK-NEXT: SCHEDQ - Scheduler full: 257 (84.0%)
+# CHECK-NEXT: LQ - Load queue full: 0
+# CHECK-NEXT: SQ - Store queue full: 0
+# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
+
+# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
+# CHECK-NEXT: [# dispatched], [# cycles]
+# CHECK-NEXT: 0, 34 (11.1%)
+# CHECK-NEXT: 1, 172 (56.2%)
+# CHECK-NEXT: 2, 86 (28.1%)
+# CHECK-NEXT: 4, 14 (4.6%)
+
+# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
+# CHECK-NEXT: [# issued], [# cycles]
+# CHECK-NEXT: 0, 5 (1.6%)
+# CHECK-NEXT: 1, 202 (66.0%)
+# CHECK-NEXT: 2, 99 (32.4%)
+
+# CHECK: Scheduler's queue usage:
+# CHECK-NEXT: [1] Resource name.
+# CHECK-NEXT: [2] Average number of used buffer entries.
+# CHECK-NEXT: [3] Maximum number of used buffer entries.
+# CHECK-NEXT: [4] Total number of buffer entries.
+
+# CHECK: [1] [2] [3] [4]
+# CHECK-NEXT: PdEX 36 40 40
+# CHECK-NEXT: PdFPU 0 0 64
+# CHECK-NEXT: PdLoad 19 22 40
+# CHECK-NEXT: PdStore 20 23 24
+
+# CHECK: Resources:
+# CHECK-NEXT: [0.0] - PdAGLU01
+# CHECK-NEXT: [0.1] - PdAGLU01
+# CHECK-NEXT: [1] - PdBranch
+# CHECK-NEXT: [2] - PdCount
+# CHECK-NEXT: [3] - PdDiv
+# CHECK-NEXT: [4] - PdEX0
+# CHECK-NEXT: [5] - PdEX1
+# CHECK-NEXT: [6] - PdFPCVT
+# CHECK-NEXT: [7.0] - PdFPFMA
+# CHECK-NEXT: [7.1] - PdFPFMA
+# CHECK-NEXT: [8.0] - PdFPMAL
+# CHECK-NEXT: [8.1] - PdFPMAL
+# CHECK-NEXT: [9] - PdFPMMA
+# CHECK-NEXT: [10] - PdFPSTO
+# CHECK-NEXT: [11] - PdFPU0
+# CHECK-NEXT: [12] - PdFPU1
+# CHECK-NEXT: [13] - PdFPU2
+# CHECK-NEXT: [14] - PdFPU3
+# CHECK-NEXT: [15] - PdFPXBR
+# CHECK-NEXT: [16.0] - PdLoad
+# CHECK-NEXT: [16.1] - PdLoad
+# CHECK-NEXT: [17] - PdMul
+# CHECK-NEXT: [18] - PdStore
+
+# CHECK: Resource pressure per iteration:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18]
+# CHECK-NEXT: 3.00 3.00 - - - - - - - - - - - - - - - - - 2.00 2.00 - 2.00
+
+# CHECK: Resource pressure by instruction:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18] Instructions:
+# CHECK-NEXT: 0.96 0.04 - - - - - - - - - - - - - - - - - - - - 1.00 movw %sp, (%rax)
+# CHECK-NEXT: 2.00 - - - - - - - - - - - - - - - - - - - 2.00 - - movw (%rcx), %bp
+# CHECK-NEXT: - 2.00 - - - - - - - - - - - - - - - - - 2.00 - - - movw (%rdx), %si
+# CHECK-NEXT: 0.04 0.96 - - - - - - - - - - - - - - - - - - - - 1.00 movw %di, (%rbx)
+
+# CHECK: Timeline view:
+# CHECK-NEXT: Index 0123456789
+
+# 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======eER movw %di, (%rbx)
+
+# 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 movw %sp, (%rax)
+# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movw (%rcx), %bp
+# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movw (%rdx), %si
+# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movw %di, (%rbx)
+
+# CHECK: [2] Code Region
+
+# CHECK: Iterations: 100
+# CHECK-NEXT: Instructions: 400
+# CHECK-NEXT: Total Cycles: 306
+# CHECK-NEXT: Total uOps: 400
+
+# CHECK: Dispatch Width: 4
+# CHECK-NEXT: uOps Per Cycle: 1.31
+# CHECK-NEXT: IPC: 1.31
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# 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 1 1.00 * movl %esp, (%rax)
+# CHECK-NEXT: 1 5 1.00 * movl (%rcx), %ebp
+# CHECK-NEXT: 1 5 1.00 * movl (%rdx), %esi
+# CHECK-NEXT: 1 1 1.00 * movl %edi, (%rbx)
+
+# CHECK: Dynamic Dispatch Stall Cycles:
+# CHECK-NEXT: RAT - Register unavailable: 0
+# CHECK-NEXT: RCU - Retire tokens unavailable: 0
+# CHECK-NEXT: SCHEDQ - Scheduler full: 257 (84.0%)
+# CHECK-NEXT: LQ - Load queue full: 0
+# CHECK-NEXT: SQ - Store queue full: 0
+# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
+
+# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
+# CHECK-NEXT: [# dispatched], [# cycles]
+# CHECK-NEXT: 0, 34 (11.1%)
+# CHECK-NEXT: 1, 172 (56.2%)
+# CHECK-NEXT: 2, 86 (28.1%)
+# CHECK-NEXT: 4, 14 (4.6%)
+
+# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
+# CHECK-NEXT: [# issued], [# cycles]
+# CHECK-NEXT: 0, 5 (1.6%)
+# CHECK-NEXT: 1, 202 (66.0%)
+# CHECK-NEXT: 2, 99 (32.4%)
+
+# CHECK: Scheduler's queue usage:
+# CHECK-NEXT: [1] Resource name.
+# CHECK-NEXT: [2] Average number of used buffer entries.
+# CHECK-NEXT: [3] Maximum number of used buffer entries.
+# CHECK-NEXT: [4] Total number of buffer entries.
+
+# CHECK: [1] [2] [3] [4]
+# CHECK-NEXT: PdEX 36 40 40
+# CHECK-NEXT: PdFPU 0 0 64
+# CHECK-NEXT: PdLoad 19 22 40
+# CHECK-NEXT: PdStore 20 23 24
+
+# CHECK: Resources:
+# CHECK-NEXT: [0.0] - PdAGLU01
+# CHECK-NEXT: [0.1] - PdAGLU01
+# CHECK-NEXT: [1] - PdBranch
+# CHECK-NEXT: [2] - PdCount
+# CHECK-NEXT: [3] - PdDiv
+# CHECK-NEXT: [4] - PdEX0
+# CHECK-NEXT: [5] - PdEX1
+# CHECK-NEXT: [6] - PdFPCVT
+# CHECK-NEXT: [7.0] - PdFPFMA
+# CHECK-NEXT: [7.1] - PdFPFMA
+# CHECK-NEXT: [8.0] - PdFPMAL
+# CHECK-NEXT: [8.1] - PdFPMAL
+# CHECK-NEXT: [9] - PdFPMMA
+# CHECK-NEXT: [10] - PdFPSTO
+# CHECK-NEXT: [11] - PdFPU0
+# CHECK-NEXT: [12] - PdFPU1
+# CHECK-NEXT: [13] - PdFPU2
+# CHECK-NEXT: [14] - PdFPU3
+# CHECK-NEXT: [15] - PdFPXBR
+# CHECK-NEXT: [16.0] - PdLoad
+# CHECK-NEXT: [16.1] - PdLoad
+# CHECK-NEXT: [17] - PdMul
+# CHECK-NEXT: [18] - PdStore
+
