| 1 |
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py |
| 2 |
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=3 -timeline -register-file-stats < %s | FileCheck %s |
| 3 |
|
| 4 |
# The register move from XMM0 to XMM1 can be eliminated at register renaming |
| 5 |
# stage. So, it should not consume pipeline resources. |
| 6 |
|
| 7 |
vxorps %xmm0, %xmm0, %xmm0 |
| 8 |
vmovaps %xmm0, %xmm1 |
| 9 |
vaddps %xmm1, %xmm1, %xmm2 |
| 10 |
|
| 11 |
# CHECK: Iterations: 3 |
| 12 |
# CHECK-NEXT: Instructions: 9 |
| 13 |
# CHECK-NEXT: Total Cycles: 10 |
| 14 |
# CHECK-NEXT: Total uOps: 9 |
| 15 |
|
| 16 |
# CHECK: Dispatch Width: 2 |
| 17 |
# CHECK-NEXT: uOps Per Cycle: 0.90 |
| 18 |
# CHECK-NEXT: IPC: 0.90 |
| 19 |
# CHECK-NEXT: Block RThroughput: 1.5 |
| 20 |
|
| 21 |
# CHECK: Instruction Info: |
| 22 |
# CHECK-NEXT: [1]: #uOps |
| 23 |
# CHECK-NEXT: [2]: Latency |
| 24 |
# CHECK-NEXT: [3]: RThroughput |
| 25 |
# CHECK-NEXT: [4]: MayLoad |
| 26 |
# CHECK-NEXT: [5]: MayStore |
| 27 |
# CHECK-NEXT: [6]: HasSideEffects (U) |
| 28 |
|
| 29 |
# CHECK: [1] [2] [3] [4] [5] [6] Instructions: |
| 30 |
# CHECK-NEXT: 1 0 0.50 vxorps %xmm0, %xmm0, %xmm0 |
| 31 |
# CHECK-NEXT: 1 1 0.50 vmovaps %xmm0, %xmm1 |
| 32 |
# CHECK-NEXT: 1 3 1.00 vaddps %xmm1, %xmm1, %xmm2 |
| 33 |
|
| 34 |
# CHECK: Register File statistics: |
| 35 |
# CHECK-NEXT: Total number of mappings created: 3 |
| 36 |
# CHECK-NEXT: Max number of mappings used: 3 |
| 37 |
|
| 38 |
# CHECK: * Register File #1 -- JFpuPRF: |
| 39 |
# CHECK-NEXT: Number of physical registers: 72 |
| 40 |
# CHECK-NEXT: Total number of mappings created: 3 |
| 41 |
# CHECK-NEXT: Max number of mappings used: 3 |
| 42 |
# CHECK-NEXT: Number of optimizable moves: 3 |
| 43 |
# CHECK-NEXT: Number of moves eliminated: 3 (100.0%) |
| 44 |
# CHECK-NEXT: Number of zero moves: 3 (100.0%) |
| 45 |
# CHECK-NEXT: Max moves eliminated per cycle: 1 |
| 46 |
|
| 47 |
# CHECK: * Register File #2 -- JIntegerPRF: |
| 48 |
# CHECK-NEXT: Number of physical registers: 64 |
| 49 |
# CHECK-NEXT: Total number of mappings created: 0 |
| 50 |
# CHECK-NEXT: Max number of mappings used: 0 |
| 51 |
|
| 52 |
# CHECK: Resources: |
| 53 |
# CHECK-NEXT: [0] - JALU0 |
| 54 |
# CHECK-NEXT: [1] - JALU1 |
| 55 |
# CHECK-NEXT: [2] - JDiv |
| 56 |
# CHECK-NEXT: [3] - JFPA |
| 57 |
# CHECK-NEXT: [4] - JFPM |
| 58 |
# CHECK-NEXT: [5] - JFPU0 |
| 59 |
# CHECK-NEXT: [6] - JFPU1 |
| 60 |
# CHECK-NEXT: [7] - JLAGU |
| 61 |
# CHECK-NEXT: [8] - JMul |
| 62 |
# CHECK-NEXT: [9] - JSAGU |
| 63 |
# CHECK-NEXT: [10] - JSTC |
| 64 |
# CHECK-NEXT: [11] - JVALU0 |
| 65 |
# CHECK-NEXT: [12] - JVALU1 |
| 66 |
# CHECK-NEXT: [13] - JVIMUL |
| 67 |
|
| 68 |
# CHECK: Resource pressure per iteration: |
| 69 |
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] |
| 70 |
# CHECK-NEXT: - - - 1.00 - 1.00 - - - - - - - - |
| 71 |
|
| 72 |
# CHECK: Resource pressure by instruction: |
| 73 |
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: |
| 74 |
# CHECK-NEXT: - - - - - - - - - - - - - - vxorps %xmm0, %xmm0, %xmm0 |
| 75 |
# CHECK-NEXT: - - - - - - - - - - - - - - vmovaps %xmm0, %xmm1 |
| 76 |
# CHECK-NEXT: - - - 1.00 - 1.00 - - - - - - - - vaddps %xmm1, %xmm1, %xmm2 |
| 77 |
|
| 78 |
# CHECK: Timeline view: |
| 79 |
# CHECK-NEXT: Index 0123456789 |
| 80 |
|
| 81 |
# CHECK: [0,0] DR . . vxorps %xmm0, %xmm0, %xmm0 |
| 82 |
# CHECK-NEXT: [0,1] DR . . vmovaps %xmm0, %xmm1 |
| 83 |
# CHECK-NEXT: [0,2] .DeeeER . vaddps %xmm1, %xmm1, %xmm2 |
| 84 |
# CHECK-NEXT: [1,0] .D----R . vxorps %xmm0, %xmm0, %xmm0 |
| 85 |
# CHECK-NEXT: [1,1] . D----R . vmovaps %xmm0, %xmm1 |
| 86 |
# CHECK-NEXT: [1,2] . DeeeER . vaddps %xmm1, %xmm1, %xmm2 |
| 87 |
# CHECK-NEXT: [2,0] . D----R. vxorps %xmm0, %xmm0, %xmm0 |
| 88 |
# CHECK-NEXT: [2,1] . D----R. vmovaps %xmm0, %xmm1 |
| 89 |
# CHECK-NEXT: [2,2] . DeeeER vaddps %xmm1, %xmm1, %xmm2 |
| 90 |
|
| 91 |
# CHECK: Average Wait times (based on the timeline view): |
| 92 |
# CHECK-NEXT: [0]: Executions |
| 93 |
# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue |
| 94 |
# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready |
| 95 |
# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage |
| 96 |
|
| 97 |
# CHECK: [0] [1] [2] [3] |
| 98 |
# CHECK-NEXT: 0. 3 0.0 0.0 2.7 vxorps %xmm0, %xmm0, %xmm0 |
| 99 |
# CHECK-NEXT: 1. 3 0.0 0.0 2.7 vmovaps %xmm0, %xmm1 |
| 100 |
# CHECK-NEXT: 2. 3 1.0 1.0 0.0 vaddps %xmm1, %xmm1, %xmm2 |
| 101 |
# CHECK-NEXT: 3 0.3 0.3 1.8 <total> |