; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt -passes=slp-vectorizer -slp-vectorize-hor -slp-vectorize-hor-store -S < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=bdver2 | FileCheck %s ; RUN: opt -passes=slp-vectorizer -slp-vectorize-hor -slp-vectorize-hor-store -S < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=bdver2 -slp-threshold=-10 | FileCheck %s --check-prefix=THRESHOLD @n = external local_unnamed_addr global i32, align 4 @arr = common local_unnamed_addr global [20 x float] zeroinitializer, align 16 @arr1 = common local_unnamed_addr global [20 x float] zeroinitializer, align 16 @res = external local_unnamed_addr global float, align 4 define float @baz() { ; CHECK-LABEL: @baz( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr @n, align 4 ; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP0]], 3 ; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr @arr, align 16 ; CHECK-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr @arr1, align 16 ; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <4 x float> [[TMP2]], [[TMP1]] ; CHECK-NEXT: [[TMP5:%.*]] = fmul fast float [[CONV]], 2.000000e+00 ; CHECK-NEXT: [[TMP4:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> [[TMP3]]) ; CHECK-NEXT: [[TMP6:%.*]] = fmul fast float [[TMP4]], 2.000000e+00 ; CHECK-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP5]], [[TMP6]] ; CHECK-NEXT: store float [[OP_RDX]], ptr @res, align 4 ; CHECK-NEXT: ret float [[OP_RDX]] ; ; THRESHOLD-LABEL: @baz( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[TMP0:%.*]] = load i32, ptr @n, align 4 ; THRESHOLD-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP0]], 3 ; THRESHOLD-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; THRESHOLD-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr @arr, align 16 ; THRESHOLD-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr @arr1, align 16 ; THRESHOLD-NEXT: [[TMP3:%.*]] = fmul fast <4 x float> [[TMP2]], [[TMP1]] ; THRESHOLD-NEXT: [[TMP4:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> [[TMP3]]) ; THRESHOLD-NEXT: [[TMP5:%.*]] = insertelement <2 x float> poison, float [[CONV]], i32 0 ; THRESHOLD-NEXT: [[TMP6:%.*]] = insertelement <2 x float> [[TMP5]], float [[TMP4]], i32 1 ; THRESHOLD-NEXT: [[TMP7:%.*]] = fmul fast <2 x float> [[TMP6]], splat (float 2.000000e+00) ; THRESHOLD-NEXT: [[TMP8:%.*]] = extractelement <2 x float> [[TMP7]], i32 0 ; THRESHOLD-NEXT: [[TMP9:%.*]] = extractelement <2 x float> [[TMP7]], i32 1 ; THRESHOLD-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP8]], [[TMP9]] ; THRESHOLD-NEXT: store float [[OP_RDX]], ptr @res, align 4 ; THRESHOLD-NEXT: ret float [[OP_RDX]] ; entry: %0 = load i32, ptr @n, align 4 %mul = mul nsw i32 %0, 3 %conv = sitofp i32 %mul to float %1 = load float, ptr @arr, align 16 %2 = load float, ptr @arr1, align 16 %mul4 = fmul fast float %2, %1 %add = fadd fast float %mul4, %conv %3 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 1), align 4 %4 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 1), align 4 %mul4.1 = fmul fast float %4, %3 %add.1 = fadd fast float %mul4.1, %add %5 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 2), align 8 %6 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 2), align 8 %mul4.2 = fmul fast float %6, %5 %add.2 = fadd fast float %mul4.2, %add.1 %7 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 3), align 4 %8 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 3), align 4 %mul4.3 = fmul fast float %8, %7 %add.3 = fadd fast float %mul4.3, %add.2 %add7 = fadd fast float %add.3, %conv %add19 = fadd fast float %mul4, %add7 %add19.1 = fadd fast float %mul4.1, %add19 %add19.2 = fadd fast float %mul4.2, %add19.1 %add19.3 = fadd fast float %mul4.3, %add19.2 store float %add19.3, ptr @res, align 4 ret float %add19.3 } define float @bazz() { ; CHECK-LABEL: @bazz( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr @n, align 4 ; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP0]], 3 ; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; CHECK-NEXT: [[MUL5:%.*]] = shl nsw i32 [[TMP0]], 2 ; CHECK-NEXT: [[CONV6:%.*]] = sitofp i32 [[MUL5]] to float ; CHECK-NEXT: [[TMP1:%.*]] = load <8 x float>, ptr @arr, align 16 ; CHECK-NEXT: [[TMP2:%.*]] = load <8 x float>, ptr @arr1, align 16 ; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <8 x float> [[TMP2]], [[TMP1]] ; CHECK-NEXT: [[TMP4:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP3]]) ; CHECK-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP4]], [[CONV]] ; CHECK-NEXT: [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], [[CONV6]] ; CHECK-NEXT: store float [[OP_RDX1]], ptr @res, align 4 ; CHECK-NEXT: ret float [[OP_RDX1]] ; ; THRESHOLD-LABEL: @bazz( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[TMP0:%.*]] = load i32, ptr @n, align 4 ; THRESHOLD-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP0]], 3 ; THRESHOLD-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; THRESHOLD-NEXT: [[MUL5:%.*]] = shl nsw i32 [[TMP0]], 2 ; THRESHOLD-NEXT: [[CONV6:%.*]] = sitofp i32 [[MUL5]] to float ; THRESHOLD-NEXT: [[TMP1:%.*]] = load <8 x float>, ptr @arr, align 16 ; THRESHOLD-NEXT: [[TMP2:%.*]] = load <8 x float>, ptr @arr1, align 16 ; THRESHOLD-NEXT: [[TMP3:%.