+# CHECK: Resource pressure per iteration:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18]
+# CHECK-NEXT: 3.00 3.00 - - - - - - - - - - - - - - - - - 2.00 2.00 - 2.00
+
+# CHECK: Resource pressure by instruction:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18] Instructions:
+# CHECK-NEXT: 0.96 0.04 - - - - - - - - - - - - - - - - - - - - 1.00 movl %esp, (%rax)
+# CHECK-NEXT: 2.00 - - - - - - - - - - - - - - - - - - - 2.00 - - movl (%rcx), %ebp
+# CHECK-NEXT: - 2.00 - - - - - - - - - - - - - - - - - 2.00 - - - movl (%rdx), %esi
+# CHECK-NEXT: 0.04 0.96 - - - - - - - - - - - - - - - - - - - - 1.00 movl %edi, (%rbx)
+
+# CHECK: Timeline view:
+# CHECK-NEXT: Index 0123456789
+
+# 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======eER movl %edi, (%rbx)
+
+# 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 movl %esp, (%rax)
+# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movl (%rcx), %ebp
+# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movl (%rdx), %esi
+# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movl %edi, (%rbx)
+
+# CHECK: [3] Code Region
+
+# CHECK: Iterations: 100
+# CHECK-NEXT: Instructions: 400
+# CHECK-NEXT: Total Cycles: 306
+# CHECK-NEXT: Total uOps: 400
+
+# CHECK: Dispatch Width: 4
+# CHECK-NEXT: uOps Per Cycle: 1.31
+# CHECK-NEXT: IPC: 1.31
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# 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 1 1.00 * movq %rsp, (%rax)
+# CHECK-NEXT: 1 5 1.00 * movq (%rcx), %rbp
+# CHECK-NEXT: 1 5 1.00 * movq (%rdx), %rsi
+# CHECK-NEXT: 1 1 1.00 * movq %rdi, (%rbx)
+
+# CHECK: Dynamic Dispatch Stall Cycles:
+# CHECK-NEXT: RAT - Register unavailable: 0
+# CHECK-NEXT: RCU - Retire tokens unavailable: 0
+# CHECK-NEXT: SCHEDQ - Scheduler full: 257 (84.0%)
+# CHECK-NEXT: LQ - Load queue full: 0
+# CHECK-NEXT: SQ - Store queue full: 0
+# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
+
+# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
+# CHECK-NEXT: [# dispatched], [# cycles]
+# CHECK-NEXT: 0, 34 (11.1%)
+# CHECK-NEXT: 1, 172 (56.2%)
+# CHECK-NEXT: 2, 86 (28.1%)
+# CHECK-NEXT: 4, 14 (4.6%)
+
+# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
+# CHECK-NEXT: [# issued], [# cycles]
+# CHECK-NEXT: 0, 5 (1.6%)
+# CHECK-NEXT: 1, 202 (66.0%)
+# CHECK-NEXT: 2, 99 (32.4%)
+
+# CHECK: Scheduler's queue usage:
+# CHECK-NEXT: [1] Resource name.
+# CHECK-NEXT: [2] Average number of used buffer entries.
+# CHECK-NEXT: [3] Maximum number of used buffer entries.
+# CHECK-NEXT: [4] Total number of buffer entries.
