Index: lib/Target/X86/X86ScheduleBtVer2.td =================================================================== --- lib/Target/X86/X86ScheduleBtVer2.td +++ lib/Target/X86/X86ScheduleBtVer2.td @@ -654,4 +654,28 @@ PCMPGTDrr, VPCMPGTDrr, PCMPGTQrr, VPCMPGTQrr, PCMPGTWrr, VPCMPGTWrr)>; + +// There are also dependency-breaking one-idioms, but they do consume resources. +def JWriteOneLatency : SchedWriteRes<[JFPU01, JVALU]> { + let Latency = 0; +} + +def JWriteVOneIdiomALU : SchedWriteVariant<[ + SchedVar, [JWriteOneLatency]>, + SchedVar, [WriteVecALU]> +]>; +def : InstRW<[JWriteVOneIdiomALU], (instrs MMX_PCMPEQBirr, + MMX_PCMPEQDirr, + // MMX_PCMPGTQirr is invalid + MMX_PCMPEQWirr)>; + +def JWriteVOneIdiomALUX : SchedWriteVariant<[ + SchedVar, [JWriteOneLatency]>, + SchedVar, [WriteVecALUX]> +]>; +def : InstRW<[JWriteVOneIdiomALUX], (instrs PCMPEQBrr, VPCMPEQBrr, + PCMPEQDrr, VPCMPEQDrr, + PCMPEQQrr, VPCMPEQQrr, + PCMPEQWrr, VPCMPEQWrr)>; + } // SchedModel Index: test/tools/llvm-mca/X86/BtVer2/one-idioms.s =================================================================== --- test/tools/llvm-mca/X86/BtVer2/one-idioms.s +++ test/tools/llvm-mca/X86/BtVer2/one-idioms.s @@ -34,9 +34,9 @@ # CHECK: Iterations: 1 # CHECK-NEXT: Instructions: 19 -# CHECK-NEXT: Total Cycles: 15 +# CHECK-NEXT: Total Cycles: 14 # CHECK-NEXT: Dispatch Width: 2 -# CHECK-NEXT: IPC: 1.27 +# CHECK-NEXT: IPC: 1.36 # CHECK-NEXT: Block RThroughput: 9.5 # CHECK: Instruction Info: @@ -50,32 +50,32 @@ # 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 0 0.50 pcmpeqb %mm2, %mm2 +# CHECK-NEXT: 1 0 0.50 pcmpeqd %mm2, %mm2 +# CHECK-NEXT: 1 0 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-NEXT: 1 0 0.50 pcmpeqb %xmm2, %xmm2 +# CHECK-NEXT: 1 0 0.50 pcmpeqd %xmm2, %xmm2 +# CHECK-NEXT: 1 0 0.50 pcmpeqq %xmm2, %xmm2 +# CHECK-NEXT: 1 0 0.50 pcmpeqw %xmm2, %xmm2 +# CHECK-NEXT: 1 0 0.50 vpcmpeqb %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 1 0 0.50 vpcmpeqd %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 1 0 0.50 vpcmpeqq %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 1 0 0.50 vpcmpeqw %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 1 0 0.50 vpcmpeqb %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 1 0 0.50 vpcmpeqd %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 1 0 0.50 vpcmpeqq %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 1 0 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-NEXT: Max number of mappings used: 8 # 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-NEXT: Max number of mappings used: 8 # CHECK: * Register File #2 -- JIntegerPRF: # CHECK-NEXT: Number of physical registers: 64 @@ -107,16 +107,16 @@ # 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 - - 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 - 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 - - 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 - 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 @@ -125,28 +125,28 @@ # CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpcmpeqw %xmm3, %xmm3, %xmm5 # CHECK: Timeline view: -# CHECK-NEXT: 01234 +# CHECK-NEXT: 0123 # 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: [0,0] DeER . . . paddb %mm2, %mm2 +# CHECK-NEXT: [0,1] D=eER. . . paddb %mm2, %mm2 +# CHECK-NEXT: [0,2] .D=ER. . . pcmpeqb %mm2, %mm2 +# CHECK-NEXT: [0,3] .D=E-R . . pcmpeqd %mm2, %mm2 +# CHECK-NEXT: [0,4] . D=ER . . pcmpeqw %mm2, %mm2 +# CHECK-NEXT: [0,5] . D=eER . . paddb %xmm2, %xmm2 +# CHECK-NEXT: [0,6] . D=eER . . paddb %xmm2, %xmm2 +# CHECK-NEXT: [0,7] . D==ER . . pcmpeqb %xmm2, %xmm2 +# CHECK-NEXT: [0,8] . D=E-R . . pcmpeqd %xmm2, %xmm2 +# CHECK-NEXT: [0,9] . D==ER . . pcmpeqq %xmm2, %xmm2 +# CHECK-NEXT: [0,10] . D=E-R. . pcmpeqw %xmm2, %xmm2 +# CHECK-NEXT: [0,11] . D==ER. . vpcmpeqb %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: [0,12] . .D=E-R . vpcmpeqd %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: [0,13] . .D==ER . vpcmpeqq %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: [0,14] . . D=E-R . vpcmpeqw %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: [0,15] . . D==ER . vpcmpeqb %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: [0,16] . . D=E-R. vpcmpeqd %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: [0,17] . . D==ER. vpcmpeqq %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: [0,18] . . D=E-R vpcmpeqw %xmm3, %xmm3, %xmm5 # CHECK: Average Wait times (based on the timeline view): # CHECK-NEXT: [0]: Executions @@ -158,19 +158,19 @@ # 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: 3. 1 2.0 0.0 1.0 pcmpeqd %mm2, %mm2 +# CHECK-NEXT: 4. 1 2.0 1.0 0.0 pcmpeqw %mm2, %mm2 +# CHECK-NEXT: 5. 1 2.0 2.0 0.0 paddb %xmm2, %xmm2 +# CHECK-NEXT: 6. 1 2.0 0.0 0.0 paddb %xmm2, %xmm2 +# CHECK-NEXT: 7. 1 3.0 0.0 0.0 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: 9. 1 3.0 1.0 0.0 pcmpeqq %xmm2, %xmm2 +# CHECK-NEXT: 10. 1 2.0 0.0 1.0 pcmpeqw %xmm2, %xmm2 +# CHECK-NEXT: 11. 1 3.0 3.0 0.0 vpcmpeqb %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 12. 1 2.0 0.0 1.0 vpcmpeqd %xmm3, %xmm3, %xmm3 +# CHECK-NEXT: 13. 1 3.0 1.0 0.0 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 +# CHECK-NEXT: 15. 1 3.0 1.0 0.0 vpcmpeqb %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 16. 1 2.0 1.0 1.0 vpcmpeqd %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 17. 1 3.0 2.0 0.0 vpcmpeqq %xmm3, %xmm3, %xmm5 +# CHECK-NEXT: 18. 1 2.0 2.0 1.0 vpcmpeqw %xmm3, %xmm3, %xmm5