From 336b9dbe88c1f44e16bf98113e821b4eddcb0d0d Mon Sep 17 00:00:00 2001 From: Roman Lebedev Date: Fri, 14 May 2021 11:26:12 +0300 Subject: [PATCH] [X86] AMD Zen 3: same-reg AVX XMM VXORPD is a zero-cycle(!) dep-breaking zero-idiom As confirmed by exegesis measurements, and ref docs. --- llvm/lib/Target/X86/X86ScheduleZnver3.td | 4 +-- .../llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s | 40 +++++++++++----------- 2 files changed, 22 insertions(+), 22 deletions(-) diff --git a/llvm/lib/Target/X86/X86ScheduleZnver3.td b/llvm/lib/Target/X86/X86ScheduleZnver3.td index 6d2a88c..63537a4 100644 --- a/llvm/lib/Target/X86/X86ScheduleZnver3.td +++ b/llvm/lib/Target/X86/X86ScheduleZnver3.td @@ -1535,7 +1535,7 @@ def Zn3WriteFZeroIdiom : SchedWriteVariant<[ SchedVar ]>; // NOTE: XORPSrr, XORPDrr are not zero-cycle! -def : InstRW<[Zn3WriteFZeroIdiom], (instrs VXORPSrr)>; +def : InstRW<[Zn3WriteFZeroIdiom], (instrs VXORPSrr, VXORPDrr)>; def Zn3WriteFZeroIdiomY : SchedWriteVariant<[ SchedVar, [Zn3WriteZeroLatency]>, @@ -1554,7 +1554,7 @@ def : IsZeroIdiomFunction<[ DepBreakingClass<[ XORPSrr, XORPDrr ], ZeroIdiomPredicate>, // AVX XMM Zero-idioms. - DepBreakingClass<[ VXORPSrr ], ZeroIdiomPredicate>, + DepBreakingClass<[ VXORPSrr, VXORPDrr ], ZeroIdiomPredicate>, // AVX YMM Zero-idioms. DepBreakingClass<[ VXORPSYrr ], ZeroIdiomPredicate>, diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s index 2c8de4c..6288c87 100644 --- a/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s +++ b/llvm/test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-xmm.s @@ -106,13 +106,13 @@ vxorpd %xmm1, %xmm0, %xmm0 # CHECK: Iterations: 10000 # CHECK-NEXT: Instructions: 20000 -# CHECK-NEXT: Total Cycles: 20003 +# CHECK-NEXT: Total Cycles: 3337 # CHECK-NEXT: Total uOps: 20000 # CHECK: Dispatch Width: 6 -# CHECK-NEXT: uOps Per Cycle: 1.00 -# CHECK-NEXT: IPC: 1.00 -# CHECK-NEXT: Block RThroughput: 0.5 +# CHECK-NEXT: uOps Per Cycle: 5.99 +# CHECK-NEXT: IPC: 5.99 +# CHECK-NEXT: Block RThroughput: 0.3 # CHECK: Instruction Info: # CHECK-NEXT: [1]: #uOps @@ -123,17 +123,17 @@ vxorpd %xmm1, %xmm0, %xmm0 # CHECK-NEXT: [6]: HasSideEffects (U) # CHECK: [1] [2] [3] [4] [5] [6] Instructions: -# CHECK-NEXT: 1 1 0.25 vxorpd %xmm0, %xmm0, %xmm0 +# CHECK-NEXT: 1 0 0.17 vxorpd %xmm0, %xmm0, %xmm0 # CHECK-NEXT: 1 1 0.25 vxorpd %xmm1, %xmm0, %xmm0 # CHECK: Register File statistics: -# CHECK-NEXT: Total number of mappings created: 20000 -# CHECK-NEXT: Max number of mappings used: 66 +# CHECK-NEXT: Total number of mappings created: 10000 +# CHECK-NEXT: Max number of mappings used: 9 # CHECK: * Register File #1 -- Zn3FpPRF: # CHECK-NEXT: Number of physical registers: 160 -# CHECK-NEXT: Total number of mappings created: 20000 -# CHECK-NEXT: Max number of mappings used: 66 +# CHECK-NEXT: Total number of mappings created: 10000 +# CHECK-NEXT: Max number of mappings used: 9 # CHECK: * Register File #2 -- Zn3IntegerPRF: # CHECK-NEXT: Number of physical registers: 192 @@ -167,20 +167,20 @@ vxorpd %xmm1, %xmm0, %xmm0 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12.0] [12.1] [13] [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] -# CHECK-NEXT: - - - - - - - - 0.50 0.50 0.50 0.50 - - - - - - - - - - - +# CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12.0] [12.1] [13] [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions: -# CHECK-NEXT: - - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - vxorpd %xmm0, %xmm0, %xmm0 -# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - vxorpd %xmm1, %xmm0, %xmm0 +# CHECK-NEXT: - - - - - - - - - - - - - - - - - - - - - - - vxorpd %xmm0, %xmm0, %xmm0 +# CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - vxorpd %xmm1, %xmm0, %xmm0 # CHECK: Timeline view: -# CHECK-NEXT: Index 0123456 +# CHECK-NEXT: Index 0123 -# CHECK: [0,0] DeER .. vxorpd %xmm0, %xmm0, %xmm0 -# CHECK-NEXT: [0,1] D=eER.. vxorpd %xmm1, %xmm0, %xmm0 -# CHECK-NEXT: [1,0] D==eER. vxorpd %xmm0, %xmm0, %xmm0 -# CHECK-NEXT: [1,1] D===eER vxorpd %xmm1, %xmm0, %xmm0 +# CHECK: [0,0] DR . vxorpd %xmm0, %xmm0, %xmm0 +# CHECK-NEXT: [0,1] DeER vxorpd %xmm1, %xmm0, %xmm0 +# CHECK-NEXT: [1,0] D--R vxorpd %xmm0, %xmm0, %xmm0 +# CHECK-NEXT: [1,1] DeER vxorpd %xmm1, %xmm0, %xmm0 # CHECK: Average Wait times (based on the timeline view): # CHECK-NEXT: [0]: Executions @@ -189,6 +189,6 @@ vxorpd %xmm1, %xmm0, %xmm0 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage # CHECK: [0] [1] [2] [3] -# CHECK-NEXT: 0. 2 2.0 0.5 0.0 vxorpd %xmm0, %xmm0, %xmm0 -# CHECK-NEXT: 1. 2 3.0 0.0 0.0 vxorpd %xmm1, %xmm0, %xmm0 -# CHECK-NEXT: 2 2.5 0.3 0.0 +# CHECK-NEXT: 0. 2 0.0 0.0 1.0 vxorpd %xmm0, %xmm0, %xmm0 +# CHECK-NEXT: 1. 2 1.0 1.0 0.0 vxorpd %xmm1, %xmm0, %xmm0 +# CHECK-NEXT: 2 0.5 0.5 0.5 -- 2.7.4