llvm-for-llvmta/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpeq.s

94 lines
4.4 KiB
ArmAsm
Raw Permalink Normal View History

2022-04-25 10:02:23 +02:00
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -timeline -timeline-max-iterations=3 -iterations=1500 < %s | FileCheck %s
# perf stat reports an IPC of 2.00 for this block of code.
# All of the vector packed compares from this test are dependency breaking
# instructions. That means, there is no RAW dependency between any of the
# instructions, and the code can be fully parallelized in hardware.
vpcmpeqb %xmm0, %xmm0, %xmm1
vpcmpeqw %xmm1, %xmm1, %xmm2
vpcmpeqd %xmm2, %xmm2, %xmm3
vpcmpeqq %xmm3, %xmm3, %xmm0
# CHECK: Iterations: 1500
# CHECK-NEXT: Instructions: 6000
# CHECK-NEXT: Total Cycles: 3003
# CHECK-NEXT: Total uOps: 6000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 2.00
# CHECK-NEXT: IPC: 2.00
# CHECK-NEXT: Block RThroughput: 2.0
# 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 0.50 vpcmpeqb %xmm0, %xmm0, %xmm1
# CHECK-NEXT: 1 1 0.50 vpcmpeqw %xmm1, %xmm1, %xmm2
# CHECK-NEXT: 1 1 0.50 vpcmpeqd %xmm2, %xmm2, %xmm3
# CHECK-NEXT: 1 1 0.50 vpcmpeqq %xmm3, %xmm3, %xmm0
# 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: - - - - - 2.00 2.00 - - - - 2.00 2.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpcmpeqb %xmm0, %xmm0, %xmm1
# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqw %xmm1, %xmm1, %xmm2
# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpcmpeqd %xmm2, %xmm2, %xmm3
# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqq %xmm3, %xmm3, %xmm0
# CHECK: Timeline view:
# CHECK-NEXT: Index 012345678
# CHECK: [0,0] DeER . . vpcmpeqb %xmm0, %xmm0, %xmm1
# CHECK-NEXT: [0,1] DeER . . vpcmpeqw %xmm1, %xmm1, %xmm2
# CHECK-NEXT: [0,2] .DeER. . vpcmpeqd %xmm2, %xmm2, %xmm3
# CHECK-NEXT: [0,3] .DeER. . vpcmpeqq %xmm3, %xmm3, %xmm0
# CHECK-NEXT: [1,0] . DeER . vpcmpeqb %xmm0, %xmm0, %xmm1
# CHECK-NEXT: [1,1] . DeER . vpcmpeqw %xmm1, %xmm1, %xmm2
# CHECK-NEXT: [1,2] . DeER . vpcmpeqd %xmm2, %xmm2, %xmm3
# CHECK-NEXT: [1,3] . DeER . vpcmpeqq %xmm3, %xmm3, %xmm0
# CHECK-NEXT: [2,0] . DeER. vpcmpeqb %xmm0, %xmm0, %xmm1
# CHECK-NEXT: [2,1] . DeER. vpcmpeqw %xmm1, %xmm1, %xmm2
# CHECK-NEXT: [2,2] . DeER vpcmpeqd %xmm2, %xmm2, %xmm3
# CHECK-NEXT: [2,3] . DeER vpcmpeqq %xmm3, %xmm3, %xmm0
# 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 1.0 1.0 0.0 vpcmpeqb %xmm0, %xmm0, %xmm1
# CHECK-NEXT: 1. 3 1.0 1.0 0.0 vpcmpeqw %xmm1, %xmm1, %xmm2
# CHECK-NEXT: 2. 3 1.0 1.0 0.0 vpcmpeqd %xmm2, %xmm2, %xmm3
# CHECK-NEXT: 3. 3 1.0 1.0 0.0 vpcmpeqq %xmm3, %xmm3, %xmm0
# CHECK-NEXT: 3 1.0 1.0 0.0 <total>