+
+# CHECK: [1] [2] [3] [4]
+# CHECK-NEXT: PdEX 36 40 40
+# CHECK-NEXT: PdFPU 0 0 64
+# CHECK-NEXT: PdLoad 19 22 40
+# CHECK-NEXT: PdStore 20 23 24
+
+# CHECK: Resources:
+# CHECK-NEXT: [0.0] - PdAGLU01
+# CHECK-NEXT: [0.1] - PdAGLU01
+# CHECK-NEXT: [1] - PdBranch
+# CHECK-NEXT: [2] - PdCount
+# CHECK-NEXT: [3] - PdDiv
+# CHECK-NEXT: [4] - PdEX0
+# CHECK-NEXT: [5] - PdEX1
+# CHECK-NEXT: [6] - PdFPCVT
+# CHECK-NEXT: [7.0] - PdFPFMA
+# CHECK-NEXT: [7.1] - PdFPFMA
+# CHECK-NEXT: [8.0] - PdFPMAL
+# CHECK-NEXT: [8.1] - PdFPMAL
+# CHECK-NEXT: [9] - PdFPMMA
+# CHECK-NEXT: [10] - PdFPSTO
+# CHECK-NEXT: [11] - PdFPU0
+# CHECK-NEXT: [12] - PdFPU1
+# CHECK-NEXT: [13] - PdFPU2
+# CHECK-NEXT: [14] - PdFPU3
+# CHECK-NEXT: [15] - PdFPXBR
+# CHECK-NEXT: [16.0] - PdLoad
+# CHECK-NEXT: [16.1] - PdLoad
+# CHECK-NEXT: [17] - PdMul
+# CHECK-NEXT: [18] - PdStore
+
+# CHECK: Resource pressure per iteration:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18]
+# CHECK-NEXT: 3.00 3.00 - - - - - - - - - - - - - - - - - 2.00 2.00 - 2.00
+
+# CHECK: Resource pressure by instruction:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18] Instructions:
+# CHECK-NEXT: 0.96 0.04 - - - - - - - - - - - - - - - - - - - - 1.00 movq %rsp, (%rax)
+# CHECK-NEXT: 2.00 - - - - - - - - - - - - - - - - - - - 2.00 - - movq (%rcx), %rbp
+# CHECK-NEXT: - 2.00 - - - - - - - - - - - - - - - - - 2.00 - - - movq (%rdx), %rsi
+# CHECK-NEXT: 0.04 0.96 - - - - - - - - - - - - - - - - - - - - 1.00 movq %rdi, (%rbx)
+
+# CHECK: Timeline view:
+# CHECK-NEXT: Index 0123456789
+
+# 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======eER movq %rdi, (%rbx)
+
+# 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 movq %rsp, (%rax)
+# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movq (%rcx), %rbp
+# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movq (%rdx), %rsi
+# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movq %rdi, (%rbx)
+
+# CHECK: [4] Code Region
+
+# CHECK: Iterations: 100
+# CHECK-NEXT: Instructions: 400
+# CHECK-NEXT: Total Cycles: 593
+# CHECK-NEXT: Total uOps: 400
+
+# CHECK: Dispatch Width: 4
+# CHECK-NEXT: uOps Per Cycle: 0.67
+# CHECK-NEXT: IPC: 0.67
+# 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: 1 2 1.50 * U movd %mm0, (%rax)
+# CHECK-NEXT: 1 5 1.50 * movd (%rcx), %mm1
+# CHECK-NEXT: 1 5 1.50 * movd (%rdx), %mm2
+# CHECK-NEXT: 1 2 1.50 * U movd %mm3, (%rbx)
+
+# CHECK: Dynamic Dispatch Stall Cycles:
+# CHECK-NEXT: RAT - Register unavailable: 0
+# CHECK-NEXT: RCU - Retire tokens unavailable: 0
+# CHECK-NEXT: SCHEDQ - Scheduler full: 187 (31.5%)
+# CHECK-NEXT: LQ - Load queue full: 0
+# CHECK-NEXT: SQ - Store queue full: 342 (57.7%)
+# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
+
+# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
+# CHECK-NEXT: [# dispatched], [# cycles]
+# CHECK-NEXT: 0, 403 (68.0%)
+# CHECK-NEXT: 1, 90 (15.2%)
+# CHECK-NEXT: 2, 2 (0.3%)
+# CHECK-NEXT: 3, 86 (14.5%)
+# CHECK-NEXT: 4, 12 (2.0%)
+
+# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
+# CHECK-NEXT: [# issued], [# cycles]
+# CHECK-NEXT: 0, 292 (49.2%)
+# CHECK-NEXT: 1, 202 (34.1%)
+# CHECK-NEXT: 2, 99 (16.7%)
+
+# CHECK: Scheduler's queue usage:
+# CHECK-NEXT: [1] Resource name.
+# CHECK-NEXT: [2] Average number of used buffer entries.
+# CHECK-NEXT: [3] Maximum number of used buffer entries.
+# CHECK-NEXT: [4] Total number of buffer entries.
