diff --git a/llvm/test/Transforms/SLPVectorizer/X86/fmaxnum.ll b/llvm/test/Transforms/SLPVectorizer/X86/fmaxnum.ll new file mode 100644 index 000000000000..3c8c344a1bd8 --- /dev/null +++ b/llvm/test/Transforms/SLPVectorizer/X86/fmaxnum.ll @@ -0,0 +1,403 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -mtriple=x86_64-unknown -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,SSE +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX256 +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=bdver1 -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX256 +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX256 +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skylake-avx512 -mattr=-prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX512 +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skylake-avx512 -mattr=+prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX256 + +@srcA64 = common global [8 x double] zeroinitializer, align 64 +@srcB64 = common global [8 x double] zeroinitializer, align 64 +@srcC64 = common global [8 x double] zeroinitializer, align 64 +@srcA32 = common global [16 x float] zeroinitializer, align 64 +@srcB32 = common global [16 x float] zeroinitializer, align 64 +@srcC32 = common global [16 x float] zeroinitializer, align 64 +@dst64 = common global [8 x double] zeroinitializer, align 64 +@dst32 = common global [16 x float] zeroinitializer, align 64 + +declare float @llvm.maxnum.f32(float, float) +declare double @llvm.maxnum.f64(double, double) + +; +; CHECK +; + +define void @fmaxnum_2f64() #0 { +; CHECK-LABEL: @fmaxnum_2f64( +; CHECK-NEXT: [[A0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 8 +; CHECK-NEXT: [[A1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[B0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 8 +; CHECK-NEXT: [[B1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[FMAXNUM0:%.*]] = call double @llvm.maxnum.f64(double [[A0]], double [[B0]]) +; CHECK-NEXT: [[FMAXNUM1:%.*]] = call double @llvm.maxnum.f64(double [[A1]], double [[B1]]) +; CHECK-NEXT: store double [[FMAXNUM0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 8 +; CHECK-NEXT: store double [[FMAXNUM1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; CHECK-NEXT: ret void +; + %a0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 8 + %a1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 8 + %b0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 8 + %b1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 8 + %fmaxnum0 = call double @llvm.maxnum.f64(double %a0, double %b0) + %fmaxnum1 = call double @llvm.maxnum.f64(double %a1, double %b1) + store double %fmaxnum0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 8 + store double %fmaxnum1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + ret void +} + +define void @fmaxnum_4f64() #0 { +; CHECK-LABEL: @fmaxnum_4f64( +; CHECK-NEXT: [[A0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 8 +; CHECK-NEXT: [[A1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[A2:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 2), align 8 +; CHECK-NEXT: [[A3:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 3), align 8 +; CHECK-NEXT: [[B0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 8 +; CHECK-NEXT: [[B1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[B2:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 2), align 8 +; CHECK-NEXT: [[B3:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 3), align 8 +; CHECK-NEXT: [[FMAXNUM0:%.*]] = call double @llvm.maxnum.f64(double [[A0]], double [[B0]]) +; CHECK-NEXT: [[FMAXNUM1:%.*]] = call double @llvm.maxnum.f64(double [[A1]], double [[B1]]) +; CHECK-NEXT: [[FMAXNUM2:%.*]] = call double @llvm.maxnum.f64(double [[A2]], double [[B2]]) +; CHECK-NEXT: [[FMAXNUM3:%.*]] = call double @llvm.maxnum.f64(double [[A3]], double [[B3]]) +; CHECK-NEXT: store double [[FMAXNUM0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 8 +; CHECK-NEXT: store double [[FMAXNUM1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; CHECK-NEXT: store double [[FMAXNUM2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 8 +; CHECK-NEXT: store double [[FMAXNUM3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; CHECK-NEXT: ret void +; + %a0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 8 + %a1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 8 + %a2 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 2), align 8 + %a3 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 3), align 8 + %b0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 8 + %b1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 8 + %b2 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 2), align 8 + %b3 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 3), align 8 + %fmaxnum0 = call double @llvm.maxnum.f64(double %a0, double %b0) + %fmaxnum1 = call double @llvm.maxnum.f64(double %a1, double %b1) + %fmaxnum2 = call double @llvm.maxnum.f64(double %a2, double %b2) + %fmaxnum3 = call double @llvm.maxnum.f64(double %a3, double %b3) + store double %fmaxnum0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 8 + store double %fmaxnum1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %fmaxnum2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 8 + store double %fmaxnum3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + ret void +} + +define void @fmaxnum_8f64() #0 { +; CHECK-LABEL: @fmaxnum_8f64( +; CHECK-NEXT: [[A0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 4 +; CHECK-NEXT: [[A1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 4 +; CHECK-NEXT: [[A2:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 2), align 4 +; CHECK-NEXT: [[A3:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 3), align 4 +; CHECK-NEXT: [[A4:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 4), align 4 +; CHECK-NEXT: [[A5:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 5), align 4 +; CHECK-NEXT: [[A6:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 6), align 4 +; CHECK-NEXT: [[A7:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 7), align 4 +; CHECK-NEXT: [[B0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 4 +; CHECK-NEXT: [[B1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 4 +; CHECK-NEXT: [[B2:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 2), align 4 +; CHECK-NEXT: [[B3:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 3), align 4 +; CHECK-NEXT: [[B4:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 4), align 4 +; CHECK-NEXT: [[B5:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 5), align 4 +; CHECK-NEXT: [[B6:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 6), align 4 +; CHECK-NEXT: [[B7:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 7), align 4 +; CHECK-NEXT: [[FMAXNUM0:%.*]] = call double @llvm.maxnum.f64(double [[A0]], double [[B0]]) +; CHECK-NEXT: [[FMAXNUM1:%.*]] = call double @llvm.maxnum.f64(double [[A1]], double [[B1]]) +; CHECK-NEXT: [[FMAXNUM2:%.*]] = call double @llvm.maxnum.f64(double [[A2]], double [[B2]]) +; CHECK-NEXT: [[FMAXNUM3:%.