diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp --- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp +++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp @@ -2735,6 +2735,32 @@ switch (ISD) { default: break; + case ISD::FADD: + { + Type *EltType = ValTy->getElementType(); + if (!EltType->isDoubleTy() && !EltType->isFloatTy() && !EltType->isHalfTy()) + break; + + unsigned NumVecElts = cast(ValTy)->getNumElements(); + unsigned RoundedNumVecElts = pow(2, Log2_32_Ceil(NumVecElts)); + unsigned BitsPerElement = EltType->getScalarSizeInBits(); + unsigned ElementsPerRegister = 128 / BitsPerElement; + + // While there are more elements than fit into a single register, + // we will use element-wise vector adds to reduce the elements. + InstructionCost VectorFADD; + unsigned ElementsLeft = RoundedNumVecElts; + while (ElementsLeft > ElementsPerRegister) { + VectorFADD += ElementsLeft / (ElementsPerRegister * 2); + ElementsLeft /= 2; + } + + // Once the remaining elements fit into a single vector register, + // they will be reduced using pairwise adds (faddp). + InstructionCost FADDPCosts(Log2_32_Ceil(ElementsLeft)); + + return FADDPCosts + VectorFADD; + } case ISD::ADD: if (const auto *Entry = CostTableLookup(CostTblNoPairwise, ISD, MTy)) return (LT.first - 1) + Entry->Cost; diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll --- a/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll +++ b/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll @@ -9,6 +9,7 @@ ; 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) +; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %fadd_v4f8 = call bfloat @llvm.vector.reduce.fadd.v4bf16(bfloat 0xR0000, <4 x bfloat> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; %fadd_v4f16 = call half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef) @@ -17,31 +18,32 @@ %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) %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef) - + %fadd_v4f8 = call bfloat @llvm.vector.reduce.fadd.v4f8(bfloat 0.0, <4 x bfloat> undef) ret void } define void @fast_fp_reductions() { ; CHECK-LABEL: 'fast_fp_reductions' -; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %fadd_v8f16 = call fast half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %fadd_v8f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %fadd_v11f16 = call fast half @llvm.vector.reduce.fadd.v11f16(half 0xH0000, <11 x half> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %fadd_v13f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v13f16(half 0xH0000, <13 x half> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f32 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %fadd_v8f32 = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %fadd_v8f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %fadd_v13f32 = call fast float @llvm.vector.reduce.fadd.v13f32(float 0.000000e+00, <13 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %fadd_v5f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v5f32(float 0.000000e+00, <5 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v2f64 = call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v2f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %fadd_v4f64 = call fast double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %fadd_v4f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.000000e+00, <7 x double> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.000000e+00, <9 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_v4f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v8f16 = call fast half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v8f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fadd_v11f16 = call fast half @llvm.vector.reduce.fadd.v11f16(half 0xH0000, <11 x half> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fadd_v13f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v13f16(half 0xH0000, <13 x half> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_v4f32 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_v4f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v8f32 = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v8f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %fadd_v13f32 = call fast float @llvm.vector.reduce.fadd.v13f32(float 0.000000e+00, <13 x float> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v5f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v5f32(float 0.000000e+00, <5 x float> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %fadd_v2f64 = call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %fadd_v2f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_v4f64 = call fast double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_v4f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.000000e+00, <7 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.000000e+00, <9 x double> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %fadd_v4f8 = call reassoc bfloat @llvm.vector.reduce.fadd.v4bf16(bfloat 0xR0000, <4 x bfloat> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; %fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef) @@ -71,9 +73,13 @@ %fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.0, <7 x double> undef) %fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.0, <9 x double> undef) + %fadd_v4f8 = call reassoc bfloat @llvm.vector.reduce.fadd.v4f8(bfloat 0.0, <4 x bfloat> undef) + ret void } +declare bfloat @llvm.vector.reduce.fadd.v4f8(bfloat, <4 x bfloat>) + declare half @llvm.vector.reduce.fadd.v4f16(half, <4 x half>) declare half @llvm.vector.reduce.fadd.v8f16(half, <8 x half>) declare half @llvm.vector.reduce.fadd.v11f16(half, <11 x half>)