diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h --- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h +++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h @@ -1895,6 +1895,22 @@ TTI::TargetCostKind CostKind) { Type *ScalarTy = Ty->getElementType(); unsigned NumVecElts = cast(Ty)->getNumElements(); + if ((Opcode == Instruction::Or || Opcode == Instruction::And) && + ScalarTy == IntegerType::getInt1Ty(Ty->getContext()) && + NumVecElts >= 2) { + // Or reduction for i1 is represented as: + // %val = bitcast to iReduxWidth + // %res = cmp ne iReduxWidth %val, 0 + // And reduction for i1 is represented as: + // %val = bitcast to iReduxWidth + // %res = cmp eq iReduxWidth %val, 11111 + Type *ValTy = IntegerType::get(Ty->getContext(), NumVecElts); + return thisT()->getCastInstrCost(Instruction::BitCast, ValTy, Ty, + TTI::CastContextHint::None, CostKind) + + thisT()->getCmpSelInstrCost(Instruction::ICmp, ValTy, + CmpInst::makeCmpResultType(ValTy), + CmpInst::BAD_ICMP_PREDICATE, CostKind); + } unsigned NumReduxLevels = Log2_32(NumVecElts); unsigned ArithCost = 0; unsigned ShuffleCost = 0; diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp --- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp +++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp @@ -750,8 +750,13 @@ } } else if (ST->hasVector()) { + // Vector to scalar cast. auto *SrcVecTy = cast(Src); - auto *DstVecTy = cast(Dst); + auto *DstVecTy = dyn_cast(Dst); + if (!DstVecTy) { + // TODO: tune vector-to-scalar cast. + return BaseT::getCastInstrCost(Opcode, Dst, Src, CCH, CostKind, I); + } unsigned VF = SrcVecTy->getNumElements(); unsigned NumDstVectors = getNumVectorRegs(Dst); unsigned NumSrcVectors = getNumVectorRegs(Src); diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll --- a/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll +++ b/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll @@ -5,12 +5,12 @@ ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 129 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 364 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 455 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 637 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 1001 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 91 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 181 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 362 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll --- a/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll +++ b/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll @@ -5,12 +5,12 @@ ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 129 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 364 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 455 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 637 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 1001 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 91 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 181 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 362 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll b/llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll --- a/llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll +++ b/llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll @@ -4,13 +4,13 @@ define i32 @reduce_i1(i32 %arg) { ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll b/llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll --- a/llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll +++ b/llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll @@ -4,13 +4,13 @@ define i32 @reduce_i1(i32 %arg) { ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/ARM/reduce-and.ll b/llvm/test/Analysis/CostModel/ARM/reduce-and.ll --- a/llvm/test/Analysis/CostModel/ARM/reduce-and.ll +++ b/llvm/test/Analysis/CostModel/ARM/reduce-and.ll @@ -4,13 +4,13 @@ define i32 @reduce_i1(i32 %arg) { ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 391 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 488 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 682 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 1070 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 385 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/ARM/reduce-or.ll b/llvm/test/Analysis/CostModel/ARM/reduce-or.ll --- a/llvm/test/Analysis/CostModel/ARM/reduce-or.ll +++ b/llvm/test/Analysis/CostModel/ARM/reduce-or.ll @@ -4,13 +4,13 @@ define i32 @reduce_i1(i32 %arg) { ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 391 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 488 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 682 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 1070 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 385 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/PowerPC/reduce-and.ll b/llvm/test/Analysis/CostModel/PowerPC/reduce-and.ll --- a/llvm/test/Analysis/CostModel/PowerPC/reduce-and.ll +++ b/llvm/test/Analysis/CostModel/PowerPC/reduce-and.ll @@ -4,13 +4,13 @@ define i32 @reduce_i1(i32 %arg) { ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 386 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/PowerPC/reduce-or.ll b/llvm/test/Analysis/CostModel/PowerPC/reduce-or.ll --- a/llvm/test/Analysis/CostModel/PowerPC/reduce-or.ll +++ b/llvm/test/Analysis/CostModel/PowerPC/reduce-or.ll @@ -4,13 +4,13 @@ define i32 @reduce_i1(i32 %arg) { ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 386 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll b/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll --- a/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll +++ b/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll @@ -1,18 +1,29 @@ ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py -; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s -; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s +; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefix=RISCV32 +; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefix=RISCV64 define i32 @reduce_i1(i32 %arg) { -; CHECK-LABEL: 'reduce_i1' -; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef +; RISCV32-LABEL: 'reduce_i1' +; RISCV32-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 132 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef +; +; RISCV64-LABEL: 'reduce_i1' +; RISCV64-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/RISCV/reduce-or.ll b/llvm/test/Analysis/CostModel/RISCV/reduce-or.ll --- a/llvm/test/Analysis/CostModel/RISCV/reduce-or.ll +++ b/llvm/test/Analysis/CostModel/RISCV/reduce-or.ll @@ -1,18 +1,29 @@ ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py -; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s -; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s +; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefix=RISCV32 +; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefix=RISCV64 define i32 @reduce_i1(i32 %arg) { -; CHECK-LABEL: 'reduce_i1' -; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef +; RISCV32-LABEL: 'reduce_i1' +; RISCV32-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 132 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) +; RISCV32-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef +; +; RISCV64-LABEL: 'reduce_i1' +; RISCV64-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) +; RISCV64-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/SystemZ/reduce-and.ll b/llvm/test/Analysis/CostModel/SystemZ/reduce-and.ll --- a/llvm/test/Analysis/CostModel/SystemZ/reduce-and.ll +++ b/llvm/test/Analysis/CostModel/SystemZ/reduce-and.ll @@ -4,13 +4,13 @@ define i32 @reduce_i1(i32 %arg) { ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 258 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/SystemZ/reduce-or.ll b/llvm/test/Analysis/CostModel/SystemZ/reduce-or.ll --- a/llvm/test/Analysis/CostModel/SystemZ/reduce-or.ll +++ b/llvm/test/Analysis/CostModel/SystemZ/reduce-or.ll @@ -4,13 +4,13 @@ define i32 @reduce_i1(i32 %arg) { ; CHECK-LABEL: 'reduce_i1' ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 258 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)