*]] = call double @llvm.maxnum.f64(double [[A3]], double [[B3]]) +; CHECK-NEXT: [[FMAXNUM4:%.*]] = call double @llvm.maxnum.f64(double [[A4]], double [[B4]]) +; CHECK-NEXT: [[FMAXNUM5:%.*]] = call double @llvm.maxnum.f64(double [[A5]], double [[B5]]) +; CHECK-NEXT: [[FMAXNUM6:%.*]] = call double @llvm.maxnum.f64(double [[A6]], double [[B6]]) +; CHECK-NEXT: [[FMAXNUM7:%.*]] = call double @llvm.maxnum.f64(double [[A7]], double [[B7]]) +; CHECK-NEXT: store double [[FMAXNUM0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 4 +; CHECK-NEXT: store double [[FMAXNUM1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 4 +; CHECK-NEXT: store double [[FMAXNUM2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 4 +; CHECK-NEXT: store double [[FMAXNUM3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 4 +; CHECK-NEXT: store double [[FMAXNUM4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 4 +; CHECK-NEXT: store double [[FMAXNUM5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 4 +; CHECK-NEXT: store double [[FMAXNUM6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 4 +; CHECK-NEXT: store double [[FMAXNUM7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 4 +; CHECK-NEXT: ret void +; + %a0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 4 + %a1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 4 + %a2 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 2), align 4 + %a3 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 3), align 4 + %a4 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 4), align 4 + %a5 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 5), align 4 + %a6 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 6), align 4 + %a7 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 7), align 4 + %b0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 4 + %b1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 4 + %b2 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 2), align 4 + %b3 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 3), align 4 + %b4 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 4), align 4 + %b5 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 5), align 4 + %b6 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 6), align 4 + %b7 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 7), align 4 + %fmaxnum0 = call double @llvm.maxnum.f64(double %a0, double %b0) + %fmaxnum1 = call double @llvm.maxnum.f64(double %a1, double %b1) + %fmaxnum2 = call double @llvm.maxnum.f64(double %a2, double %b2) + %fmaxnum3 = call double @llvm.maxnum.f64(double %a3, double %b3) + %fmaxnum4 = call double @llvm.maxnum.f64(double %a4, double %b4) + %fmaxnum5 = call double @llvm.maxnum.f64(double %a5, double %b5) + %fmaxnum6 = call double @llvm.maxnum.f64(double %a6, double %b6) + %fmaxnum7 = call double @llvm.maxnum.f64(double %a7, double %b7) + store double %fmaxnum0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 4 + store double %fmaxnum1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 4 + store double %fmaxnum2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 4 + store double %fmaxnum3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 4 + store double %fmaxnum4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 4 + store double %fmaxnum5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 4 + store double %fmaxnum6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 4 + store double %fmaxnum7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 4 + ret void +} + +define void @fmaxnum_4f32() #0 { +; CHECK-LABEL: @fmaxnum_4f32( +; CHECK-NEXT: [[A0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[A1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[A2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[A3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[B0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[B1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[B2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[B3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[FMAXNUM0:%.*]] = call float @llvm.maxnum.f32(float [[A0]], float [[B0]]) +; CHECK-NEXT: [[FMAXNUM1:%.*]] = call float @llvm.maxnum.f32(float [[A1]], float [[B1]]) +; CHECK-NEXT: [[FMAXNUM2:%.*]] = call float @llvm.maxnum.f32(float [[A2]], float [[B2]]) +; CHECK-NEXT: [[FMAXNUM3:%.*]] = call float @llvm.maxnum.f32(float [[A3]], float [[B3]]) +; CHECK-NEXT: store float [[FMAXNUM0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 +; CHECK-NEXT: store float [[FMAXNUM1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; CHECK-NEXT: store float [[FMAXNUM2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 +; CHECK-NEXT: store float [[FMAXNUM3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; CHECK-NEXT: ret void +; + %a0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 + %a1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 + %a2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 + %a3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 + %b0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 + %b1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 + %b2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 + %b3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 + %fmaxnum0 = call float @llvm.maxnum.f32(float %a0, float %b0) + %fmaxnum1 = call float @llvm.maxnum.f32(float %a1, float %b1) + %fmaxnum2 = call float @llvm.maxnum.f32(float %a2, float %b2) + %fmaxnum3 = call float @llvm.maxnum.f32(float %a3, float %b3) + store float %fmaxnum0, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 + store float %fmaxnum1, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 + store float %fmaxnum2, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 + store float %fmaxnum3, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 + ret void +} + +define void @fmaxnum_8f32() #0 { +; CHECK-LABEL: @fmaxnum_8f32( +; CHECK-NEXT: [[A0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[A1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[A2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[A3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[A4:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 4), align 4 +; CHECK-NEXT: [[A5:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 5), align 4 +; CHECK-NEXT: [[A6:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 6), align 4 +; CHECK-NEXT: [[A7:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 7), align 4 +; CHECK-NEXT: [[B0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[B1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[B2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[B3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[B4:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 4), align 4 +; CHECK-NEXT: [[B5:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 5), align 4 +; CHECK-NEXT: [[B6:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 6), align 4 +; CHECK-NEXT: [[B7:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 7), align 4 +; CHECK-NEXT: [[FMAXNUM0:%.