[llvm] [AArch64] Update IssueWidth for Neoverse V1, N1, N3 (PR #154495)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Aug 20 02:31:15 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
Author: Simon Wallis (simonwallis2)
<details>
<summary>Changes</summary>
Recently the IssueWidth in the scheduling model was reduced for Neoverse-V2 and N2. This patch does the same for Neoverse-V1, N1 and N3.
On Neoverse-V1, various values of IssueWidth (15, 8, 7, 6, 5) were tried with runs of various workloads.
The highest overall geomean score was achieved with an issue width of 8. No significant regressions were noted.
On Neoverse-N1, various values of IssueWidth (8, 6, 5, 4, 3) were tried with runs of various workloads.
The highest overall geomean score was achieved with an issue width of 3. No significant regressions were noted.
On Neoverse-N3, it makes sense to do exactly the same as was done for N2. It is proposed to use an issue width of 5.
Related V2 PR: https://github.com/llvm/llvm-project/pull/142565
Related N2 PR: https://github.com/llvm/llvm-project/pull/145717
---
Patch is 964.04 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/154495.diff
12 Files Affected:
- (modified) llvm/lib/Target/AArch64/AArch64SchedNeoverseN1.td (+1-1)
- (modified) llvm/lib/Target/AArch64/AArch64SchedNeoverseN3.td (+1-1)
- (modified) llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td (+1-1)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/N1-writeback.s (+2214-2203)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/N3-writeback.s (+1916-1906)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-basic-instructions.s (+1-1)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-clear-upper-regs.s (+16-16)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s (+123-123)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-misc-instructions.s (+15-15)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-sve-instructions.s (+9-9)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s (+1457-1456)
- (modified) llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s (+1-1)
``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64SchedNeoverseN1.td b/llvm/lib/Target/AArch64/AArch64SchedNeoverseN1.td
index 524fa33f498bb..9da42322dd10d 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedNeoverseN1.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedNeoverseN1.td
@@ -15,7 +15,7 @@
//===----------------------------------------------------------------------===//
def NeoverseN1Model : SchedMachineModel {
- let IssueWidth = 8; // Maximum micro-ops dispatch rate.
+ let IssueWidth = 3; // Maximum micro-ops dispatch rate.
let MicroOpBufferSize = 128; // NOTE: Copied from Cortex-A76.
let LoadLatency = 4; // Optimistic load latency.
let MispredictPenalty = 11; // Cycles cost of branch mispredicted.
diff --git a/llvm/lib/Target/AArch64/AArch64SchedNeoverseN3.td b/llvm/lib/Target/AArch64/AArch64SchedNeoverseN3.td
index e44d40f8d7020..cd0d8a9186d5b 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedNeoverseN3.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedNeoverseN3.td
@@ -11,7 +11,7 @@
//===----------------------------------------------------------------------===//
def NeoverseN3Model : SchedMachineModel {
- let IssueWidth = 10; // Micro-ops dispatched at a time.
+ let IssueWidth = 5; // Micro-ops dispatched at a time.
let MicroOpBufferSize = 160; // Entries in micro-op re-order buffer. NOTE: Copied from N2.
let LoadLatency = 4; // Optimistic load latency.
let MispredictPenalty = 10; // Extra cycles for mispredicted branch. NOTE: Copied from N2.
diff --git a/llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td b/llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td
index 44625a2034d9d..b78c5e90d6338 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td
@@ -19,7 +19,7 @@
//===----------------------------------------------------------------------===//
def NeoverseV1Model : SchedMachineModel {
- let IssueWidth = 15; // Maximum micro-ops dispatch rate.
+ let IssueWidth = 8; // Maximum micro-ops dispatch rate.
let MicroOpBufferSize = 256; // Micro-op re-order buffer.
let LoadLatency = 4; // Optimistic load latency.
let MispredictPenalty = 11; // Cycles cost of branch mispredicted.