*]] = fmul fast <8 x float> [[TMP2]], [[TMP1]] ; THRESHOLD-NEXT: [[TMP4:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP3]]) ; THRESHOLD-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP4]], [[CONV]] ; THRESHOLD-NEXT: [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], [[CONV6]] ; THRESHOLD-NEXT: store float [[OP_RDX1]], ptr @res, align 4 ; THRESHOLD-NEXT: ret float [[OP_RDX1]] ; entry: %0 = load i32, ptr @n, align 4 %mul = mul nsw i32 %0, 3 %conv = sitofp i32 %mul to float %1 = load float, ptr @arr, align 16 %2 = load float, ptr @arr1, align 16 %mul4 = fmul fast float %2, %1 %add = fadd fast float %mul4, %conv %3 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 1), align 4 %4 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 1), align 4 %mul4.1 = fmul fast float %4, %3 %add.1 = fadd fast float %mul4.1, %add %5 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 2), align 8 %6 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 2), align 8 %mul4.2 = fmul fast float %6, %5 %add.2 = fadd fast float %mul4.2, %add.1 %7 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 3), align 4 %8 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 3), align 4 %mul4.3 = fmul fast float %8, %7 %add.3 = fadd fast float %mul4.3, %add.2 %mul5 = shl nsw i32 %0, 2 %conv6 = sitofp i32 %mul5 to float %add7 = fadd fast float %add.3, %conv6 %9 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 4), align 16 %10 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 4), align 16 %mul18 = fmul fast float %10, %9 %add19 = fadd fast float %mul18, %add7 %11 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 5), align 4 %12 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 5), align 4 %mul18.1 = fmul fast float %12, %11 %add19.1 = fadd fast float %mul18.1, %add19 %13 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 6), align 8 %14 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 6), align 8 %mul18.2 = fmul fast float %14, %13 %add19.2 = fadd fast float %mul18.2, %add19.1 %15 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 7), align 4 %16 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 7), align 4 %mul18.3 = fmul fast float %16, %15 %add19.3 = fadd fast float %mul18.3, %add19.2 store float %add19.3, ptr @res, align 4 ret float %add19.3 } define float @bazzz() { ; CHECK-LABEL: @bazzz( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr @n, align 4 ; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr @arr, align 16 ; CHECK-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr @arr1, align 16 ; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <4 x float> [[TMP2]], [[TMP1]] ; CHECK-NEXT: [[TMP4:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> [[TMP3]]) ; CHECK-NEXT: [[TMP5:%.*]] = fmul fast float [[CONV]], [[TMP4]] ; CHECK-NEXT: store float [[TMP5]], ptr @res, align 4 ; CHECK-NEXT: ret float [[TMP5]] ; ; THRESHOLD-LABEL: @bazzz( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[TMP0:%.*]] = load i32, ptr @n, align 4 ; THRESHOLD-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float ; THRESHOLD-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr @arr, align 16 ; THRESHOLD-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr @arr1, align 16 ; THRESHOLD-NEXT: [[TMP3:%.*]] = fmul fast <4 x float> [[TMP2]], [[TMP1]] ; THRESHOLD-NEXT: [[TMP4:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> [[TMP3]]) ; THRESHOLD-NEXT: [[TMP5:%.*]] = fmul fast float [[CONV]], [[TMP4]] ; THRESHOLD-NEXT: store float [[TMP5]], ptr @res, align 4 ; THRESHOLD-NEXT: ret float [[TMP5]] ; entry: %0 = load i32, ptr @n, align 4 %conv = sitofp i32 %0 to float %1 = load float, ptr @arr, align 16 %2 = load float, ptr @arr1, align 16 %mul = fmul fast float %2, %1 %3 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 1), align 4 %4 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 1), align 4 %mul.1 = fmul fast float %4, %3 %5 = fadd fast float %mul.1, %mul %6 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 2), align 8 %7 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 2), align 8 %mul.2 = fmul fast float %7, %6 %8 = fadd fast float %mul.2, %5 %9 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 3), align 4 %10 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 3), align 4 %mul.3 = fmul fast float %10, %9 %11 = fadd fast float %mul.3, %8 %12 = fmul fast float %conv, %11 store float %12, ptr @res, align 4 ret float %12 } define i32 @foo() { ; CHECK-LABEL: @foo( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr @n, align 4 ; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr @arr, align 16 ; CHECK-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr @arr1, align 16 ; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <4 x float> [[TMP2]], [[TMP1]] ; CHECK-NEXT: [[TMP4:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> [[TMP3]]) ; CHECK-NEXT: [[TMP5:%.*]] = fmul fast float [[CONV]], [[TMP4]] ; CHECK-NEXT: [[CONV4:%.*]] = fptosi float [[TMP5]] to i32 ; CHECK-NEXT: store i32 [[CONV4]], ptr @n, align 4 ; CHECK-NEXT: ret i32 [[CONV4]] ; ; THRESHOLD-LABEL: @foo( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[TMP0:%.*]] = load i32, ptr @n, align 4 ; THRESHOLD-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float ; THRESHOLD-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr @arr, align 16 ; THRESHOLD-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr @arr1, align 16 ; THRESHOLD-NEXT: [[TMP3:%.*]] = fmul fast <4 x float> [[TMP2]], [[TMP1]] ; THRESHOLD-NEXT: [[TMP4:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> [[TMP3]]) ; THRESHOLD-NEXT: [[TMP5:%.*]] = fmul fast float [[CONV]], [[TMP4]] ; THRESHOLD-NEXT: [[CONV4:%.*]] = fptosi float [[TMP5]] to i32 ; THRESHOLD-NEXT: store i32 [[CONV4]], ptr @n, align 4 ; THRESHOLD-NEXT: ret i32 [[CONV4]] ; entry: %0 = load i32, ptr @n, align 4 %conv = sitofp i32 %0 to float %1 = load float, ptr @arr, align 16 %2 = load float, ptr @arr1, align 16 %mul = fmul fast float %2, %1 %3 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 1), align 4 %4 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 1), align 4 %mul.1 = fmul fast float %4, %3 %5 = fadd fast float %mul.1, %mul %6 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 2), align 8 %7 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 2), align 8 %mul.2 = fmul fast float %7, %6 %8 = fadd fast float %mul.2, %5 %9 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 3), align 4 %10 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 3), align 4 %mul.3 = fmul fast float %10, %9 %11 = fadd fast float %mul.3, %8 %12 = fmul fast float %conv, %11 %conv4 = fptosi float %12 to i32 store i32 %conv4, ptr @n, align 4 ret i32 %conv4 } ; FIXME: Use fmaxnum intrinsics to match what InstCombine creates for fcmp+select ; with fastmath on the select. define float @bar() { ; CHECK-LABEL: @bar( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = load <2 x float>, ptr @arr, align 16 ; CHECK-NEXT: [[TMP1:%.