+
+# CHECK: [1] [2] [3] [4]
+# CHECK-NEXT: PdEX 23 40 40
+# CHECK-NEXT: PdFPU 23 40 64
+# CHECK-NEXT: PdLoad 3 22 40
+# CHECK-NEXT: PdStore 22 24 24
+
+# CHECK: Resources:
+# CHECK-NEXT: [0.0] - PdAGLU01
+# CHECK-NEXT: [0.1] - PdAGLU01
+# CHECK-NEXT: [1] - PdBranch
+# CHECK-NEXT: [2] - PdCount
+# CHECK-NEXT: [3] - PdDiv
+# CHECK-NEXT: [4] - PdEX0
+# CHECK-NEXT: [5] - PdEX1
+# CHECK-NEXT: [6] - PdFPCVT
+# CHECK-NEXT: [7.0] - PdFPFMA
+# CHECK-NEXT: [7.1] - PdFPFMA
+# CHECK-NEXT: [8.0] - PdFPMAL
+# CHECK-NEXT: [8.1] - PdFPMAL
+# CHECK-NEXT: [9] - PdFPMMA
+# CHECK-NEXT: [10] - PdFPSTO
+# CHECK-NEXT: [11] - PdFPU0
+# CHECK-NEXT: [12] - PdFPU1
+# CHECK-NEXT: [13] - PdFPU2
+# CHECK-NEXT: [14] - PdFPU3
+# CHECK-NEXT: [15] - PdFPXBR
+# CHECK-NEXT: [16.0] - PdLoad
+# CHECK-NEXT: [16.1] - PdLoad
+# CHECK-NEXT: [17] - PdMul
+# CHECK-NEXT: [18] - PdStore
+
+# CHECK: Resource pressure per iteration:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18]
+# CHECK-NEXT: 4.00 4.00 - - - - - - - - 3.00 3.00 - 2.00 1.00 1.00 3.00 3.00 - 3.00 3.00 - 2.00
+
+# CHECK: Resource pressure by instruction:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18] Instructions:
+# CHECK-NEXT: - 1.00 - - - - - - - - - - - 1.00 - - - 3.00 - - - - 1.00 movd %mm0, (%rax)
+# CHECK-NEXT: 0.36 2.64 - - - - - - - - - 3.00 - - - 1.00 - - - - 3.00 - - movd (%rcx), %mm1
+# CHECK-NEXT: 2.64 0.36 - - - - - - - - 3.00 - - - 1.00 - - - - 3.00 - - - movd (%rdx), %mm2
+# CHECK-NEXT: 1.00 - - - - - - - - - - - - 1.00 - - 3.00 - - - - - 1.00 movd %mm3, (%rbx)
+
+# CHECK: Timeline view:
+# CHECK-NEXT: 0
+# CHECK-NEXT: Index 0123456789
+
+# 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======eeER movd %mm3, (%rbx)
+
+# 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 movd %mm0, (%rax)
+# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movd (%rcx), %mm1
+# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movd (%rdx), %mm2
+# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movd %mm3, (%rbx)
+
+# CHECK: [5] Code Region
+
+# CHECK: Iterations: 100
+# CHECK-NEXT: Instructions: 400
+# CHECK-NEXT: Total Cycles: 405
+# CHECK-NEXT: Total uOps: 400
+
+# CHECK: Dispatch Width: 4
+# CHECK-NEXT: uOps Per Cycle: 0.99
+# CHECK-NEXT: IPC: 0.99
+# 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: 1 1 1.50 * movaps %xmm0, (%rax)
+# CHECK-NEXT: 1 5 1.50 * movaps (%rcx), %xmm1
+# CHECK-NEXT: 1 5 1.50 * movaps (%rdx), %xmm2
+# CHECK-NEXT: 1 1 1.50 * movaps %xmm3, (%rbx)
+
+# CHECK: Dynamic Dispatch Stall Cycles:
+# CHECK-NEXT: RAT - Register unavailable: 0
+# CHECK-NEXT: RCU - Retire tokens unavailable: 0
+# CHECK-NEXT: SCHEDQ - Scheduler full: 347 (85.7%)
+# CHECK-NEXT: LQ - Load queue full: 0
+# CHECK-NEXT: SQ - Store queue full: 0
+# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
+
+# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
+# CHECK-NEXT: [# dispatched], [# cycles]
+# CHECK-NEXT: 0, 131 (32.3%)
+# CHECK-NEXT: 1, 174 (43.0%)
+# CHECK-NEXT: 2, 87 (21.5%)
+# CHECK-NEXT: 4, 13 (3.2%)
+
+# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
+# CHECK-NEXT: [# issued], [# cycles]
+# CHECK-NEXT: 0, 104 (25.7%)
+# CHECK-NEXT: 1, 202 (49.9%)
+# CHECK-NEXT: 2, 99 (24.4%)
+
+# CHECK: Scheduler's queue usage:
+# CHECK-NEXT: [1] Resource name.