*]] = call float @llvm.maxnum.f32(float [[A0]], float [[B0]]) +; CHECK-NEXT: [[FMAXNUM1:%.*]] = call float @llvm.maxnum.f32(float [[A1]], float [[B1]]) +; CHECK-NEXT: [[FMAXNUM2:%.*]] = call float @llvm.maxnum.f32(float [[A2]], float [[B2]]) +; CHECK-NEXT: [[FMAXNUM3:%.*]] = call float @llvm.maxnum.f32(float [[A3]], float [[B3]]) +; CHECK-NEXT: [[FMAXNUM4:%.*]] = call float @llvm.maxnum.f32(float [[A4]], float [[B4]]) +; CHECK-NEXT: [[FMAXNUM5:%.*]] = call float @llvm.maxnum.f32(float [[A5]], float [[B5]]) +; CHECK-NEXT: [[FMAXNUM6:%.*]] = call float @llvm.maxnum.f32(float [[A6]], float [[B6]]) +; CHECK-NEXT: [[FMAXNUM7:%.*]] = call float @llvm.maxnum.f32(float [[A7]], float [[B7]]) +; CHECK-NEXT: store float [[FMAXNUM0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 +; CHECK-NEXT: store float [[FMAXNUM1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; CHECK-NEXT: store float [[FMAXNUM2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 +; CHECK-NEXT: store float [[FMAXNUM3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; CHECK-NEXT: store float [[FMAXNUM4]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 4 +; CHECK-NEXT: store float [[FMAXNUM5]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 +; CHECK-NEXT: store float [[FMAXNUM6]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 4 +; CHECK-NEXT: store float [[FMAXNUM7]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 +; CHECK-NEXT: ret void +; + %a0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 + %a1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 + %a2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 + %a3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 + %a4 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 4), align 4 + %a5 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 5), align 4 + %a6 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 6), align 4 + %a7 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 7), align 4 + %b0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 + %b1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 + %b2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 + %b3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 + %b4 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 4), align 4 + %b5 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 5), align 4 + %b6 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 6), align 4 + %b7 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 7), align 4 + %fmaxnum0 = call float @llvm.maxnum.f32(float %a0, float %b0) + %fmaxnum1 = call float @llvm.maxnum.f32(float %a1, float %b1) + %fmaxnum2 = call float @llvm.maxnum.f32(float %a2, float %b2) + %fmaxnum3 = call float @llvm.maxnum.f32(float %a3, float %b3) + %fmaxnum4 = call float @llvm.maxnum.f32(float %a4, float %b4) + %fmaxnum5 = call float @llvm.maxnum.f32(float %a5, float %b5) + %fmaxnum6 = call float @llvm.maxnum.f32(float %a6, float %b6) + %fmaxnum7 = call float @llvm.maxnum.f32(float %a7, float %b7) + store float %fmaxnum0, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 + store float %fmaxnum1, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 + store float %fmaxnum2, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 + store float %fmaxnum3, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 + store float %fmaxnum4, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 4 + store float %fmaxnum5, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 + store float %fmaxnum6, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 4 + store float %fmaxnum7, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 + ret void +} + +define void @fmaxnum_16f32() #0 { +; CHECK-LABEL: @fmaxnum_16f32( +; CHECK-NEXT: [[A0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[A1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[A2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[A3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[A4:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 4), align 4 +; CHECK-NEXT: [[A5:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 5), align 4 +; CHECK-NEXT: [[A6:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 6), align 4 +; CHECK-NEXT: [[A7:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 7), align 4 +; CHECK-NEXT: [[A8:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 8), align 4 +; CHECK-NEXT: [[A9:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 9), align 4 +; CHECK-NEXT: [[A10:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 10), align 4 +; CHECK-NEXT: [[A11:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 11), align 4 +; CHECK-NEXT: [[A12:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 12), align 4 +; CHECK-NEXT: [[A13:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 13), align 4 +; CHECK-NEXT: [[A14:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 14), align 4 +; CHECK-NEXT: [[A15:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 15), align 4 +; CHECK-NEXT: [[B0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[B1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[B2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[B3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[B4:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 4), align 4 +; CHECK-NEXT: [[B5:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 5), align 4 +; CHECK-NEXT: [[B6:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 6), align 4 +; CHECK-NEXT: [[B7:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 7), align 4 +; CHECK-NEXT: [[B8:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 8), align 4 +; CHECK-NEXT: [[B9:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 9), align 4 +; CHECK-NEXT: [[B10:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 10), align 4 +; CHECK-NEXT: [[B11:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 11), align 4 +; CHECK-NEXT: [[B12:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 12), align 4 +; CHECK-NEXT: [[B13:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 13), align 4 +; CHECK-NEXT: [[B14:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 14), align 4 +; CHECK-NEXT: [[B15:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 15), align 4 +; CHECK-NEXT: [[FMAXNUM0:%.*]] = call float @llvm.maxnum.f32(float [[A0]], float [[B0]]) +; CHECK-NEXT: [[FMAXNUM1:%.*]] = call float @llvm.maxnum.f32(float [[A1]], float [[B1]]) +; CHECK-NEXT: [[FMAXNUM2:%.*]] = call float @llvm.maxnum.f32(float [[A2]], float [[B2]]) +; CHECK-NEXT: [[FMAXNUM3:%.*]] = call float @llvm.maxnum.f32(float [[A3]], float [[B3]]) +; CHECK-NEXT: [[FMAXNUM4:%.*]] = call float @llvm.maxnum.f32(float [[A4]], float [[B4]]) +; CHECK-NEXT: [[FMAXNUM5:%.*]] = call float @llvm.maxnum.f32(float [[A5]], float [[B5]]) +; CHECK-NEXT: [[FMAXNUM6:%.*]] = call float @llvm.maxnum.f32(float [[A6]], float [[B6]]) +; CHECK-NEXT: [[FMAXNUM7:%.*]] = call float @llvm.maxnum.f32(float [[A7]], float [[B7]]) +; CHECK-NEXT: [[FMAXNUM8:%.