*]] = load <2 x float>, ptr @arr1, align 16 ; CHECK-NEXT: [[TMP2:%.*]] = fmul fast <2 x float> [[TMP1]], [[TMP0]] ; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0 ; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 1 ; CHECK-NEXT: [[CMP4:%.*]] = fcmp fast ogt float [[TMP3]], [[TMP4]] ; CHECK-NEXT: [[MAX_0_MUL3:%.*]] = select i1 [[CMP4]], float [[TMP3]], float [[TMP4]] ; CHECK-NEXT: [[TMP5:%.*]] = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 2), align 8 ; CHECK-NEXT: [[TMP6:%.*]] = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 2), align 8 ; CHECK-NEXT: [[MUL3_1:%.*]] = fmul fast float [[TMP6]], [[TMP5]] ; CHECK-NEXT: [[CMP4_1:%.*]] = fcmp fast ogt float [[MAX_0_MUL3]], [[MUL3_1]] ; CHECK-NEXT: [[MAX_0_MUL3_1:%.*]] = select i1 [[CMP4_1]], float [[MAX_0_MUL3]], float [[MUL3_1]] ; CHECK-NEXT: [[TMP7:%.*]] = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 3), align 4 ; CHECK-NEXT: [[TMP8:%.*]] = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 3), align 4 ; CHECK-NEXT: [[MUL3_2:%.*]] = fmul fast float [[TMP8]], [[TMP7]] ; CHECK-NEXT: [[CMP4_2:%.*]] = fcmp fast ogt float [[MAX_0_MUL3_1]], [[MUL3_2]] ; CHECK-NEXT: [[MAX_0_MUL3_2:%.*]] = select i1 [[CMP4_2]], float [[MAX_0_MUL3_1]], float [[MUL3_2]] ; CHECK-NEXT: store float [[MAX_0_MUL3_2]], ptr @res, align 4 ; CHECK-NEXT: ret float [[MAX_0_MUL3_2]] ; ; THRESHOLD-LABEL: @bar( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[TMP0:%.*]] = load <2 x float>, ptr @arr, align 16 ; THRESHOLD-NEXT: [[TMP1:%.*]] = load <2 x float>, ptr @arr1, align 16 ; THRESHOLD-NEXT: [[TMP2:%.*]] = fmul fast <2 x float> [[TMP1]], [[TMP0]] ; THRESHOLD-NEXT: [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0 ; THRESHOLD-NEXT: [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 1 ; THRESHOLD-NEXT: [[CMP4:%.*]] = fcmp fast ogt float [[TMP3]], [[TMP4]] ; THRESHOLD-NEXT: [[MAX_0_MUL3:%.*]] = select i1 [[CMP4]], float [[TMP3]], float [[TMP4]] ; THRESHOLD-NEXT: [[TMP5:%.*]] = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 2), align 8 ; THRESHOLD-NEXT: [[TMP6:%.*]] = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 2), align 8 ; THRESHOLD-NEXT: [[MUL3_1:%.*]] = fmul fast float [[TMP6]], [[TMP5]] ; THRESHOLD-NEXT: [[CMP4_1:%.*]] = fcmp fast ogt float [[MAX_0_MUL3]], [[MUL3_1]] ; THRESHOLD-NEXT: [[MAX_0_MUL3_1:%.*]] = select i1 [[CMP4_1]], float [[MAX_0_MUL3]], float [[MUL3_1]] ; THRESHOLD-NEXT: [[TMP7:%.*]] = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 3), align 4 ; THRESHOLD-NEXT: [[TMP8:%.*]] = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 3), align 4 ; THRESHOLD-NEXT: [[MUL3_2:%.*]] = fmul fast float [[TMP8]], [[TMP7]] ; THRESHOLD-NEXT: [[CMP4_2:%.*]] = fcmp fast ogt float [[MAX_0_MUL3_1]], [[MUL3_2]] ; THRESHOLD-NEXT: [[MAX_0_MUL3_2:%.*]] = select i1 [[CMP4_2]], float [[MAX_0_MUL3_1]], float [[MUL3_2]] ; THRESHOLD-NEXT: store float [[MAX_0_MUL3_2]], ptr @res, align 4 ; THRESHOLD-NEXT: ret float [[MAX_0_MUL3_2]] ; entry: %0 = load float, ptr @arr, align 16 %1 = load float, ptr @arr1, align 16 %mul = fmul fast float %1, %0 %2 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 1), align 4 %3 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 1), align 4 %mul3 = fmul fast float %3, %2 %cmp4 = fcmp fast ogt float %mul, %mul3 %max.0.mul3 = select i1 %cmp4, float %mul, float %mul3 %4 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 2), align 8 %5 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 2), align 8 %mul3.1 = fmul fast float %5, %4 %cmp4.1 = fcmp fast ogt float %max.0.mul3, %mul3.1 %max.0.mul3.1 = select i1 %cmp4.1, float %max.0.mul3, float %mul3.1 %6 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr, i64 0, i64 3), align 4 %7 = load float, ptr getelementptr inbounds ([20 x float], ptr @arr1, i64 0, i64 3), align 4 %mul3.2 = fmul fast float %7, %6 %cmp4.2 = fcmp fast ogt float %max.0.mul3.1, %mul3.2 %max.0.mul3.2 = select i1 %cmp4.2, float %max.0.mul3.1, float %mul3.2 store float %max.0.mul3.2, ptr @res, align 4 ret float %max.0.mul3.2 } define float @f(ptr nocapture readonly %x) { ; CHECK-LABEL: @f( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = load <48 x float>, ptr [[X:%.*]], align 4 ; CHECK-NEXT: [[OP_RDX:%.*]] = call fast float @llvm.vector.reduce.fadd.v48f32(float 0.000000e+00, <48 x float> [[TMP0]]) ; CHECK-NEXT: ret float [[OP_RDX]] ; ; THRESHOLD-LABEL: @f( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[TMP0:%.*]] = load <48 x float>, ptr [[X:%.*]], align 4 ; THRESHOLD-NEXT: [[OP_RDX:%.*]] = call fast float @llvm.vector.reduce.fadd.v48f32(float 0.000000e+00, <48 x float> [[TMP0]]) ; THRESHOLD-NEXT: ret float [[OP_RDX]] ; entry: %0 = load float, ptr %x, align 4 %arrayidx.1 = getelementptr inbounds float, ptr %x, i64 1 %1 = load float, ptr %arrayidx.1, align 4 %add.1 = fadd fast float %1, %0 %arrayidx.2 = getelementptr inbounds float, ptr %x, i64 2 %2 = load float, ptr %arrayidx.2, align 4 %add.2 = fadd fast float %2, %add.1 %arrayidx.3 = getelementptr inbounds float, ptr %x, i64 3 %3 = load float, ptr %arrayidx.3, align 4 %add.3 = fadd fast float %3, %add.2 %arrayidx.4 = getelementptr inbounds float, ptr %x, i64 4 %4 = load float, ptr %arrayidx.4, align 4 %add.4 = fadd fast float %4, %add.3 %arrayidx.5 = getelementptr inbounds float, ptr %x, i64 5 %5 = load float, ptr %arrayidx.5, align 4 %add.5 = fadd fast float %5, %add.4 %arrayidx.6 = getelementptr inbounds float, ptr %x, i64 6 %6 = load float, ptr %arrayidx.6, align 4 %add.6 = fadd fast float %6, %add.5 %arrayidx.7 = getelementptr inbounds float, ptr %x, i64 7 %7 = load float, ptr %arrayidx.7, align 4 %add.7 = fadd fast float %7, %add.6 %arrayidx.8 = getelementptr inbounds float, ptr %x, i64 8 %8 = load float, ptr %arrayidx.8, align 4 %add.8 = fadd fast float %8, %add.7 %arrayidx.9 = getelementptr inbounds float, ptr %x, i64 9 %9 = load float, ptr %arrayidx.9, align 4 %add.9 = fadd fast float %9, %add.8 %arrayidx.10 = getelementptr inbounds float, ptr %x, i64 10 %10 = load float, ptr %arrayidx.10, align 4 %add.10 = fadd fast float %10, %add.9 %arrayidx.11 = getelementptr inbounds float, ptr %x, i64 11 %11 = load float, ptr %arrayidx.11, align 4 %add.11 = fadd fast float %11, %add.10 %arrayidx.12 = getelementptr inbounds float, ptr %x, i64 12 %12 = load float, ptr %arrayidx.12, align 4 %add.12 = fadd fast float %12, %add.11 %arrayidx.13 = getelementptr inbounds float, ptr %x, i64 13 %13 = load float, ptr %arrayidx.13, align 4 %add.13 = fadd fast float %13, %add.12 %arrayidx.14 = getelementptr inbounds float, ptr %x, i64 14 %14 = load float, ptr %arrayidx.14, align 4 %add.14 = fadd fast float %14, %add.13 %arrayidx.15 = getelementptr inbounds float, ptr %x, i64 15 %15 = load float, ptr %arrayidx.15, align 4 %add.15 = fadd fast float %15, %add.14 %arrayidx.16 = getelementptr inbounds float, ptr %x, i64 16 %16 = load float, ptr %arrayidx.16, align 4 %add.16 = fadd fast float %16, %add.15 %arrayidx.17 = getelementptr inbounds float, ptr %x, i64 17 %17 = load float, ptr %arrayidx.17, align 4 %add.17 = fadd fast float %17, %add.16 %arrayidx.18 = getelementptr inbounds float, ptr %x, i64 18 %18 = load float, ptr %arrayidx.18, align 4 %add.18 = fadd fast float %18, %add.17 %arrayidx.19 = getelementptr inbounds float, ptr %x, i64 19 %19 = load float, ptr %arrayidx.19, align 4 %add.19 = fadd fast float %19, %add.18 %arrayidx.20 = getelementptr inbounds float, ptr %x, i64 20 %20 = load float, ptr %arrayidx.20, align 4 %add.20 = fadd fast float %20, %add.19 %arrayidx.21 = getelementptr inbounds float, ptr %x, i64 21 %21 = load float, ptr %arrayidx.21, align 4 %add.21 = fadd fast float %21, %add.20 %arrayidx.22 = getelementptr inbounds float, ptr %x, i64 22 %22 = load float, ptr %arrayidx.22, align 4 %add.22 = fadd fast float %22, %add.21 %arrayidx.23 = getelementptr inbounds float, ptr %x, i64 23 %23 = load float, ptr %arrayidx.23, align 4 %add.23 = fadd fast float %23, %add.22 %arrayidx.24 = getelementptr inbounds float, ptr %x, i64 24 %24 = load float, ptr %arrayidx.24, align 4 %add.24 = fadd fast float %24, %add.23 %arrayidx.25 = getelementptr inbounds float, ptr %x, i64 25 %25 = load float, ptr %arrayidx.25, align 4 %add.25 = fadd fast float %25, %add.24 %arrayidx.26 = getelementptr inbounds float, ptr %x, i64 26 %26 = load float, ptr %arrayidx.26, align 4 %add.26 = fadd fast float %26, %add.25 %arrayidx.27 = getelementptr inbounds float, ptr %x, i64 27 %27 = load float, ptr %arrayidx.27, align 4 %add.27 = fadd fast float %27, %add.26 %arrayidx.28 = getelementptr inbounds float, ptr %x, i64 28 %28 = load float, ptr %arrayidx.28, align 4 %add.28 = fadd fast float %28, %add.27 %arrayidx.29 = getelementptr inbounds float, ptr %x, i64 29 %29 = load float, ptr %arrayidx.29, align 4 %add.29 = fadd fast float %29, %add.28 %arrayidx.30 = getelementptr inbounds float, ptr %x, i64 30 %30 = load float, ptr %arrayidx.30, align 4 %add.30 = fadd fast float %30, %add.29 %arrayidx.31 = getelementptr inbounds float, ptr %x, i64 31 %31 = load float, ptr %arrayidx.31, align 4 %add.31 = fadd fast float %31, %add.30 %arrayidx.32 = getelementptr inbounds float, ptr %x, i64 32 %32 = load float, ptr %arrayidx.32, align 4 %add.32 = fadd fast float %32, %add.31 %arrayidx.33 = getelementptr inbounds float, ptr %x, i64 33 %33 = load float, ptr %arrayidx.33, align 4 %add.33 = fadd fast float %33, %add.32 %arrayidx.34 = getelementptr inbounds float, ptr %x, i64 34 %34 = load float, ptr %arrayidx.34, align 4 %add.34 = fadd fast float %34, %add.33 %arrayidx.35 = getelementptr inbounds float, ptr %x, i64 35 %35 = load float, ptr %arrayidx.35, align 4 %add.35 = fadd fast float %35, %add.34 %arrayidx.36 = getelementptr inbounds float, ptr %x, i64 36 %36 = load float, ptr %arrayidx.36, align 4 %add.36 = fadd fast float %36, %add.35 %arrayidx.37 = getelementptr inbounds float, ptr %x, i64 37 %37 = load float, ptr %arrayidx.37, align 4 %add.37 = fadd fast float %37, %add.36 %arrayidx.38 = getelementptr inbounds float, ptr %x, i64 38 %38 = load float, ptr %arrayidx.38, align 4 %add.38 = fadd fast float %38, %add.37 %arrayidx.39 = getelementptr inbounds float, ptr %x, i64 39 %39 = load float, ptr %arrayidx.39, align 4 %add.39 = fadd fast float %39, %add.38 %arrayidx.40 = getelementptr inbounds float, ptr %x, i64 40 %40 = load float, ptr %arrayidx.40, align 4 %add.40 = fadd fast float %40, %add.39 %arrayidx.41 = getelementptr inbounds float, ptr %x, i64 41 %41 = load float, ptr %arrayidx.41, align 4 %add.41 = fadd fast float %41, %add.40 %arrayidx.42 = getelementptr inbounds float, ptr %x, i64 42 %42 = load float, ptr %arrayidx.42, align 4 %add.42 = fadd fast float %42, %add.41 %arrayidx.43 = getelementptr inbounds float, ptr %x, i64 43 %43 = load float, ptr %arrayidx.43, align 4 %add.43 = fadd fast float %43, %add.42 %arrayidx.44 = getelementptr inbounds float, ptr %x, i64 44 %44 = load float, ptr %arrayidx.44, align 4 %add.44 = fadd fast float %44, %add.43 %arrayidx.45 = getelementptr inbounds float, ptr %x, i64 45 %45 = load float, ptr %arrayidx.45, align 4 %add.45 = fadd fast float %45, %add.44 %arrayidx.46 = getelementptr inbounds float, ptr %x, i64 46 %46 = load float, ptr %arrayidx.46, align 4 %add.46 = fadd fast float %46, %add.45 %arrayidx.47 = getelementptr inbounds float, ptr %x, i64 47 %47 = load float, ptr %arrayidx.47, align 4 %add.47 = fadd fast float %47, %add.46 ret float %add.47 } define float @f1(ptr nocapture readonly %x, i32 %a, i32 %b) { ; CHECK-LABEL: @f1( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[REM:%.*]] = srem i32 [[A:%.*]], [[B:%.*]] ; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[REM]] to float ; CHECK-NEXT: [[TMP0:%.*]] = load <32 x float>, ptr [[X:%.*]], align 4 ; CHECK-NEXT: [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v32f32(float 0.000000e+00, <32 x float> [[TMP0]]) ; CHECK-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP1]], [[CONV]] ; CHECK-NEXT: ret float [[OP_RDX]] ; ; THRESHOLD-LABEL: @f1( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[REM:%.*]] = srem i32 [[A:%.*]], [[B:%.*]] ; THRESHOLD-NEXT: [[CONV:%.*]] = sitofp i32 [[REM]] to float ; THRESHOLD-NEXT: [[TMP0:%.*]] = load <32 x float>, ptr [[X:%.