+# CHECK-NEXT: [2] Average number of used buffer entries.
+# CHECK-NEXT: [3] Maximum number of used buffer entries.
+# CHECK-NEXT: [4] Total number of buffer entries.
+
+# CHECK: [1] [2] [3] [4]
+# CHECK-NEXT: PdEX 37 40 40
+# CHECK-NEXT: PdFPU 37 40 64
+# CHECK-NEXT: PdLoad 19 22 40
+# CHECK-NEXT: PdStore 20 22 24
+
+# CHECK: Resources:
+# CHECK-NEXT: [0.0] - PdAGLU01
+# CHECK-NEXT: [0.1] - PdAGLU01
+# CHECK-NEXT: [1] - PdBranch
+# CHECK-NEXT: [2] - PdCount
+# CHECK-NEXT: [3] - PdDiv
+# CHECK-NEXT: [4] - PdEX0
+# CHECK-NEXT: [5] - PdEX1
+# CHECK-NEXT: [6] - PdFPCVT
+# CHECK-NEXT: [7.0] - PdFPFMA
+# CHECK-NEXT: [7.1] - PdFPFMA
+# CHECK-NEXT: [8.0] - PdFPMAL
+# CHECK-NEXT: [8.1] - PdFPMAL
+# CHECK-NEXT: [9] - PdFPMMA
+# CHECK-NEXT: [10] - PdFPSTO
+# CHECK-NEXT: [11] - PdFPU0
+# CHECK-NEXT: [12] - PdFPU1
+# CHECK-NEXT: [13] - PdFPU2
+# CHECK-NEXT: [14] - PdFPU3
+# CHECK-NEXT: [15] - PdFPXBR
+# CHECK-NEXT: [16.0] - PdLoad
+# CHECK-NEXT: [16.1] - PdLoad
+# CHECK-NEXT: [17] - PdMul
+# CHECK-NEXT: [18] - PdStore
+
+# CHECK: Resource pressure per iteration:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18]
+# CHECK-NEXT: 4.00 4.00 - - - - - - 3.00 3.00 - - - 2.00 1.00 1.00 3.00 3.00 - 3.00 3.00 - 2.00
+
+# CHECK: Resource pressure by instruction:
+# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18] Instructions:
+# CHECK-NEXT: - 1.00 - - - - - - - - - - - 1.00 - - - 3.00 - - - - 1.00 movaps %xmm0, (%rax)
+# CHECK-NEXT: 3.00 - - - - - - - - 3.00 - - - - - 1.00 - - - - 3.00 - - movaps (%rcx), %xmm1
+# CHECK-NEXT: - 3.00 - - - - - - 3.00 - - - - - 1.00 - - - - 3.00 - - - movaps (%rdx), %xmm2
+# CHECK-NEXT: 1.00 - - - - - - - - - - - - 1.00 - - 3.00 - - - - - 1.00 movaps %xmm3, (%rbx)
+
+# CHECK: Timeline view:
+# CHECK-NEXT: Index 0123456789
+
+# 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======eER movaps %xmm3, (%rbx)
+
+# 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 movaps %xmm0, (%rax)
+# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movaps (%rcx), %xmm1
+# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movaps (%rdx), %xmm2
+# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movaps %xmm3, (%rbx)
More information about the llvm-commits
mailing list