*]] = call float @llvm.maxnum.f32(float [[A8]], float [[B8]]) +; CHECK-NEXT: [[FMAXNUM9:%.*]] = call float @llvm.maxnum.f32(float [[A9]], float [[B9]]) +; CHECK-NEXT: [[FMAXNUM10:%.*]] = call float @llvm.maxnum.f32(float [[A10]], float [[B10]]) +; CHECK-NEXT: [[FMAXNUM11:%.*]] = call float @llvm.maxnum.f32(float [[A11]], float [[B11]]) +; CHECK-NEXT: [[FMAXNUM12:%.*]] = call float @llvm.maxnum.f32(float [[A12]], float [[B12]]) +; CHECK-NEXT: [[FMAXNUM13:%.*]] = call float @llvm.maxnum.f32(float [[A13]], float [[B13]]) +; CHECK-NEXT: [[FMAXNUM14:%.*]] = call float @llvm.maxnum.f32(float [[A14]], float [[B14]]) +; CHECK-NEXT: [[FMAXNUM15:%.*]] = call float @llvm.maxnum.f32(float [[A15]], float [[B15]]) +; CHECK-NEXT: store float [[FMAXNUM0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 +; CHECK-NEXT: store float [[FMAXNUM1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; CHECK-NEXT: store float [[FMAXNUM2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 +; CHECK-NEXT: store float [[FMAXNUM3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; CHECK-NEXT: store float [[FMAXNUM4]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 4 +; CHECK-NEXT: store float [[FMAXNUM5]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 +; CHECK-NEXT: store float [[FMAXNUM6]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 4 +; CHECK-NEXT: store float [[FMAXNUM7]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 +; CHECK-NEXT: store float [[FMAXNUM8]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8), align 4 +; CHECK-NEXT: store float [[FMAXNUM9]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9), align 4 +; CHECK-NEXT: store float [[FMAXNUM10]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 4 +; CHECK-NEXT: store float [[FMAXNUM11]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 +; CHECK-NEXT: store float [[FMAXNUM12]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 4 +; CHECK-NEXT: store float [[FMAXNUM13]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 +; CHECK-NEXT: store float [[FMAXNUM14]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 4 +; CHECK-NEXT: store float [[FMAXNUM15]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 +; CHECK-NEXT: ret void +; + %a0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 + %a1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 + %a2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 + %a3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 + %a4 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 4), align 4 + %a5 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 5), align 4 + %a6 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 6), align 4 + %a7 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 7), align 4 + %a8 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 8), align 4 + %a9 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 9), align 4 + %a10 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 10), align 4 + %a11 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 11), align 4 + %a12 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 12), align 4 + %a13 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 13), align 4 + %a14 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 14), align 4 + %a15 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 15), align 4 + %b0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 + %b1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 + %b2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 + %b3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 + %b4 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 4), align 4 + %b5 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 5), align 4 + %b6 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 6), align 4 + %b7 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 7), align 4 + %b8 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 8), align 4 + %b9 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 9), align 4 + %b10 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 10), align 4 + %b11 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 11), align 4 + %b12 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 12), align 4 + %b13 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 13), align 4 + %b14 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 14), align 4 + %b15 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 15), align 4 + %fmaxnum0 = call float @llvm.maxnum.f32(float %a0 , float %b0 ) + %fmaxnum1 = call float @llvm.maxnum.f32(float %a1 , float %b1 ) + %fmaxnum2 = call float @llvm.maxnum.f32(float %a2 , float %b2 ) + %fmaxnum3 = call float @llvm.maxnum.f32(float %a3 , float %b3 ) + %fmaxnum4 = call float @llvm.maxnum.f32(float %a4 , float %b4 ) + %fmaxnum5 = call float @llvm.maxnum.f32(float %a5 , float %b5 ) + %fmaxnum6 = call float @llvm.maxnum.f32(float %a6 , float %b6 ) + %fmaxnum7 = call float @llvm.maxnum.f32(float %a7 , float %b7 ) + %fmaxnum8 = call float @llvm.maxnum.f32(float %a8 , float %b8 ) + %fmaxnum9 = call float @llvm.maxnum.f32(float %a9 , float %b9 ) + %fmaxnum10 = call float @llvm.maxnum.f32(float %a10, float %b10) + %fmaxnum11 = call float @llvm.maxnum.f32(float %a11, float %b11) + %fmaxnum12 = call float @llvm.maxnum.f32(float %a12, float %b12) + %fmaxnum13 = call float @llvm.maxnum.f32(float %a13, float %b13) + %fmaxnum14 = call float @llvm.maxnum.f32(float %a14, float %b14) + %fmaxnum15 = call float @llvm.maxnum.f32(float %a15, float %b15) + store float %fmaxnum0 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 + store float %fmaxnum1 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 + store float %fmaxnum2 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 + store float %fmaxnum3 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 + store float %fmaxnum4 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 4 + store float %fmaxnum5 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 + store float %fmaxnum6 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 4 + store float %fmaxnum7 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 + store float %fmaxnum8 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8), align 4 + store float %fmaxnum9 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9), align 4 + store float %fmaxnum10, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 4 + store float %fmaxnum11, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 + store float %fmaxnum12, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 4 + store float %fmaxnum13, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 + store float %fmaxnum14, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 4 + store float %fmaxnum15, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 + ret void +} + +attributes #0 = { nounwind } diff --git a/llvm/test/Transforms/SLPVectorizer/X86/fminnum.ll b/llvm/test/Transforms/SLPVectorizer/X86/fminnum.ll new file mode 100644 index 000000000000..ca0a25747675 --- /dev/null +++ b/llvm/test/Transforms/SLPVectorizer/X86/fminnum.ll @@ -0,0 +1,403 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -mtriple=x86_64-unknown -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,SSE +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX256 +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=bdver1 -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX256 +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX256 +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skylake-avx512 -mattr=-prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX512 +; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skylake-avx512 -mattr=+prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefixes=CHECK,AVX,AVX256 + +@srcA64 = common global [8 x double] zeroinitializer, align 64 +@srcB64 = common global [8 x double] zeroinitializer, align 64 +@srcC64 = common global [8 x double] zeroinitializer, align 64 +@srcA32 = common global [16 x float] zeroinitializer, align 64 +@srcB32 = common global [16 x float] zeroinitializer, align 64 +@srcC32 = common global [16 x float] zeroinitializer, align 64 +@dst64 = common global [8 x double] zeroinitializer, align 64 +@dst32 = common global [16 x float] zeroinitializer, align 64 + +declare float @llvm.minnum.f32(float, float) +declare double @llvm.minnum.f64(double, double) + +; +; CHECK +; + +define void @fminnum_2f64() #0 { +; CHECK-LABEL: @fminnum_2f64( +; CHECK-NEXT: [[A0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 8 +; CHECK-NEXT: [[A1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[B0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 8 +; CHECK-NEXT: [[B1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[FMINNUM0:%.*]] = call double @llvm.minnum.f64(double [[A0]], double [[B0]]) +; CHECK-NEXT: [[FMINNUM1:%.*]] = call double @llvm.minnum.f64(double [[A1]], double [[B1]]) +; CHECK-NEXT: store double [[FMINNUM0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 8 +; CHECK-NEXT: store double [[FMINNUM1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; CHECK-NEXT: ret void +; + %a0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 8 + %a1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 8 + %b0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 8 + %b1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 8 + %fminnum0 = call double @llvm.minnum.f64(double %a0, double %b0) + %fminnum1 = call double @llvm.minnum.f64(double %a1, double %b1) + store double %fminnum0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 8 + store double %fminnum1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + ret void +} + +define void @fminnum_4f64() #0 { +; CHECK-LABEL: @fminnum_4f64( +; CHECK-NEXT: [[A0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 8 +; CHECK-NEXT: [[A1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[A2:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 2), align 8 +; CHECK-NEXT: [[A3:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 3), align 8 +; CHECK-NEXT: [[B0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 8 +; CHECK-NEXT: [[B1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[B2:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 2), align 8 +; CHECK-NEXT: [[B3:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 3), align 8 +; CHECK-NEXT: [[FMINNUM0:%.*]] = call double @llvm.minnum.f64(double [[A0]], double [[B0]]) +; CHECK-NEXT: [[FMINNUM1:%.*]] = call double @llvm.minnum.f64(double [[A1]], double [[B1]]) +; CHECK-NEXT: [[FMINNUM2:%.*]] = call double @llvm.minnum.f64(double [[A2]], double [[B2]]) +; CHECK-NEXT: [[FMINNUM3:%.*]] = call double @llvm.minnum.f64(double [[A3]], double [[B3]]) +; CHECK-NEXT: store double [[FMINNUM0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 8 +; CHECK-NEXT: store double [[FMINNUM1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; CHECK-NEXT: store double [[FMINNUM2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 8 +; CHECK-NEXT: store double [[FMINNUM3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; CHECK-NEXT: ret void +; + %a0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 8 + %a1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 8 + %a2 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 2), align 8 + %a3 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 3), align 8 + %b0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 8 + %b1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 8 + %b2 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 2), align 8 + %b3 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 3), align 8 + %fminnum0 = call double @llvm.minnum.f64(double %a0, double %b0) + %fminnum1 = call double @llvm.minnum.f64(double %a1, double %b1) + %fminnum2 = call double @llvm.minnum.f64(double %a2, double %b2) + %fminnum3 = call double @llvm.minnum.f64(double %a3, double %b3) + store double %fminnum0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 8 + store double %fminnum1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %fminnum2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 8 + store double %fminnum3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + ret void +} + +define void @fminnum_8f64() #0 { +; CHECK-LABEL: @fminnum_8f64( +; CHECK-NEXT: [[A0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 4 +; CHECK-NEXT: [[A1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 4 +; CHECK-NEXT: [[A2:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 2), align 4 +; CHECK-NEXT: [[A3:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 3), align 4 +; CHECK-NEXT: [[A4:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 4), align 4 +; CHECK-NEXT: [[A5:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 5), align 4 +; CHECK-NEXT: [[A6:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 6), align 4 +; CHECK-NEXT: [[A7:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 7), align 4 +; CHECK-NEXT: [[B0:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 4 +; CHECK-NEXT: [[B1:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 4 +; CHECK-NEXT: [[B2:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 2), align 4 +; CHECK-NEXT: [[B3:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 3), align 4 +; CHECK-NEXT: [[B4:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 4), align 4 +; CHECK-NEXT: [[B5:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 5), align 4 +; CHECK-NEXT: [[B6:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 6), align 4 +; CHECK-NEXT: [[B7:%.*]] = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 7), align 4 +; CHECK-NEXT: [[FMINNUM0:%.*]] = call double @llvm.minnum.f64(double [[A0]], double [[B0]]) +; CHECK-NEXT: [[FMINNUM1:%.*]] = call double @llvm.minnum.f64(double [[A1]], double [[B1]]) +; CHECK-NEXT: [[FMINNUM2:%.*]] = call double @llvm.minnum.f64(double [[A2]], double [[B2]]) +; CHECK-NEXT: [[FMINNUM3:%.*]] = call double @llvm.minnum.f64(double [[A3]], double [[B3]]) +; CHECK-NEXT: [[FMINNUM4:%.