*]], align 4 ; THRESHOLD-NEXT: [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v32f32(float 0.000000e+00, <32 x float> [[TMP0]]) ; THRESHOLD-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP1]], [[CONV]] ; THRESHOLD-NEXT: ret float [[OP_RDX]] ; entry: %rem = srem i32 %a, %b %conv = sitofp i32 %rem to float %0 = load float, ptr %x, align 4 %add = fadd fast float %0, %conv %arrayidx.1 = getelementptr inbounds float, ptr %x, i64 1 %1 = load float, ptr %arrayidx.1, align 4 %add.1 = fadd fast float %1, %add %arrayidx.2 = getelementptr inbounds float, ptr %x, i64 2 %2 = load float, ptr %arrayidx.2, align 4 %add.2 = fadd fast float %2, %add.1 %arrayidx.3 = getelementptr inbounds float, ptr %x, i64 3 %3 = load float, ptr %arrayidx.3, align 4 %add.3 = fadd fast float %3, %add.2 %arrayidx.4 = getelementptr inbounds float, ptr %x, i64 4 %4 = load float, ptr %arrayidx.4, align 4 %add.4 = fadd fast float %4, %add.3 %arrayidx.5 = getelementptr inbounds float, ptr %x, i64 5 %5 = load float, ptr %arrayidx.5, align 4 %add.5 = fadd fast float %5, %add.4 %arrayidx.6 = getelementptr inbounds float, ptr %x, i64 6 %6 = load float, ptr %arrayidx.6, align 4 %add.6 = fadd fast float %6, %add.5 %arrayidx.7 = getelementptr inbounds float, ptr %x, i64 7 %7 = load float, ptr %arrayidx.7, align 4 %add.7 = fadd fast float %7, %add.6 %arrayidx.8 = getelementptr inbounds float, ptr %x, i64 8 %8 = load float, ptr %arrayidx.8, align 4 %add.8 = fadd fast float %8, %add.7 %arrayidx.9 = getelementptr inbounds float, ptr %x, i64 9 %9 = load float, ptr %arrayidx.9, align 4 %add.9 = fadd fast float %9, %add.8 %arrayidx.10 = getelementptr inbounds float, ptr %x, i64 10 %10 = load float, ptr %arrayidx.10, align 4 %add.10 = fadd fast float %10, %add.9 %arrayidx.11 = getelementptr inbounds float, ptr %x, i64 11 %11 = load float, ptr %arrayidx.11, align 4 %add.11 = fadd fast float %11, %add.10 %arrayidx.12 = getelementptr inbounds float, ptr %x, i64 12 %12 = load float, ptr %arrayidx.12, align 4 %add.12 = fadd fast float %12, %add.11 %arrayidx.13 = getelementptr inbounds float, ptr %x, i64 13 %13 = load float, ptr %arrayidx.13, align 4 %add.13 = fadd fast float %13, %add.12 %arrayidx.14 = getelementptr inbounds float, ptr %x, i64 14 %14 = load float, ptr %arrayidx.14, align 4 %add.14 = fadd fast float %14, %add.13 %arrayidx.15 = getelementptr inbounds float, ptr %x, i64 15 %15 = load float, ptr %arrayidx.15, align 4 %add.15 = fadd fast float %15, %add.14 %arrayidx.16 = getelementptr inbounds float, ptr %x, i64 16 %16 = load float, ptr %arrayidx.16, align 4 %add.16 = fadd fast float %16, %add.15 %arrayidx.17 = getelementptr inbounds float, ptr %x, i64 17 %17 = load float, ptr %arrayidx.17, align 4 %add.17 = fadd fast float %17, %add.16 %arrayidx.18 = getelementptr inbounds float, ptr %x, i64 18 %18 = load float, ptr %arrayidx.18, align 4 %add.18 = fadd fast float %18, %add.17 %arrayidx.19 = getelementptr inbounds float, ptr %x, i64 19 %19 = load float, ptr %arrayidx.19, align 4 %add.19 = fadd fast float %19, %add.18 %arrayidx.20 = getelementptr inbounds float, ptr %x, i64 20 %20 = load float, ptr %arrayidx.20, align 4 %add.20 = fadd fast float %20, %add.19 %arrayidx.21 = getelementptr inbounds float, ptr %x, i64 21 %21 = load float, ptr %arrayidx.21, align 4 %add.21 = fadd fast float %21, %add.20 %arrayidx.22 = getelementptr inbounds float, ptr %x, i64 22 %22 = load float, ptr %arrayidx.22, align 4 %add.22 = fadd fast float %22, %add.21 %arrayidx.23 = getelementptr inbounds float, ptr %x, i64 23 %23 = load float, ptr %arrayidx.23, align 4 %add.23 = fadd fast float %23, %add.22 %arrayidx.24 = getelementptr inbounds float, ptr %x, i64 24 %24 = load float, ptr %arrayidx.24, align 4 %add.24 = fadd fast float %24, %add.23 %arrayidx.25 = getelementptr inbounds float, ptr %x, i64 25 %25 = load float, ptr %arrayidx.25, align 4 %add.25 = fadd fast float %25, %add.24 %arrayidx.26 = getelementptr inbounds float, ptr %x, i64 26 %26 = load float, ptr %arrayidx.26, align 4 %add.26 = fadd fast float %26, %add.25 %arrayidx.27 = getelementptr inbounds float, ptr %x, i64 27 %27 = load float, ptr %arrayidx.27, align 4 %add.27 = fadd fast float %27, %add.26 %arrayidx.28 = getelementptr inbounds float, ptr %x, i64 28 %28 = load float, ptr %arrayidx.28, align 4 %add.28 = fadd fast float %28, %add.27 %arrayidx.29 = getelementptr inbounds float, ptr %x, i64 29 %29 = load float, ptr %arrayidx.29, align 4 %add.29 = fadd fast float %29, %add.28 %arrayidx.30 = getelementptr inbounds float, ptr %x, i64 30 %30 = load float, ptr %arrayidx.30, align 4 %add.30 = fadd fast float %30, %add.29 %arrayidx.31 = getelementptr inbounds float, ptr %x, i64 31 %31 = load float, ptr %arrayidx.31, align 4 %add.31 = fadd fast float %31, %add.30 ret float %add.31 } define float @loadadd31(ptr nocapture readonly %x) { ; CHECK-LABEL: @loadadd31( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[X:%.*]], i64 1 ; CHECK-NEXT: [[TMP0:%.*]] = load <24 x float>, ptr [[ARRAYIDX]], align 4 ; CHECK-NEXT: [[ARRAYIDX_24:%.*]] = getelementptr inbounds float, ptr [[X]], i64 25 ; CHECK-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr [[ARRAYIDX_24]], align 4 ; CHECK-NEXT: [[ARRAYIDX_28:%.*]] = getelementptr inbounds float, ptr [[X]], i64 29 ; CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[ARRAYIDX_28]], align 4 ; CHECK-NEXT: [[ARRAYIDX_29:%.*]] = getelementptr inbounds float, ptr [[X]], i64 30 ; CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[ARRAYIDX_29]], align 4 ; CHECK-NEXT: [[RDX_OP2:%.*]] = shufflevector <24 x float> [[TMP0]], <24 x float> poison, <4 x i32> ; CHECK-NEXT: [[RDX_OP3:%.*]] = fadd fast <4 x float> [[RDX_OP2]], [[TMP2]] ; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x float> [[RDX_OP3]], <4 x float> poison, <24 x i32> ; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <24 x float> [[TMP0]], <24 x float> [[TMP6]], <24 x i32> ; CHECK-NEXT: [[OP_RDX1:%.*]] = call fast float @llvm.vector.reduce.fadd.v24f32(float 0.000000e+00, <24 x float> [[TMP5]]) ; CHECK-NEXT: [[OP_RDX2:%.*]] = fadd fast float [[OP_RDX1]], [[TMP3]] ; CHECK-NEXT: [[OP_RDX3:%.*]] = fadd fast float [[OP_RDX2]], [[TMP4]] ; CHECK-NEXT: ret float [[OP_RDX3]] ; ; THRESHOLD-LABEL: @loadadd31( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[X:%.