1# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py 2# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -timeline -timeline-max-iterations=3 -iterations=1500 < %s | FileCheck %s 3 4# perf stat reports an IPC of 2.00 for this block of code. 5 6# All of the vector packed compares from this test are dependency breaking 7# instructions. That means, there is no RAW dependency between any of the 8# instructions, and the code can be fully parallelized in hardware. 9 10vpcmpeqb %xmm0, %xmm0, %xmm1 11vpcmpeqw %xmm1, %xmm1, %xmm2 12vpcmpeqd %xmm2, %xmm2, %xmm3 13vpcmpeqq %xmm3, %xmm3, %xmm0 14 15# CHECK: Iterations: 1500 16# CHECK-NEXT: Instructions: 6000 17# CHECK-NEXT: Total Cycles: 3003 18# CHECK-NEXT: Total uOps: 6000 19 20# CHECK: Dispatch Width: 2 21# CHECK-NEXT: uOps Per Cycle: 2.00 22# CHECK-NEXT: IPC: 2.00 23# CHECK-NEXT: Block RThroughput: 2.0 24 25# CHECK: Instruction Info: 26# CHECK-NEXT: [1]: #uOps 27# CHECK-NEXT: [2]: Latency 28# CHECK-NEXT: [3]: RThroughput 29# CHECK-NEXT: [4]: MayLoad 30# CHECK-NEXT: [5]: MayStore 31# CHECK-NEXT: [6]: HasSideEffects (U) 32 33# CHECK: [1] [2] [3] [4] [5] [6] Instructions: 34# CHECK-NEXT: 1 1 0.50 vpcmpeqb %xmm0, %xmm0, %xmm1 35# CHECK-NEXT: 1 1 0.50 vpcmpeqw %xmm1, %xmm1, %xmm2 36# CHECK-NEXT: 1 1 0.50 vpcmpeqd %xmm2, %xmm2, %xmm3 37# CHECK-NEXT: 1 1 0.50 vpcmpeqq %xmm3, %xmm3, %xmm0 38 39# CHECK: Resources: 40# CHECK-NEXT: [0] - JALU0 41# CHECK-NEXT: [1] - JALU1 42# CHECK-NEXT: [2] - JDiv 43# CHECK-NEXT: [3] - JFPA 44# CHECK-NEXT: [4] - JFPM 45# CHECK-NEXT: [5] - JFPU0 46# CHECK-NEXT: [6] - JFPU1 47# CHECK-NEXT: [7] - JLAGU 48# CHECK-NEXT: [8] - JMul 49# CHECK-NEXT: [9] - JSAGU 50# CHECK-NEXT: [10] - JSTC 51# CHECK-NEXT: [11] - JVALU0 52# CHECK-NEXT: [12] - JVALU1 53# CHECK-NEXT: [13] - JVIMUL 54 55# CHECK: Resource pressure per iteration: 56# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] 57# CHECK-NEXT: - - - - - 2.00 2.00 - - - - 2.00 2.00 - 58 59# CHECK: Resource pressure by instruction: 60# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: 61# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpcmpeqb %xmm0, %xmm0, %xmm1 62# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqw %xmm1, %xmm1, %xmm2 63# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpcmpeqd %xmm2, %xmm2, %xmm3 64# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqq %xmm3, %xmm3, %xmm0 65 66# CHECK: Timeline view: 67# CHECK-NEXT: Index 012345678 68 69# CHECK: [0,0] DeER . . vpcmpeqb %xmm0, %xmm0, %xmm1 70# CHECK-NEXT: [0,1] DeER . . vpcmpeqw %xmm1, %xmm1, %xmm2 71# CHECK-NEXT: [0,2] .DeER. . vpcmpeqd %xmm2, %xmm2, %xmm3 72# CHECK-NEXT: [0,3] .DeER. . vpcmpeqq %xmm3, %xmm3, %xmm0 73# CHECK-NEXT: [1,0] . DeER . vpcmpeqb %xmm0, %xmm0, %xmm1 74# CHECK-NEXT: [1,1] . DeER . vpcmpeqw %xmm1, %xmm1, %xmm2 75# CHECK-NEXT: [1,2] . DeER . vpcmpeqd %xmm2, %xmm2, %xmm3 76# CHECK-NEXT: [1,3] . DeER . vpcmpeqq %xmm3, %xmm3, %xmm0 77# CHECK-NEXT: [2,0] . DeER. vpcmpeqb %xmm0, %xmm0, %xmm1 78# CHECK-NEXT: [2,1] . DeER. vpcmpeqw %xmm1, %xmm1, %xmm2 79# CHECK-NEXT: [2,2] . DeER vpcmpeqd %xmm2, %xmm2, %xmm3 80# CHECK-NEXT: [2,3] . DeER vpcmpeqq %xmm3, %xmm3, %xmm0 81 82# CHECK: Average Wait times (based on the timeline view): 83# CHECK-NEXT: [0]: Executions 84# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue 85# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready 86# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage 87 88# CHECK: [0] [1] [2] [3] 89# CHECK-NEXT: 0. 3 1.0 1.0 0.0 vpcmpeqb %xmm0, %xmm0, %xmm1 90# CHECK-NEXT: 1. 3 1.0 1.0 0.0 vpcmpeqw %xmm1, %xmm1, %xmm2 91# CHECK-NEXT: 2. 3 1.0 1.0 0.0 vpcmpeqd %xmm2, %xmm2, %xmm3 92# CHECK-NEXT: 3. 3 1.0 1.0 0.0 vpcmpeqq %xmm3, %xmm3, %xmm0 93# CHECK-NEXT: 3 1.0 1.0 0.0 <total> 94