*]] = call double @llvm.minnum.f64(double [[A4]], double [[B4]]) +; CHECK-NEXT: [[FMINNUM5:%.*]] = call double @llvm.minnum.f64(double [[A5]], double [[B5]]) +; CHECK-NEXT: [[FMINNUM6:%.*]] = call double @llvm.minnum.f64(double [[A6]], double [[B6]]) +; CHECK-NEXT: [[FMINNUM7:%.*]] = call double @llvm.minnum.f64(double [[A7]], double [[B7]]) +; CHECK-NEXT: store double [[FMINNUM0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 4 +; CHECK-NEXT: store double [[FMINNUM1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 4 +; CHECK-NEXT: store double [[FMINNUM2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 4 +; CHECK-NEXT: store double [[FMINNUM3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 4 +; CHECK-NEXT: store double [[FMINNUM4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 4 +; CHECK-NEXT: store double [[FMINNUM5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 4 +; CHECK-NEXT: store double [[FMINNUM6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 4 +; CHECK-NEXT: store double [[FMINNUM7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 4 +; CHECK-NEXT: ret void +; + %a0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 0), align 4 + %a1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 1), align 4 + %a2 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 2), align 4 + %a3 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 3), align 4 + %a4 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 4), align 4 + %a5 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 5), align 4 + %a6 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 6), align 4 + %a7 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcA64, i32 0, i64 7), align 4 + %b0 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 0), align 4 + %b1 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 1), align 4 + %b2 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 2), align 4 + %b3 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 3), align 4 + %b4 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 4), align 4 + %b5 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 5), align 4 + %b6 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 6), align 4 + %b7 = load double, double* getelementptr inbounds ([8 x double], [8 x double]* @srcB64, i32 0, i64 7), align 4 + %fminnum0 = call double @llvm.minnum.f64(double %a0, double %b0) + %fminnum1 = call double @llvm.minnum.f64(double %a1, double %b1) + %fminnum2 = call double @llvm.minnum.f64(double %a2, double %b2) + %fminnum3 = call double @llvm.minnum.f64(double %a3, double %b3) + %fminnum4 = call double @llvm.minnum.f64(double %a4, double %b4) + %fminnum5 = call double @llvm.minnum.f64(double %a5, double %b5) + %fminnum6 = call double @llvm.minnum.f64(double %a6, double %b6) + %fminnum7 = call double @llvm.minnum.f64(double %a7, double %b7) + store double %fminnum0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 4 + store double %fminnum1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 4 + store double %fminnum2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 4 + store double %fminnum3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 4 + store double %fminnum4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 4 + store double %fminnum5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 4 + store double %fminnum6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 4 + store double %fminnum7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 4 + ret void +} + +define void @fminnum_4f32() #0 { +; CHECK-LABEL: @fminnum_4f32( +; CHECK-NEXT: [[A0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[A1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[A2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[A3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[B0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[B1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[B2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[B3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[FMINNUM0:%.*]] = call float @llvm.minnum.f32(float [[A0]], float [[B0]]) +; CHECK-NEXT: [[FMINNUM1:%.*]] = call float @llvm.minnum.f32(float [[A1]], float [[B1]]) +; CHECK-NEXT: [[FMINNUM2:%.*]] = call float @llvm.minnum.f32(float [[A2]], float [[B2]]) +; CHECK-NEXT: [[FMINNUM3:%.*]] = call float @llvm.minnum.f32(float [[A3]], float [[B3]]) +; CHECK-NEXT: store float [[FMINNUM0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 +; CHECK-NEXT: store float [[FMINNUM1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; CHECK-NEXT: store float [[FMINNUM2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 +; CHECK-NEXT: store float [[FMINNUM3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; CHECK-NEXT: ret void +; + %a0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 + %a1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 + %a2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 + %a3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 + %b0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 + %b1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 + %b2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 + %b3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 + %fminnum0 = call float @llvm.minnum.f32(float %a0, float %b0) + %fminnum1 = call float @llvm.minnum.f32(float %a1, float %b1) + %fminnum2 = call float @llvm.minnum.f32(float %a2, float %b2) + %fminnum3 = call float @llvm.minnum.f32(float %a3, float %b3) + store float %fminnum0, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 + store float %fminnum1, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 + store float %fminnum2, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 + store float %fminnum3, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 + ret void +} + +define void @fminnum_8f32() #0 { +; CHECK-LABEL: @fminnum_8f32( +; CHECK-NEXT: [[A0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[A1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[A2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[A3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[A4:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 4), align 4 +; CHECK-NEXT: [[A5:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 5), align 4 +; CHECK-NEXT: [[A6:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 6), align 4 +; CHECK-NEXT: [[A7:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 7), align 4 +; CHECK-NEXT: [[B0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[B1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[B2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[B3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[B4:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 4), align 4 +; CHECK-NEXT: [[B5:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 5), align 4 +; CHECK-NEXT: [[B6:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 6), align 4 +; CHECK-NEXT: [[B7:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 7), align 4 +; CHECK-NEXT: [[FMINNUM0:%.*]] = call float @llvm.minnum.f32(float [[A0]], float [[B0]]) +; CHECK-NEXT: [[FMINNUM1:%.*]] = call float @llvm.minnum.f32(float [[A1]], float [[B1]]) +; CHECK-NEXT: [[FMINNUM2:%.*]] = call float @llvm.minnum.f32(float [[A2]], float [[B2]]) +; CHECK-NEXT: [[FMINNUM3:%.*]] = call float @llvm.minnum.f32(float [[A3]], float [[B3]]) +; CHECK-NEXT: [[FMINNUM4:%.*]] = call float @llvm.minnum.f32(float [[A4]], float [[B4]]) +; CHECK-NEXT: [[FMINNUM5:%.*]] = call float @llvm.minnum.f32(float [[A5]], float [[B5]]) +; CHECK-NEXT: [[FMINNUM6:%.*]] = call float @llvm.minnum.f32(float [[A6]], float [[B6]]) +; CHECK-NEXT: [[FMINNUM7:%.*]] = call float @llvm.minnum.f32(float [[A7]], float [[B7]]) +; CHECK-NEXT: store float [[FMINNUM0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 +; CHECK-NEXT: store float [[FMINNUM1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; CHECK-NEXT: store float [[FMINNUM2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 +; CHECK-NEXT: store float [[FMINNUM3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; CHECK-NEXT: store float [[FMINNUM4]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 4 +; CHECK-NEXT: store float [[FMINNUM5]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 +; CHECK-NEXT: store float [[FMINNUM6]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 4 +; CHECK-NEXT: store float [[FMINNUM7]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 +; CHECK-NEXT: ret void +; + %a0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 + %a1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 + %a2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 + %a3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 + %a4 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 4), align 4 + %a5 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 5), align 4 + %a6 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 6), align 4 + %a7 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 7), align 4 + %b0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 + %b1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 + %b2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 + %b3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 + %b4 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 4), align 4 + %b5 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 5), align 4 + %b6 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 6), align 4 + %b7 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 7), align 4 + %fminnum0 = call float @llvm.minnum.f32(float %a0, float %b0) + %fminnum1 = call float @llvm.minnum.f32(float %a1, float %b1) + %fminnum2 = call float @llvm.minnum.f32(float %a2, float %b2) + %fminnum3 = call float @llvm.minnum.f32(float %a3, float %b3) + %fminnum4 = call float @llvm.minnum.f32(float %a4, float %b4) + %fminnum5 = call float @llvm.minnum.f32(float %a5, float %b5) + %fminnum6 = call float @llvm.minnum.f32(float %a6, float %b6) + %fminnum7 = call float @llvm.minnum.f32(float %a7, float %b7) + store float %fminnum0, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 + store float %fminnum1, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 + store float %fminnum2, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 + store float %fminnum3, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 + store float %fminnum4, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 4 + store float %fminnum5, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 + store float %fminnum6, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 4 + store float %fminnum7, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 + ret void +} + +define void @fminnum_16f32() #0 { +; CHECK-LABEL: @fminnum_16f32( +; CHECK-NEXT: [[A0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[A1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[A2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[A3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[A4:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 4), align 4 +; CHECK-NEXT: [[A5:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 5), align 4 +; CHECK-NEXT: [[A6:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 6), align 4 +; CHECK-NEXT: [[A7:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 7), align 4 +; CHECK-NEXT: [[A8:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 8), align 4 +; CHECK-NEXT: [[A9:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 9), align 4 +; CHECK-NEXT: [[A10:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 10), align 4 +; CHECK-NEXT: [[A11:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 11), align 4 +; CHECK-NEXT: [[A12:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 12), align 4 +; CHECK-NEXT: [[A13:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 13), align 4 +; CHECK-NEXT: [[A14:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 14), align 4 +; CHECK-NEXT: [[A15:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 15), align 4 +; CHECK-NEXT: [[B0:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 +; CHECK-NEXT: [[B1:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 +; CHECK-NEXT: [[B2:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 +; CHECK-NEXT: [[B3:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 +; CHECK-NEXT: [[B4:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 4), align 4 +; CHECK-NEXT: [[B5:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 5), align 4 +; CHECK-NEXT: [[B6:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 6), align 4 +; CHECK-NEXT: [[B7:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 7), align 4 +; CHECK-NEXT: [[B8:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 8), align 4 +; CHECK-NEXT: [[B9:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 9), align 4 +; CHECK-NEXT: [[B10:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 10), align 4 +; CHECK-NEXT: [[B11:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 11), align 4 +; CHECK-NEXT: [[B12:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 12), align 4 +; CHECK-NEXT: [[B13:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 13), align 4 +; CHECK-NEXT: [[B14:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 14), align 4 +; CHECK-NEXT: [[B15:%.*]] = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 15), align 4 +; CHECK-NEXT: [[FMINNUM0:%.*]] = call float @llvm.minnum.f32(float [[A0]], float [[B0]]) +; CHECK-NEXT: [[FMINNUM1:%.*]] = call float @llvm.minnum.f32(float [[A1]], float [[B1]]) +; CHECK-NEXT: [[FMINNUM2:%.*]] = call float @llvm.minnum.f32(float [[A2]], float [[B2]]) +; CHECK-NEXT: [[FMINNUM3:%.*]] = call float @llvm.minnum.f32(float [[A3]], float [[B3]]) +; CHECK-NEXT: [[FMINNUM4:%.*]] = call float @llvm.minnum.f32(float [[A4]], float [[B4]]) +; CHECK-NEXT: [[FMINNUM5:%.*]] = call float @llvm.minnum.f32(float [[A5]], float [[B5]]) +; CHECK-NEXT: [[FMINNUM6:%.*]] = call float @llvm.minnum.f32(float [[A6]], float [[B6]]) +; CHECK-NEXT: [[FMINNUM7:%.*]] = call float @llvm.minnum.f32(float [[A7]], float [[B7]]) +; CHECK-NEXT: [[FMINNUM8:%.*]] = call float @llvm.minnum.f32(float [[A8]], float [[B8]]) +; CHECK-NEXT: [[FMINNUM9:%.*]] = call float @llvm.minnum.f32(float [[A9]], float [[B9]]) +; CHECK-NEXT: [[FMINNUM10:%.*]] = call float @llvm.minnum.f32(float [[A10]], float [[B10]]) +; CHECK-NEXT: [[FMINNUM11:%.*]] = call float @llvm.minnum.f32(float [[A11]], float [[B11]]) +; CHECK-NEXT: [[FMINNUM12:%.*]] = call float @llvm.minnum.f32(float [[A12]], float [[B12]]) +; CHECK-NEXT: [[FMINNUM13:%.*]] = call float @llvm.minnum.f32(float [[A13]], float [[B13]]) +; CHECK-NEXT: [[FMINNUM14:%.*]] = call float @llvm.minnum.f32(float [[A14]], float [[B14]]) +; CHECK-NEXT: [[FMINNUM15:%.*]] = call float @llvm.minnum.f32(float [[A15]], float [[B15]]) +; CHECK-NEXT: store float [[FMINNUM0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 +; CHECK-NEXT: store float [[FMINNUM1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; CHECK-NEXT: store float [[FMINNUM2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 +; CHECK-NEXT: store float [[FMINNUM3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; CHECK-NEXT: store float [[FMINNUM4]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 4 +; CHECK-NEXT: store float [[FMINNUM5]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 +; CHECK-NEXT: store float [[FMINNUM6]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 4 +; CHECK-NEXT: store float [[FMINNUM7]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 +; CHECK-NEXT: store float [[FMINNUM8]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8), align 4 +; CHECK-NEXT: store float [[FMINNUM9]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9), align 4 +; CHECK-NEXT: store float [[FMINNUM10]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 4 +; CHECK-NEXT: store float [[FMINNUM11]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 +; CHECK-NEXT: store float [[FMINNUM12]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 4 +; CHECK-NEXT: store float [[FMINNUM13]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 +; CHECK-NEXT: store float [[FMINNUM14]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 4 +; CHECK-NEXT: store float [[FMINNUM15]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 +; CHECK-NEXT: ret void +; + %a0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 0), align 4 + %a1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 1), align 4 + %a2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 2), align 4 + %a3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 3), align 4 + %a4 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 4), align 4 + %a5 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 5), align 4 + %a6 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 6), align 4 + %a7 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 7), align 4 + %a8 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 8), align 4 + %a9 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 9), align 4 + %a10 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 10), align 4 + %a11 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 11), align 4 + %a12 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 12), align 4 + %a13 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 13), align 4 + %a14 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 14), align 4 + %a15 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcA32, i32 0, i64 15), align 4 + %b0 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 0), align 4 + %b1 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 1), align 4 + %b2 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 2), align 4 + %b3 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 3), align 4 + %b4 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 4), align 4 + %b5 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 5), align 4 + %b6 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 6), align 4 + %b7 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 7), align 4 + %b8 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 8), align 4 + %b9 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 9), align 4 + %b10 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 10), align 4 + %b11 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 11), align 4 + %b12 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 12), align 4 + %b13 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 13), align 4 + %b14 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 14), align 4 + %b15 = load float, float* getelementptr inbounds ([16 x float], [16 x float]* @srcB32, i32 0, i64 15), align 4 + %fminnum0 = call float @llvm.minnum.f32(float %a0 , float %b0 ) + %fminnum1 = call float @llvm.minnum.f32(float %a1 , float %b1 ) + %fminnum2 = call float @llvm.minnum.f32(float %a2 , float %b2 ) + %fminnum3 = call float @llvm.minnum.f32(float %a3 , float %b3 ) + %fminnum4 = call float @llvm.minnum.f32(float %a4 , float %b4 ) + %fminnum5 = call float @llvm.minnum.f32(float %a5 , float %b5 ) + %fminnum6 = call float @llvm.minnum.f32(float %a6 , float %b6 ) + %fminnum7 = call float @llvm.minnum.f32(float %a7 , float %b7 ) + %fminnum8 = call float @llvm.minnum.f32(float %a8 , float %b8 ) + %fminnum9 = call float @llvm.minnum.f32(float %a9 , float %b9 ) + %fminnum10 = call float @llvm.minnum.f32(float %a10, float %b10) + %fminnum11 = call float @llvm.minnum.f32(float %a11, float %b11) + %fminnum12 = call float @llvm.minnum.f32(float %a12, float %b12) + %fminnum13 = call float @llvm.minnum.f32(float %a13, float %b13) + %fminnum14 = call float @llvm.minnum.f32(float %a14, float %b14) + %fminnum15 = call float @llvm.minnum.f32(float %a15, float %b15) + store float %fminnum0 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 4 + store float %fminnum1 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 + store float %fminnum2 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 4 + store float %fminnum3 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 + store float %fminnum4 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 4 + store float %fminnum5 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 + store float %fminnum6 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 4 + store float %fminnum7 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 + store float %fminnum8 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8), align 4 + store float %fminnum9 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9), align 4 + store float %fminnum10, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 4 + store float %fminnum11, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 + store float %fminnum12, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 4 + store float %fminnum13, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 + store float %fminnum14, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 4 + store float %fminnum15, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 + ret void +} + +attributes #0 = { nounwind }