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..127c8c30fc2c6 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/N1-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/N1-writeback.s
@@ -1165,10 +1165,10 @@ add x0, x27, 1
# CHECK-NEXT: Total Cycles: 507
# CHECK-NEXT: Total uOps: 1500
-# CHECK: Dispatch Width: 8
+# CHECK: Dispatch Width: 3
# CHECK-NEXT: uOps Per Cycle: 2.96
# CHECK-NEXT: IPC: 1.97
-# CHECK-NEXT: Block RThroughput: 3.3
+# CHECK-NEXT: Block RThroughput: 5.0
# CHECK: Timeline view:
# CHECK-NEXT: 01
@@ -1176,14 +1176,14 @@ add x0, x27, 1
# 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: [0,2] .DeeeeeER .. ld1 { v1.2d }, [x27], #16
+# CHECK-NEXT: [0,3] .D=eE---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: [0,6] . DeeeeeER. ld1 { v1.4h }, [x27], #8
+# CHECK-NEXT: [0,7] . D=eE---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: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
@@ -1194,15 +1194,15 @@ add x0, x27, 1
# CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 1 1.0 1.0 0.0 ld1 { v1.1d }, [x27], #8
# CHECK-NEXT: 1. 1 2.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 2. 1 2.0 0.0 0.0 ld1 { v1.2d }, [x27], #16
-# CHECK-NEXT: 3. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 4. 1 3.0 0.0 0.0 ld1 { v1.2s }, [x27], #8
-# CHECK-NEXT: 5. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 6. 1 3.0 0.0 0.0 ld1 { v1.4h }, [x27], #8
-# CHECK-NEXT: 7. 1 4.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 8. 1 4.0 0.0 0.0 ld1 { v1.4s }, [x27], #16
-# CHECK-NEXT: 9. 1 5.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 1 3.0 0.1 1.5 <total>
+# CHECK-NEXT: 2. 1 1.0 0.0 0.0 ld1 { v1.2d }, [x27], #16
+# CHECK-NEXT: 3. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 4. 1 1.0 0.0 0.0 ld1 { v1.2s }, [x27], #8
+# CHECK-NEXT: 5. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 6. 1 1.0 0.0 0.0 ld1 { v1.4h }, [x27], #8
+# CHECK-NEXT: 7. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 8. 1 1.0 0.0 0.0 ld1 { v1.4s }, [x27], #16
+# CHECK-NEXT: 9. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 1 1.5 0.1 1.5 <total>
# CHECK: [1] Code Region - G02
@@ -1211,10 +1211,10 @@ add x0, x27, 1
# CHECK-NEXT: Total Cycles: 507
# CHECK-NEXT: Total uOps: 1500
-# CHECK: Dispatch Width: 8
+# CHECK: Dispatch Width: 3
# CHECK-NEXT: uOps Per Cycle: 2.96
# CHECK-NEXT: IPC: 1.97
-# CHECK-NEXT: Block RThroughput: 3.3
+# CHECK-NEXT: Block RThroughput: 5.0
# CHECK: Timeline view:
# CHECK-NEXT: 01
@@ -1222,14 +1222,14 @@ add x0, x27, 1
# 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: [0,2] .DeeeeeER .. ld1 { v1.8h }, [x27], #16
+# CHECK-NEXT: [0,3] .D=eE---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: [0,6] . DeeeeeER. ld1 { v1.1d }, [x27], x28
+# CHECK-NEXT: [0,7] . D=eE---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: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
@@ -1240,15 +1240,15 @@ add x0, x27, 1
# CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 1 1.0 1.0 0.0 ld1 { v1.8b }, [x27], #8
# CHECK-NEXT: 1. 1 2.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 2. 1 2.0 0.0 0.0 ld1 { v1.8h }, [x27], #16
-# CHECK-NEXT: 3. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 4. 1 3.0 0.0 0.0 ld1 { v1.16b }, [x27], #16
-# CHECK-NEXT: 5. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 6. 1 3.0 0.0 0.0 ld1 { v1.1d }, [x27], x28
-# CHECK-NEXT: 7. 1 4.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 8. 1 4.0 0.0 0.0 ld1 { v1.2d }, [x27], x28
-# CHECK-NEXT: 9. 1 5.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 1 3.0 0.1 1.5 <total>
+# CHECK-NEXT: 2. 1 1.0 0.0 0.0 ld1 { v1.8h }, [x27], #16
+# CHECK-NEXT: 3. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 4. 1 1.0 0.0 0.0 ld1 { v1.16b }, [x27], #16
+# CHECK-NEXT: 5. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 6. 1 1.0 0.0 0.0 ld1 { v1.1d }, [x27], x28
+# CHECK-NEXT: 7. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 8. 1 1.0 0.0 0.0 ld1 { v1.2d }, [x27], x28
