From 219d4518fce9aafcb5eba9b92fb778837f0a4827 Mon Sep 17 00:00:00 2001 From: David Sherwood Date: Wed, 18 Aug 2021 09:40:21 +0100 Subject: [PATCH] [Analysis][AArch64] Make fixed-width ordered reductions slightly more expensive For tight loops like this: float r = 0; for (int i = 0; i < n; i++) { r += a[i]; } it's better not to vectorise at -O3 using fixed-width ordered reductions on AArch64 targets. Although the resulting number of instructions in the generated code ends up being comparable to not vectorising at all, there may be additional costs on some CPUs, for example perhaps the scheduling is worse. It makes sense to deter vectorisation in tight loops. Differential Revision: https://reviews.llvm.org/D108292 --- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp | 9 +++++++-- llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll | 8 ++++---- .../Transforms/LoopVectorize/AArch64/strict-fadd-cost.ll | 8 ++++---- 3 files changed, 15 insertions(+), 10 deletions(-) diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp index 1c20dddfbf4b..869c2c121177 100644 --- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp +++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp @@ -1999,8 +1999,13 @@ AArch64TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy, Optional FMF, TTI::TargetCostKind CostKind) { if (TTI::requiresOrderedReduction(FMF)) { - if (!isa(ValTy)) - return BaseT::getArithmeticReductionCost(Opcode, ValTy, FMF, CostKind); + if (auto *FixedVTy = dyn_cast(ValTy)) { + InstructionCost BaseCost = + BaseT::getArithmeticReductionCost(Opcode, ValTy, FMF, CostKind); + // Add on extra cost to reflect the extra overhead on some CPUs. We still + // end up vectorizing for more computationally intensive loops. + return BaseCost + FixedVTy->getNumElements(); + } if (Opcode != Instruction::FAdd) return InstructionCost::getInvalid(); diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll index 935f245fcdd2..b1f0c1d714d3 100644 --- a/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll +++ b/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll @@ -2,10 +2,10 @@ define void @strict_fp_reductions() { ; CHECK-LABEL: strict_fp_reductions -; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.0, <4 x float> undef) %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.0, <8 x float> undef) %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef) diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd-cost.ll index 1f309ff3cac1..20ed971e409f 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd-cost.ll @@ -6,8 +6,8 @@ target triple="aarch64-unknown-linux-gnu" -; CHECK-VF4: Found an estimated cost of 17 for VF 4 For instruction: %add = fadd float %0, %sum.07 -; CHECK-VF8: Found an estimated cost of 34 for VF 8 For instruction: %add = fadd float %0, %sum.07 +; CHECK-VF4: Found an estimated cost of 21 for VF 4 For instruction: %add = fadd float %0, %sum.07 +; CHECK-VF8: Found an estimated cost of 42 for VF 8 For instruction: %add = fadd float %0, %sum.07 define float @fadd_strict32(float* noalias nocapture readonly %a, i64 %n) { entry: @@ -28,8 +28,8 @@ for.end: } -; CHECK-VF4: Found an estimated cost of 14 for VF 4 For instruction: %add = fadd double %0, %sum.07 -; CHECK-VF8: Found an estimated cost of 28 for VF 8 For instruction: %add = fadd double %0, %sum.07 +; CHECK-VF4: Found an estimated cost of 18 for VF 4 For instruction: %add = fadd double %0, %sum.07 +; CHECK-VF8: Found an estimated cost of 36 for VF 8 For instruction: %add = fadd double %0, %sum.07 define double @fadd_strict64(double* noalias nocapture readonly %a, i64 %n) { entry: