| # NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py |
| # RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=3 -timeline -register-file-stats < %s | FileCheck %s |
| |
| # The register move from XMM0 to XMM1 can be eliminated at register renaming |
| # stage. So, it should not consume pipeline resources. |
| |
| vxorps %xmm0, %xmm0, %xmm0 |
| vmovaps %xmm0, %xmm1 |
| vaddps %xmm1, %xmm1, %xmm2 |
| |
| # CHECK: Iterations: 3 |
| # CHECK-NEXT: Instructions: 9 |
| # CHECK-NEXT: Total Cycles: 10 |
| # CHECK-NEXT: Total uOps: 9 |
| |
| # CHECK: Dispatch Width: 2 |
| # CHECK-NEXT: uOps Per Cycle: 0.90 |
| # CHECK-NEXT: IPC: 0.90 |
| # CHECK-NEXT: Block RThroughput: 1.5 |
| |
| # 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 0 0.50 vxorps %xmm0, %xmm0, %xmm0 |
| # CHECK-NEXT: 1 1 0.50 vmovaps %xmm0, %xmm1 |
| # CHECK-NEXT: 1 3 1.00 vaddps %xmm1, %xmm1, %xmm2 |
| |
| # CHECK: Register File statistics: |
| # CHECK-NEXT: Total number of mappings created: 3 |
| # CHECK-NEXT: Max number of mappings used: 3 |
| |
| # CHECK: * Register File #1 -- JFpuPRF: |
| # CHECK-NEXT: Number of physical registers: 72 |
| # CHECK-NEXT: Total number of mappings created: 3 |
| # CHECK-NEXT: Max number of mappings used: 3 |
| # CHECK-NEXT: Number of optimizable moves: 3 |
| # CHECK-NEXT: Number of moves eliminated: 3 (100.0%) |
| # CHECK-NEXT: Number of zero moves: 3 (100.0%) |
| # CHECK-NEXT: Max moves eliminated per cycle: 1 |
| |
| # CHECK: * Register File #2 -- JIntegerPRF: |
| # CHECK-NEXT: Number of physical registers: 64 |
| # CHECK-NEXT: Total number of mappings created: 0 |
| # CHECK-NEXT: Max number of mappings used: 0 |
| |
| # CHECK: Resources: |
| # CHECK-NEXT: [0] - JALU0 |
| # CHECK-NEXT: [1] - JALU1 |
| # CHECK-NEXT: [2] - JDiv |
| # CHECK-NEXT: [3] - JFPA |
| # CHECK-NEXT: [4] - JFPM |
| # CHECK-NEXT: [5] - JFPU0 |
| # CHECK-NEXT: [6] - JFPU1 |
| # CHECK-NEXT: [7] - JLAGU |
| # CHECK-NEXT: [8] - JMul |
| # CHECK-NEXT: [9] - JSAGU |
| # CHECK-NEXT: [10] - JSTC |
| # CHECK-NEXT: [11] - JVALU0 |
| # CHECK-NEXT: [12] - JVALU1 |
| # CHECK-NEXT: [13] - JVIMUL |
| |
| # CHECK: Resource pressure per iteration: |
| # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] |
| # CHECK-NEXT: - - - 1.00 - 1.00 - - - - - - - - |
| |
| # CHECK: Resource pressure by instruction: |
| # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: |
| # CHECK-NEXT: - - - - - - - - - - - - - - vxorps %xmm0, %xmm0, %xmm0 |
| # CHECK-NEXT: - - - - - - - - - - - - - - vmovaps %xmm0, %xmm1 |
| # CHECK-NEXT: - - - 1.00 - 1.00 - - - - - - - - vaddps %xmm1, %xmm1, %xmm2 |
| |
| # CHECK: Timeline view: |
| # CHECK-NEXT: Index 0123456789 |
| |
| # CHECK: [0,0] DR . . vxorps %xmm0, %xmm0, %xmm0 |
| # CHECK-NEXT: [0,1] DR . . vmovaps %xmm0, %xmm1 |
| # CHECK-NEXT: [0,2] .DeeeER . vaddps %xmm1, %xmm1, %xmm2 |
| # CHECK-NEXT: [1,0] .D----R . vxorps %xmm0, %xmm0, %xmm0 |
| # CHECK-NEXT: [1,1] . D----R . vmovaps %xmm0, %xmm1 |
| # CHECK-NEXT: [1,2] . DeeeER . vaddps %xmm1, %xmm1, %xmm2 |
| # CHECK-NEXT: [2,0] . D----R. vxorps %xmm0, %xmm0, %xmm0 |
| # CHECK-NEXT: [2,1] . D----R. vmovaps %xmm0, %xmm1 |
| # CHECK-NEXT: [2,2] . DeeeER vaddps %xmm1, %xmm1, %xmm2 |
| |
| # 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. 3 0.0 0.0 2.7 vxorps %xmm0, %xmm0, %xmm0 |
| # CHECK-NEXT: 1. 3 0.0 0.0 2.7 vmovaps %xmm0, %xmm1 |
| # CHECK-NEXT: 2. 3 1.0 1.0 0.0 vaddps %xmm1, %xmm1, %xmm2 |