*]], i64 1 ; THRESHOLD-NEXT: [[TMP0:%.*]] = load <24 x float>, ptr [[ARRAYIDX]], align 4 ; THRESHOLD-NEXT: [[ARRAYIDX_24:%.*]] = getelementptr inbounds float, ptr [[X]], i64 25 ; THRESHOLD-NEXT: [[TMP2:%.*]] = load <4 x float>, ptr [[ARRAYIDX_24]], align 4 ; THRESHOLD-NEXT: [[ARRAYIDX_28:%.*]] = getelementptr inbounds float, ptr [[X]], i64 29 ; THRESHOLD-NEXT: [[TMP3:%.*]] = load float, ptr [[ARRAYIDX_28]], align 4 ; THRESHOLD-NEXT: [[ARRAYIDX_29:%.*]] = getelementptr inbounds float, ptr [[X]], i64 30 ; THRESHOLD-NEXT: [[TMP4:%.*]] = load float, ptr [[ARRAYIDX_29]], align 4 ; THRESHOLD-NEXT: [[RDX_OP2:%.*]] = shufflevector <24 x float> [[TMP0]], <24 x float> poison, <4 x i32> ; THRESHOLD-NEXT: [[RDX_OP3:%.*]] = fadd fast <4 x float> [[RDX_OP2]], [[TMP2]] ; THRESHOLD-NEXT: [[TMP6:%.*]] = shufflevector <4 x float> [[RDX_OP3]], <4 x float> poison, <24 x i32> ; THRESHOLD-NEXT: [[TMP5:%.*]] = shufflevector <24 x float> [[TMP0]], <24 x float> [[TMP6]], <24 x i32> ; THRESHOLD-NEXT: [[OP_RDX1:%.*]] = call fast float @llvm.vector.reduce.fadd.v24f32(float 0.000000e+00, <24 x float> [[TMP5]]) ; THRESHOLD-NEXT: [[OP_RDX2:%.*]] = fadd fast float [[OP_RDX1]], [[TMP3]] ; THRESHOLD-NEXT: [[OP_RDX3:%.*]] = fadd fast float [[OP_RDX2]], [[TMP4]] ; THRESHOLD-NEXT: ret float [[OP_RDX3]] ; entry: %arrayidx = getelementptr inbounds float, ptr %x, i64 1 %0 = load float, ptr %arrayidx, align 4 %arrayidx.1 = getelementptr inbounds float, ptr %x, i64 2 %1 = load float, ptr %arrayidx.1, align 4 %add.1 = fadd fast float %1, %0 %arrayidx.2 = getelementptr inbounds float, ptr %x, i64 3 %2 = load float, ptr %arrayidx.2, align 4 %add.2 = fadd fast float %2, %add.1 %arrayidx.3 = getelementptr inbounds float, ptr %x, i64 4 %3 = load float, ptr %arrayidx.3, align 4 %add.3 = fadd fast float %3, %add.2 %arrayidx.4 = getelementptr inbounds float, ptr %x, i64 5 %4 = load float, ptr %arrayidx.4, align 4 %add.4 = fadd fast float %4, %add.3 %arrayidx.5 = getelementptr inbounds float, ptr %x, i64 6 %5 = load float, ptr %arrayidx.5, align 4 %add.5 = fadd fast float %5, %add.4 %arrayidx.6 = getelementptr inbounds float, ptr %x, i64 7 %6 = load float, ptr %arrayidx.6, align 4 %add.6 = fadd fast float %6, %add.5 %arrayidx.7 = getelementptr inbounds float, ptr %x, i64 8 %7 = load float, ptr %arrayidx.7, align 4 %add.7 = fadd fast float %7, %add.6 %arrayidx.8 = getelementptr inbounds float, ptr %x, i64 9 %8 = load float, ptr %arrayidx.8, align 4 %add.8 = fadd fast float %8, %add.7 %arrayidx.9 = getelementptr inbounds float, ptr %x, i64 10 %9 = load float, ptr %arrayidx.9, align 4 %add.9 = fadd fast float %9, %add.8 %arrayidx.10 = getelementptr inbounds float, ptr %x, i64 11 %10 = load float, ptr %arrayidx.10, align 4 %add.10 = fadd fast float %10, %add.9 %arrayidx.11 = getelementptr inbounds float, ptr %x, i64 12 %11 = load float, ptr %arrayidx.11, align 4 %add.11 = fadd fast float %11, %add.10 %arrayidx.12 = getelementptr inbounds float, ptr %x, i64 13 %12 = load float, ptr %arrayidx.12, align 4 %add.12 = fadd fast float %12, %add.11 %arrayidx.13 = getelementptr inbounds float, ptr %x, i64 14 %13 = load float, ptr %arrayidx.13, align 4 %add.13 = fadd fast float %13, %add.12 %arrayidx.14 = getelementptr inbounds float, ptr %x, i64 15 %14 = load float, ptr %arrayidx.14, align 4 %add.14 = fadd fast float %14, %add.13 %arrayidx.15 = getelementptr inbounds float, ptr %x, i64 16 %15 = load float, ptr %arrayidx.15, align 4 %add.15 = fadd fast float %15, %add.14 %arrayidx.16 = getelementptr inbounds float, ptr %x, i64 17 %16 = load float, ptr %arrayidx.16, align 4 %add.16 = fadd fast float %16, %add.15 %arrayidx.17 = getelementptr inbounds float, ptr %x, i64 18 %17 = load float, ptr %arrayidx.17, align 4 %add.17 = fadd fast float %17, %add.16 %arrayidx.18 = getelementptr inbounds float, ptr %x, i64 19 %18 = load float, ptr %arrayidx.18, align 4 %add.18 = fadd fast float %18, %add.17 %arrayidx.19 = getelementptr inbounds float, ptr %x, i64 20 %19 = load float, ptr %arrayidx.19, align 4 %add.19 = fadd fast float %19, %add.18 %arrayidx.20 = getelementptr inbounds float, ptr %x, i64 21 %20 = load float, ptr %arrayidx.20, align 4 %add.20 = fadd fast float %20, %add.19 %arrayidx.21 = getelementptr inbounds float, ptr %x, i64 22 %21 = load float, ptr %arrayidx.21, align 4 %add.21 = fadd fast float %21, %add.20 %arrayidx.22 = getelementptr inbounds float, ptr %x, i64 23 %22 = load float, ptr %arrayidx.22, align 4 %add.22 = fadd fast float %22, %add.21 %arrayidx.23 = getelementptr inbounds float, ptr %x, i64 24 %23 = load float, ptr %arrayidx.23, align 4 %add.23 = fadd fast float %23, %add.22 %arrayidx.24 = getelementptr inbounds float, ptr %x, i64 25 %24 = load float, ptr %arrayidx.24, align 4 %add.24 = fadd fast float %24, %add.23 %arrayidx.25 = getelementptr inbounds float, ptr %x, i64 26 %25 = load float, ptr %arrayidx.25, align 4 %add.25 = fadd fast float %25, %add.24 %arrayidx.26 = getelementptr inbounds float, ptr %x, i64 27 %26 = load float, ptr %arrayidx.26, align 4 %add.26 = fadd fast float %26, %add.25 %arrayidx.27 = getelementptr inbounds float, ptr %x, i64 28 %27 = load float, ptr %arrayidx.27, align 4 %add.27 = fadd fast float %27, %add.26 %arrayidx.28 = getelementptr inbounds float, ptr %x, i64 29 %28 = load float, ptr %arrayidx.28, align 4 %add.28 = fadd fast float %28, %add.27 %arrayidx.29 = getelementptr inbounds float, ptr %x, i64 30 %29 = load float, ptr %arrayidx.29, align 4 %add.29 = fadd fast float %29, %add.28 ret float %add.29 } define float @extra_args(ptr nocapture readonly %x, i32 %a, i32 %b) { ; CHECK-LABEL: @extra_args( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[B:%.*]], [[A:%.*]] ; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; CHECK-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[X:%.*]], align 4 ; CHECK-NEXT: [[TMP2:%.*]] = fmul fast float [[CONV]], 2.000000e+00 ; CHECK-NEXT: [[TMP3:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP0]]) ; CHECK-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP2]], [[TMP3]] ; CHECK-NEXT: [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], 3.000000e+00 ; CHECK-NEXT: ret float [[OP_RDX1]] ; ; THRESHOLD-LABEL: @extra_args( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[MUL:%.