Index: test/tools/llvm-mca/X86/BtVer2/one-idioms.s =================================================================== --- /dev/null +++ test/tools/llvm-mca/X86/BtVer2/one-idioms.s @@ -0,0 +1,176 @@ +# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -timeline -register-file-stats -iterations=1 < %s | FileCheck %s + +# These are dependency-breaking one-idioms. +# Much like zero-idioms, but they produce ones, and do consume resources. + +# Not zero/one idioms, just to show the non-idiom baseline. +paddb %mm2, %mm2 +paddb %mm2, %mm2 + +pcmpeqb %mm2, %mm2 +pcmpeqd %mm2, %mm2 +# pcmpeqq %mm2, %mm2 # invalid operand for instruction +pcmpeqw %mm2, %mm2 + +# Not zero/one idioms, just to show the non-idiom baseline. +paddb %xmm2, %xmm2 +paddb %xmm2, %xmm2 + +pcmpeqb %xmm2, %xmm2 +pcmpeqd %xmm2, %xmm2 +pcmpeqq %xmm2, %xmm2 +pcmpeqw %xmm2, %xmm2 + +vpcmpeqb %xmm3, %xmm3, %xmm3 +vpcmpeqd %xmm3, %xmm3, %xmm3 +vpcmpeqq %xmm3, %xmm3, %xmm3 +vpcmpeqw %xmm3, %xmm3, %xmm3 + +vpcmpeqb %xmm3, %xmm3, %xmm5 +vpcmpeqd %xmm3, %xmm3, %xmm5 +vpcmpeqq %xmm3, %xmm3, %xmm5 +vpcmpeqw %xmm3, %xmm3, %xmm5 + +# CHECK: Iterations: 1 +# CHECK-NEXT: Instructions: 19 +# CHECK-NEXT: Total Cycles: 15 +# CHECK-NEXT: Dispatch Width: 2 +# CHECK-NEXT: IPC: 1.27 +# CHECK-NEXT: Block RThroughput: 9.5 + +# 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 + +# CHECK: [1] [2] [3] [4] [5] [6] Instructions: +# CHECK-NEXT: 1 1 0.50 paddb %mm2, %mm2 +# CHECK-NEXT: 1 1 0.50 paddb %mm2, %mm2 +# CHECK-NEXT: 1 1 0.50 pcmpeqb %mm2, %mm2 +# CHECK-NEXT: 1 1 0.50 pcmpeqd %mm2, %mm2 +# CHECK-NEXT: 1 1 0.50 pcmpeqw %mm2, %mm2 +# CHECK-NEXT: 1 1 0.50 paddb %xmm2, %xmm2 +# CHECK-NEXT: 1 1 0.50 paddb %xmm2, %xmm2 +# CHECK-NEXT: 1 1 0.50 pcmpeqb %xmm2, %xmm2 +# CHECK-NEXT: 1 1 0.50 pcmpeqd %xmm2, %xmm2 +# CHECK-NEXT: 1 1 0.50 pcmpeqq %xmm2, %xmm2 +# CHECK-NEXT: 1 1 0.50 pcmpeqw %xmm2, %xmm2 +# CHECK-NEXT: 1 1 0.50 vpcmpeqb %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 1 1 0.50 vpcmpeqd %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 1 1 0.50 vpcmpeqq %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 1 1 0.50 vpcmpeqw %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 1 1 0.50 vpcmpeqb %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 1 1 0.50 vpcmpeqd %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 1 1 0.50 vpcmpeqq %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 1 1 0.50 vpcmpeqw %xmm3, %xmm3, %xmm5 + +# CHECK: Register File statistics: +# CHECK-NEXT: Total number of mappings created: 19 +# CHECK-NEXT: Max number of mappings used: 10 + +# CHECK: * Register File #1 -- JFpuPRF: +# CHECK-NEXT: Number of physical registers: 72 +# CHECK-NEXT: Total number of mappings created: 19 +# CHECK-NEXT: Max number of mappings used: 10 + +# 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: - - - - - 9.00 10.00 - - - - 9.00 10.00 - + +# 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 - paddb %mm2, %mm2 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - paddb %mm2, %mm2 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - pcmpeqb %mm2, %mm2 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - pcmpeqd %mm2, %mm2 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - pcmpeqw %mm2, %mm2 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - paddb %xmm2, %xmm2 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - paddb %xmm2, %xmm2 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - pcmpeqb %xmm2, %xmm2 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - pcmpeqd %xmm2, %xmm2 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - pcmpeqq %xmm2, %xmm2 