+# CHECK-NEXT: 9. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 1 1.5 0.1 1.5 <total>
# CHECK: [2] Code Region - G03
@@ -1257,10 +1257,10 @@ add x0, x27, 1
# CHECK-NEXT: Total Cycles: 507
# CHECK-NEXT: Total uOps: 1500
-# CHECK: Dispatch Width: 8
+# CHECK: Dispatch Width: 3
# CHECK-NEXT: uOps Per Cycle: 2.96
# CHECK-NEXT: IPC: 1.97
-# CHECK-NEXT: Block RThroughput: 3.3
+# CHECK-NEXT: Block RThroughput: 5.0
# CHECK: Timeline view:
# CHECK-NEXT: 01
@@ -1268,14 +1268,14 @@ add x0, x27, 1
# 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: [0,2] .DeeeeeER .. ld1 { v1.4h }, [x27], x28
+# CHECK-NEXT: [0,3] .D=eE---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: [0,6] . DeeeeeER. ld1 { v1.8b }, [x27], x28
+# CHECK-NEXT: [0,7] . D=eE---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: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
@@ -1286,42 +1286,42 @@ add x0, x27, 1
# CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 1 1.0 1.0 0.0 ld1 { v1.2s }, [x27], x28
# CHECK-NEXT: 1. 1 2.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 2. 1 2.0 0.0 0.0 ld1 { v1.4h }, [x27], x28
-# CHECK-NEXT: 3. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 4. 1 3.0 0.0 0.0 ld1 { v1.4s }, [x27], x28
-# CHECK-NEXT: 5. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 6. 1 3.0 0.0 0.0 ld1 { v1.8b }, [x27], x28
-# CHECK-NEXT: 7. 1 4.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 8. 1 4.0 0.0 0.0 ld1 { v1.8h }, [x27], x28
-# CHECK-NEXT: 9. 1 5.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 1 3.0 0.1 1.5 <total>
+# CHECK-NEXT: 2. 1 1.0 0.0 0.0 ld1 { v1.4h }, [x27], x28
+# CHECK-NEXT: 3. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 4. 1 1.0 0.0 0.0 ld1 { v1.4s }, [x27], x28
+# CHECK-NEXT: 5. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 6. 1 1.0 0.0 0.0 ld1 { v1.8b }, [x27], x28
+# CHECK-NEXT: 7. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 8. 1 1.0 0.0 0.0 ld1 { v1.8h }, [x27], x28
+# CHECK-NEXT: 9. 1 2.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 1 1.5 0.1 1.5 <total>
# CHECK: [3] Code Region - G04
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 1000
-# CHECK-NEXT: Total Cycles: 507
+# CHECK-NEXT: Total Cycles: 906
# CHECK-NEXT: Total uOps: 1900
-# CHECK: Dispatch Width: 8
-# CHECK-NEXT: uOps Per Cycle: 3.75
-# CHECK-NEXT: IPC: 1.97
-# CHECK-NEXT: Block RThroughput: 4.5
+# CHECK: Dispatch Width: 3
+# CHECK-NEXT: uOps Per Cycle: 2.10
+# CHECK-NEXT: IPC: 1.10
+# CHECK-NEXT: Block RThroughput: 6.3
# CHECK: Timeline view:
-# CHECK-NEXT: 01
+# CHECK-NEXT: 01234
# 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: [0,0] DeeeeeER . . ld1 { v1.16b }, [x27], x28
+# CHECK-NEXT: [0,1] D=eE---R . . add x0, x27, #1
+# CHECK-NEXT: [0,2] .DeeeeeER . . ld1 { v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,3] . DeE---R . . add x0, x27, #1
+# CHECK-NEXT: [0,4] . DeeeeeER . ld1 { v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: [0,5] . DeE---R . add x0, x27, #1
+# CHECK-NEXT: [0,6] . DeeeeeER . ld1 { v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,7] . .DeE---R . add x0, x27, #1
+# CHECK-NEXT: [0,8] . . DeeeeeER ld1 { v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9] . . DeE---R add x0, x27, #1
# CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
@@ -1332,42 +1332,42 @@ add x0, x27, 1
# CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 1 1.0 1.0 0.0 ld1 { v1.16b }, [x27], x28
# CHECK-NEXT: 1. 1 2.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 2. 1 2.0 0.0 0.0 ld1 { v1.1d, v2.1d }, [x27], #16
-# CHECK-NEXT: 3. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 4. 1 2.0 0.0 0.0 ld1 { v1.2d, v2.2d }, [x27], #32
-# CHECK-NEXT: 5. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 6. 1 3.0 0.0 0.0 ld1 { v1.2s, v2.2s }, [x27], #16
-# CHECK-NEXT: 7. 1 4.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 8. 1 3.0 0.0 0.0 ld1 { v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: 9. 1 4.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 1 2.7 0.1 1.5 <total>