*]] = mul nsw i32 [[B:%.*]], [[A:%.*]] ; THRESHOLD-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; THRESHOLD-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[X:%.*]], align 4 ; THRESHOLD-NEXT: [[TMP2:%.*]] = fmul fast float [[CONV]], 2.000000e+00 ; THRESHOLD-NEXT: [[TMP3:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP0]]) ; THRESHOLD-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP2]], [[TMP3]] ; THRESHOLD-NEXT: [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], 3.000000e+00 ; THRESHOLD-NEXT: ret float [[OP_RDX1]] ; entry: %mul = mul nsw i32 %b, %a %conv = sitofp i32 %mul to float %0 = load float, ptr %x, align 4 %add = fadd fast float %conv, 3.000000e+00 %add1 = fadd fast float %0, %add %arrayidx3 = getelementptr inbounds float, ptr %x, i64 1 %1 = load float, ptr %arrayidx3, align 4 %add4 = fadd fast float %1, %add1 %add5 = fadd fast float %add4, %conv %arrayidx3.1 = getelementptr inbounds float, ptr %x, i64 2 %2 = load float, ptr %arrayidx3.1, align 4 %add4.1 = fadd fast float %2, %add5 %arrayidx3.2 = getelementptr inbounds float, ptr %x, i64 3 %3 = load float, ptr %arrayidx3.2, align 4 %add4.2 = fadd fast float %3, %add4.1 %arrayidx3.3 = getelementptr inbounds float, ptr %x, i64 4 %4 = load float, ptr %arrayidx3.3, align 4 %add4.3 = fadd fast float %4, %add4.2 %arrayidx3.4 = getelementptr inbounds float, ptr %x, i64 5 %5 = load float, ptr %arrayidx3.4, align 4 %add4.4 = fadd fast float %5, %add4.3 %arrayidx3.5 = getelementptr inbounds float, ptr %x, i64 6 %6 = load float, ptr %arrayidx3.5, align 4 %add4.5 = fadd fast float %6, %add4.4 %arrayidx3.6 = getelementptr inbounds float, ptr %x, i64 7 %7 = load float, ptr %arrayidx3.6, align 4 %add4.6 = fadd fast float %7, %add4.5 ret float %add4.6 } define float @extra_args_same_several_times(ptr nocapture readonly %x, i32 %a, i32 %b) { ; CHECK-LABEL: @extra_args_same_several_times( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[B:%.*]], [[A:%.*]] ; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; CHECK-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[X:%.*]], align 4 ; CHECK-NEXT: [[TMP2:%.*]] = fmul fast float [[CONV]], 2.000000e+00 ; CHECK-NEXT: [[OP_RDX:%.*]] = fadd fast float 1.300000e+01, [[TMP2]] ; CHECK-NEXT: [[TMP3:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP0]]) ; CHECK-NEXT: [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], [[TMP3]] ; CHECK-NEXT: ret float [[OP_RDX1]] ; ; THRESHOLD-LABEL: @extra_args_same_several_times( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[MUL:%.*]] = mul nsw i32 [[B:%.*]], [[A:%.*]] ; THRESHOLD-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; THRESHOLD-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[X:%.*]], align 4 ; THRESHOLD-NEXT: [[TMP2:%.*]] = fmul fast float [[CONV]], 2.000000e+00 ; THRESHOLD-NEXT: [[OP_RDX:%.*]] = fadd fast float 1.300000e+01, [[TMP2]] ; THRESHOLD-NEXT: [[TMP3:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP0]]) ; THRESHOLD-NEXT: [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], [[TMP3]] ; THRESHOLD-NEXT: ret float [[OP_RDX1]] ; entry: %mul = mul nsw i32 %b, %a %conv = sitofp i32 %mul to float %0 = load float, ptr %x, align 4 %add = fadd fast float %conv, 3.000000e+00 %add1 = fadd fast float %0, %add %arrayidx3 = getelementptr inbounds float, ptr %x, i64 1 %1 = load float, ptr %arrayidx3, align 4 %add4 = fadd fast float %1, %add1 %add41 = fadd fast float %add4, 5.000000e+00 %add5 = fadd fast float %add41, %conv %arrayidx3.1 = getelementptr inbounds float, ptr %x, i64 2 %2 = load float, ptr %arrayidx3.1, align 4 %add4.1 = fadd fast float %2, %add5 %add4.11 = fadd fast float %add4.1, 5.000000e+00 %arrayidx3.2 = getelementptr inbounds float, ptr %x, i64 3 %3 = load float, ptr %arrayidx3.2, align 4 %add4.2 = fadd fast float %3, %add4.11 %arrayidx3.3 = getelementptr inbounds float, ptr %x, i64 4 %4 = load float, ptr %arrayidx3.3, align 4 %add4.3 = fadd fast float %4, %add4.2 %arrayidx3.4 = getelementptr inbounds float, ptr %x, i64 5 %5 = load float, ptr %arrayidx3.4, align 4 %add4.4 = fadd fast float %5, %add4.3 %arrayidx3.5 = getelementptr inbounds float, ptr %x, i64 6 %6 = load float, ptr %arrayidx3.5, align 4 %add4.5 = fadd fast float %6, %add4.4 %arrayidx3.6 = getelementptr inbounds float, ptr %x, i64 7 %7 = load float, ptr %arrayidx3.6, align 4 %add4.6 = fadd fast float %7, %add4.5 ret float %add4.6 } define float @extra_args_no_replace(ptr nocapture readonly %x, i32 %a, i32 %b, i32 %c) { ; CHECK-LABEL: @extra_args_no_replace( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[B:%.*]], [[A:%.*]] ; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; CHECK-NEXT: [[CONVC:%.*]] = sitofp i32 [[C:%.*]] to float ; CHECK-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[X:%.*]], align 4 ; CHECK-NEXT: [[TMP2:%.*]] = fmul fast float [[CONV]], 2.000000e+00 ; CHECK-NEXT: [[TMP3:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP0]]) ; CHECK-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP2]], [[TMP3]] ; CHECK-NEXT: [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], 3.000000e+00 ; CHECK-NEXT: [[OP_RDX2:%.*]] = fadd fast float [[OP_RDX1]], [[CONVC]] ; CHECK-NEXT: ret float [[OP_RDX2]] ; ; THRESHOLD-LABEL: @extra_args_no_replace( ; THRESHOLD-NEXT: entry: ; THRESHOLD-NEXT: [[MUL:%.*]] = mul nsw i32 [[B:%.*]], [[A:%.*]] ; THRESHOLD-NEXT: [[CONV:%.*]] = sitofp i32 [[MUL]] to float ; THRESHOLD-NEXT: [[CONVC:%.*]] = sitofp i32 [[C:%.*]] to float ; THRESHOLD-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[X:%.*]], align 4 ; THRESHOLD-NEXT: [[TMP2:%.*]] = fmul fast float [[CONV]], 2.000000e+00 ; THRESHOLD-NEXT: [[TMP3:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP0]]) ; THRESHOLD-NEXT: [[OP_RDX:%.*]] = fadd fast float [[TMP2]], [[TMP3]] ; THRESHOLD-NEXT: [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], 3.000000e+00 ; THRESHOLD-NEXT: [[OP_RDX2:%.