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - pcmpeqw %xmm2, %xmm2 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqb %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqd %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqq %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpcmpeqw %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqb %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpcmpeqd %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpcmpeqq %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpcmpeqw %xmm3, %xmm3, %xmm5 + +# CHECK: Timeline view: +# CHECK-NEXT: 01234 +# CHECK-NEXT: Index 0123456789 + +# CHECK: [0,0] DeER . . . paddb %mm2, %mm2 +# CHECK-NEXT: [0,1] D=eER. . . paddb %mm2, %mm2 +# CHECK-NEXT: [0,2] .D=eER . . pcmpeqb %mm2, %mm2 +# CHECK-NEXT: [0,3] .D==eER . . pcmpeqd %mm2, %mm2 +# CHECK-NEXT: [0,4] . D==eER . . pcmpeqw %mm2, %mm2 +# CHECK-NEXT: [0,5] . DeE--R . . paddb %xmm2, %xmm2 +# CHECK-NEXT: [0,6] . DeE--R . . paddb %xmm2, %xmm2 +# CHECK-NEXT: [0,7] . D=eE-R . . pcmpeqb %xmm2, %xmm2 +# CHECK-NEXT: [0,8] . D=eE-R. . pcmpeqd %xmm2, %xmm2 +# CHECK-NEXT: [0,9] . D==eER. . pcmpeqq %xmm2, %xmm2 +# CHECK-NEXT: [0,10] . D==eER . pcmpeqw %xmm2, %xmm2 +# CHECK-NEXT: [0,11] . DeE--R . vpcmpeqb %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: [0,12] . .DeE--R . vpcmpeqd %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: [0,13] . .D=eE-R . vpcmpeqq %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: [0,14] . . D=eE-R . vpcmpeqw %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: [0,15] . . D==eER . vpcmpeqb %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: [0,16] . . D=eE-R. vpcmpeqd %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: [0,17] . . D==eER. vpcmpeqq %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: [0,18] . . D=eE-R vpcmpeqw %xmm3, %xmm3, %xmm5 + +# 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. 1 1.0 1.0 0.0 paddb %mm2, %mm2 +# CHECK-NEXT: 1. 1 2.0 0.0 0.0 paddb %mm2, %mm2 +# CHECK-NEXT: 2. 1 2.0 0.0 0.0 pcmpeqb %mm2, %mm2 +# CHECK-NEXT: 3. 1 3.0 0.0 0.0 pcmpeqd %mm2, %mm2 +# CHECK-NEXT: 4. 1 3.0 0.0 0.0 pcmpeqw %mm2, %mm2 +# CHECK-NEXT: 5. 1 1.0 1.0 2.0 paddb %xmm2, %xmm2 +# CHECK-NEXT: 6. 1 1.0 0.0 2.0 paddb %xmm2, %xmm2 +# CHECK-NEXT: 7. 1 2.0 0.0 1.0 pcmpeqb %xmm2, %xmm2 +# CHECK-NEXT: 8. 1 2.0 0.0 1.0 pcmpeqd %xmm2, %xmm2 +# CHECK-NEXT: 9. 1 3.0 0.0 0.0 pcmpeqq %xmm2, %xmm2 +# CHECK-NEXT: 10. 1 3.0 0.0 0.0 pcmpeqw %xmm2, %xmm2 +# CHECK-NEXT: 11. 1 1.0 1.0 2.0 vpcmpeqb %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 12. 1 1.0 0.0 2.0 vpcmpeqd %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 13. 1 2.0 0.0 1.0 vpcmpeqq %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 14. 1 2.0 0.0 1.0 vpcmpeqw %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 15. 1 3.0 0.0 0.0 vpcmpeqb %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 16. 1 2.0 0.0 1.0 vpcmpeqd %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 17. 1 3.0 1.0 0.0 vpcmpeqq %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 18. 1 2.0 1.0 1.0 vpcmpeqw %xmm3, %xmm3, %xmm5 Index: test/tools/llvm-mca/X86/BtVer2/zero-idioms.s =================================================================== --- test/tools/llvm-mca/X86/BtVer2/zero-idioms.s +++ test/tools/llvm-mca/X86/BtVer2/zero-idioms.s @@ -8,11 +8,14 @@ pcmpgtb %mm2, %mm2 pcmpgtd %mm2, %mm2 +# pcmpgtq %mm2, %mm2 # invalid operand for instruction pcmpgtw %mm2, %mm2 + pcmpgtb %xmm2, %xmm2 pcmpgtd %xmm2, %xmm2 pcmpgtq %xmm2, %xmm2 pcmpgtw %xmm2, %xmm2 + vpcmpgtb %xmm3, %xmm3, %xmm3 vpcmpgtd %xmm3, %xmm3, %xmm3 vpcmpgtq %xmm3, %xmm3, %xmm3