+# CHECK-NEXT: 2. 1 1.0 0.0 0.0 ld1 { v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: 3. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 4. 1 1.0 1.0 0.0 ld1 { v1.2d, v2.2d }, [x27], #32
+# CHECK-NEXT: 5. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 6. 1 1.0 1.0 0.0 ld1 { v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: 7. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 8. 1 1.0 1.0 0.0 ld1 { v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: 9. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 1 1.1 0.4 1.5 <total>
# CHECK: [4] Code Region - G05
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 1000
-# CHECK-NEXT: Total Cycles: 507
+# CHECK-NEXT: Total Cycles: 1006
# CHECK-NEXT: Total uOps: 2000
-# CHECK: Dispatch Width: 8
-# CHECK-NEXT: uOps Per Cycle: 3.94
-# CHECK-NEXT: IPC: 1.97
-# CHECK-NEXT: Block RThroughput: 5.0
+# CHECK: Dispatch Width: 3
+# CHECK-NEXT: uOps Per Cycle: 1.99
+# CHECK-NEXT: IPC: 0.99
+# CHECK-NEXT: Block RThroughput: 6.7
# CHECK: Timeline view:
-# CHECK-NEXT: 01
+# CHECK-NEXT: 012345
# 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: [0,0] DeeeeeER . . ld1 { v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,1] .DeE---R . . add x0, x27, #1
+# CHECK-NEXT: [0,2] . DeeeeeER. . ld1 { v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,3] . DeE---R. . add x0, x27, #1
+# CHECK-NEXT: [0,4] . DeeeeeER . ld1 { v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5] . DeE---R . add x0, x27, #1
+# CHECK-NEXT: [0,6] . .DeeeeeER . ld1 { v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,7] . . DeE---R . add x0, x27, #1
+# CHECK-NEXT: [0,8] . . DeeeeeER ld1 { v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,9] . . DeE---R add x0, x27, #1
# CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
@@ -1377,43 +1377,43 @@ add x0, x27, 1
# CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 1 1.0 1.0 0.0 ld1 { v1.4s, v2.4s }, [x27], #32
-# CHECK-NEXT: 1. 1 2.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 2. 1 2.0 0.0 0.0 ld1 { v1.8b, v2.8b }, [x27], #16
-# CHECK-NEXT: 3. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 4. 1 2.0 0.0 0.0 ld1 { v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: 5. 1 3.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 6. 1 3.0 0.0 0.0 ld1 { v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: 7. 1 4.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 8. 1 3.0 0.0 0.0 ld1 { v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: 9. 1 4.0 0.0 3.0 add x0, x27, #1
-# CHECK-NEXT: 1 2.7 0.1 1.5 <total>
+# CHECK-NEXT: 1. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 2. 1 1.0 1.0 0.0 ld1 { v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: 3. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 4. 1 1.0 1.0 0.0 ld1 { v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: 5. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 6. 1 1.0 1.0 0.0 ld1 { v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: 7. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 8. 1 1.0 1.0 0.0 ld1 { v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: 9. 1 1.0 0.0 3.0 add x0, x27, #1
+# CHECK-NEXT: 1 1.0 0.5 1.5 <total>
# CHECK: [5] Code Region - G06
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 1000
-# CHECK-NEXT: Total Cycles: 507
+# CHECK-NEXT: Total Cycles: 1006
# CHECK-NEXT: Total uOps: 2000
-# CHECK: Dispatch Width: 8
-# CHECK-NEXT: uOps Per Cycle: 3.94
-# CHECK-NEXT: IPC: 1.97
-# CHECK-NEXT: Block RThroughput: 5.0
+# CHECK: Dispatch Width: 3
+# CHECK-NEXT: uOps Per Cycle: 1.99
+# CHECK-NEXT: IPC: 0.99
+# CHECK-NEXT: Block RThroughput: 6.7
# CHECK: Timeline view:
-# CHECK-NEXT: 01
+# CHECK-NEXT: 012345
# CHECK-NEXT: Index 0123456789
-# CHECK: [0,0] DeeeeeER .. ld1 { v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,1] D=eE---R .. ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/154495
More information about the llvm-commits
mailing list