*]] = fadd fast float [[OP_RDX1]], [[CONVC]] ; THRESHOLD-NEXT: ret float [[OP_RDX2]] ; entry: %mul = mul nsw i32 %b, %a %conv = sitofp i32 %mul to float %0 = load float, ptr %x, align 4 %convc = sitofp i32 %c to float %addc = fadd fast float %convc, 3.000000e+00 %add = fadd fast float %conv, %addc %add1 = fadd fast float %0, %add %arrayidx3 = getelementptr inbounds float, ptr %x, i64 1 %1 = load float, ptr %arrayidx3, align 4 %add4 = fadd fast float %1, %add1 %arrayidx3.1 = getelementptr inbounds float, ptr %x, i64 2 %2 = load float, ptr %arrayidx3.1, align 4 %add4.1 = fadd fast float %2, %add4 %arrayidx3.2 = getelementptr inbounds float, ptr %x, i64 3 %3 = load float, ptr %arrayidx3.2, align 4 %add4.2 = fadd fast float %3, %add4.1 %arrayidx3.3 = getelementptr inbounds float, ptr %x, i64 4 %4 = load float, ptr %arrayidx3.3, align 4 %add4.3 = fadd fast float %4, %add4.2 %add5 = fadd fast float %add4.3, %conv %arrayidx3.4 = getelementptr inbounds float, ptr %x, i64 5 %5 = load float, ptr %arrayidx3.4, align 4 %add4.4 = fadd fast float %5, %add5 %arrayidx3.5 = getelementptr inbounds float, ptr %x, i64 6 %6 = load float, ptr %arrayidx3.5, align 4 %add4.5 = fadd fast float %6, %add4.4 %arrayidx3.6 = getelementptr inbounds float, ptr %x, i64 7 %7 = load float, ptr %arrayidx3.6, align 4 %add4.6 = fadd fast float %7, %add4.5 ret float %add4.6 } define float @extra_args_no_fast(ptr %x, float %a, float %b) { ; CHECK-LABEL: @extra_args_no_fast( ; CHECK-NEXT: [[ADDC:%.*]] = fadd fast float [[B:%.*]], 3.000000e+00 ; CHECK-NEXT: [[ADD:%.*]] = fadd fast float [[A:%.*]], [[ADDC]] ; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, ptr [[X:%.*]], i64 1 ; CHECK-NEXT: [[ARRAYIDX3_1:%.*]] = getelementptr inbounds float, ptr [[X]], i64 2 ; CHECK-NEXT: [[ARRAYIDX3_2:%.*]] = getelementptr inbounds float, ptr [[X]], i64 3 ; CHECK-NEXT: [[T0:%.*]] = load float, ptr [[X]], align 4 ; CHECK-NEXT: [[T1:%.*]] = load float, ptr [[ARRAYIDX3]], align 4 ; CHECK-NEXT: [[T2:%.*]] = load float, ptr [[ARRAYIDX3_1]], align 4 ; CHECK-NEXT: [[T3:%.*]] = load float, ptr [[ARRAYIDX3_2]], align 4 ; CHECK-NEXT: [[ADD1:%.*]] = fadd fast float [[T0]], [[ADD]] ; CHECK-NEXT: [[ADD4:%.*]] = fadd fast float [[T1]], [[ADD1]] ; CHECK-NEXT: [[ADD4_1:%.*]] = fadd float [[T2]], [[ADD4]] ; CHECK-NEXT: [[ADD4_2:%.*]] = fadd fast float [[T3]], [[ADD4_1]] ; CHECK-NEXT: [[ADD5:%.*]] = fadd fast float [[ADD4_2]], [[A]] ; CHECK-NEXT: ret float [[ADD5]] ; ; THRESHOLD-LABEL: @extra_args_no_fast( ; THRESHOLD-NEXT: [[ADDC:%.*]] = fadd fast float [[B:%.*]], 3.000000e+00 ; THRESHOLD-NEXT: [[ADD:%.*]] = fadd fast float [[A:%.*]], [[ADDC]] ; THRESHOLD-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, ptr [[X:%.*]], i64 1 ; THRESHOLD-NEXT: [[ARRAYIDX3_1:%.*]] = getelementptr inbounds float, ptr [[X]], i64 2 ; THRESHOLD-NEXT: [[ARRAYIDX3_2:%.*]] = getelementptr inbounds float, ptr [[X]], i64 3 ; THRESHOLD-NEXT: [[T0:%.*]] = load float, ptr [[X]], align 4 ; THRESHOLD-NEXT: [[T1:%.*]] = load float, ptr [[ARRAYIDX3]], align 4 ; THRESHOLD-NEXT: [[T2:%.*]] = load float, ptr [[ARRAYIDX3_1]], align 4 ; THRESHOLD-NEXT: [[T3:%.*]] = load float, ptr [[ARRAYIDX3_2]], align 4 ; THRESHOLD-NEXT: [[ADD1:%.*]] = fadd fast float [[T0]], [[ADD]] ; THRESHOLD-NEXT: [[ADD4:%.*]] = fadd fast float [[T1]], [[ADD1]] ; THRESHOLD-NEXT: [[ADD4_1:%.*]] = fadd float [[T2]], [[ADD4]] ; THRESHOLD-NEXT: [[ADD4_2:%.*]] = fadd fast float [[T3]], [[ADD4_1]] ; THRESHOLD-NEXT: [[ADD5:%.*]] = fadd fast float [[ADD4_2]], [[A]] ; THRESHOLD-NEXT: ret float [[ADD5]] ; %addc = fadd fast float %b, 3.0 %add = fadd fast float %a, %addc %arrayidx3 = getelementptr inbounds float, ptr %x, i64 1 %arrayidx3.1 = getelementptr inbounds float, ptr %x, i64 2 %arrayidx3.2 = getelementptr inbounds float, ptr %x, i64 3 %t0 = load float, ptr %x, align 4 %t1 = load float, ptr %arrayidx3, align 4 %t2 = load float, ptr %arrayidx3.1, align 4 %t3 = load float, ptr %arrayidx3.2, align 4 %add1 = fadd fast float %t0, %add %add4 = fadd fast float %t1, %add1 %add4.1 = fadd float %t2, %add4 ; this is not a reduction candidate %add4.2 = fadd fast float %t3, %add4.1 %add5 = fadd fast float %add4.2, %a ret float %add5 } define i32 @wobble(i32 %arg, i32 %bar) { ; CHECK-LABEL: @wobble( ; CHECK-NEXT: bb: ; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[ARG:%.*]], i32 0 ; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> poison, i32 [[BAR:%.*]], i32 0 ; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP4:%.*]] = xor <4 x i32> [[TMP1]], [[TMP3]] ; CHECK-NEXT: [[X4:%.*]] = xor i32 [[ARG]], [[BAR]] ; CHECK-NEXT: [[TMP5:%.*]] = icmp eq <4 x i32> [[TMP4]], zeroinitializer ; CHECK-NEXT: [[TMP6:%.*]] = sext <4 x i1> [[TMP5]] to <4 x i32> ; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP6]]) ; CHECK-NEXT: [[OP_RDX:%.*]] = add i32 [[TMP7]], [[X4]] ; CHECK-NEXT: [[OP_RDX1:%.*]] = add i32 [[OP_RDX]], [[ARG]] ; CHECK-NEXT: ret i32 [[OP_RDX1]] ; ; THRESHOLD-LABEL: @wobble( ; THRESHOLD-NEXT: bb: ; THRESHOLD-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[ARG:%.*]], i32 0 ; THRESHOLD-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer ; THRESHOLD-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> poison, i32 [[BAR:%.*]], i32 0 ; THRESHOLD-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> zeroinitializer ; THRESHOLD-NEXT: [[TMP4:%.*]] = xor <4 x i32> [[TMP1]], [[TMP3]] ; THRESHOLD-NEXT: [[X4:%.*]] = xor i32 [[ARG]], [[BAR]] ; THRESHOLD-NEXT: [[TMP5:%.*]] = icmp eq <4 x i32> [[TMP4]], zeroinitializer ; THRESHOLD-NEXT: [[TMP6:%.*]] = sext <4 x i1> [[TMP5]] to <4 x i32> ; THRESHOLD-NEXT: [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP6]]) ; THRESHOLD-NEXT: [[OP_RDX:%.*]] = add i32 [[TMP7]], [[X4]] ; THRESHOLD-NEXT: [[OP_RDX1:%.*]] = add i32 [[OP_RDX]], [[ARG]] ; THRESHOLD-NEXT: ret i32 [[OP_RDX1]] ; bb: %x1 = xor i32 %arg, %bar %i1 = icmp eq i32 %x1, 0 %s1 = sext i1 %i1 to i32 %x2 = xor i32 %arg, %bar %i2 = icmp eq i32 %x2, 0 %s2 = sext i1 %i2 to i32 %x3 = xor i32 %arg, %bar %i3 = icmp eq i32 %x3, 0 %s3 = sext i1 %i3 to i32 %x4 = xor i32 %arg, %bar %i4 = icmp eq i32 %x4, 0 %s4 = sext i1 %i4 to i32 %r1 = add nuw i32 %arg, %s1 %r2 = add nsw i32 %r1, %s2 %r3 = add nsw i32 %r2, %s3 %r4 = add nsw i32 %r3, %s4 %r5 = add nsw i32 %r4, %x4 ret i32 %r5 }