From cfef627b1f2e7a06945d5565db170f88963147fb Mon Sep 17 00:00:00 2001 From: Simon Pilgrim Date: Mon, 10 Oct 2016 14:28:06 +0000 Subject: [PATCH] [SLPVectorizer][X86] Add 512-bit sitofp/uitofp tests llvm-svn: 283756 --- .../Transforms/SLPVectorizer/X86/sitofp.ll | 582 +++++++++++++++- .../Transforms/SLPVectorizer/X86/uitofp.ll | 648 +++++++++++++++++- 2 files changed, 1214 insertions(+), 16 deletions(-) diff --git a/llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll b/llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll index 92e72199162e..ddbcde5ce650 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll @@ -69,6 +69,61 @@ define void @sitofp_4i64_4f64() #0 { ret void } +define void @sitofp_8i64_8f64() #0 { +; CHECK-LABEL: @sitofp_8i64_8f64( +; CHECK-NEXT: [[LD0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 +; CHECK-NEXT: [[LD1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[LD2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 +; CHECK-NEXT: [[LD3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 +; CHECK-NEXT: [[LD4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 +; CHECK-NEXT: [[LD5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 +; CHECK-NEXT: [[LD6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 +; CHECK-NEXT: [[LD7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 +; CHECK-NEXT: [[CVT0:%.*]] = sitofp i64 [[LD0]] to double +; CHECK-NEXT: [[CVT1:%.*]] = sitofp i64 [[LD1]] to double +; CHECK-NEXT: [[CVT2:%.*]] = sitofp i64 [[LD2]] to double +; CHECK-NEXT: [[CVT3:%.*]] = sitofp i64 [[LD3]] to double +; CHECK-NEXT: [[CVT4:%.*]] = sitofp i64 [[LD4]] to double +; CHECK-NEXT: [[CVT5:%.*]] = sitofp i64 [[LD5]] to double +; CHECK-NEXT: [[CVT6:%.*]] = sitofp i64 [[LD6]] to double +; CHECK-NEXT: [[CVT7:%.*]] = sitofp i64 [[LD7]] to double +; CHECK-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; CHECK-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; CHECK-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; CHECK-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; CHECK-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; CHECK-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; CHECK-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; CHECK-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; CHECK-NEXT: ret void +; + %ld0 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 + %ld1 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 + %ld2 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 + %ld3 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 + %ld4 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 + %ld5 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 + %ld6 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 + %ld7 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 + %cvt0 = sitofp i64 %ld0 to double + %cvt1 = sitofp i64 %ld1 to double + %cvt2 = sitofp i64 %ld2 to double + %cvt3 = sitofp i64 %ld3 to double + %cvt4 = sitofp i64 %ld4 to double + %cvt5 = sitofp i64 %ld5 to double + %cvt6 = sitofp i64 %ld6 to double + %cvt7 = sitofp i64 %ld7 to double + store double %cvt0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 + store double %cvt1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %cvt2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 + store double %cvt3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + store double %cvt4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 + store double %cvt5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 + store double %cvt6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 + store double %cvt7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 + ret void +} + define void @sitofp_2i32_2f64() #0 { ; CHECK-LABEL: @sitofp_2i32_2f64( ; CHECK-NEXT: [[LD0:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 0), align 64 @@ -125,6 +180,76 @@ define void @sitofp_4i32_4f64() #0 { ret void } +define void @sitofp_8i32_8f64() #0 { +; SSE-LABEL: @sitofp_8i32_8f64( +; SSE-NEXT: [[LD0:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 0), align 64 +; SSE-NEXT: [[LD1:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 1), align 4 +; SSE-NEXT: [[LD2:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 2), align 8 +; SSE-NEXT: [[LD3:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 3), align 4 +; SSE-NEXT: [[LD4:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4), align 16 +; SSE-NEXT: [[LD5:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 5), align 4 +; SSE-NEXT: [[LD6:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 6), align 8 +; SSE-NEXT: [[LD7:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 7), align 4 +; SSE-NEXT: [[CVT0:%.*]] = sitofp i32 [[LD0]] to double +; SSE-NEXT: [[CVT1:%.*]] = sitofp i32 [[LD1]] to double +; SSE-NEXT: [[CVT2:%.*]] = sitofp i32 [[LD2]] to double +; SSE-NEXT: [[CVT3:%.*]] = sitofp i32 [[LD3]] to double +; SSE-NEXT: [[CVT4:%.*]] = sitofp i32 [[LD4]] to double +; SSE-NEXT: [[CVT5:%.*]] = sitofp i32 [[LD5]] to double +; SSE-NEXT: [[CVT6:%.*]] = sitofp i32 [[LD6]] to double +; SSE-NEXT: [[CVT7:%.*]] = sitofp i32 [[LD7]] to double +; SSE-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; SSE-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; SSE-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; SSE-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; SSE-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; SSE-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; SSE-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; SSE-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @sitofp_8i32_8f64( +; AVX256-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @src32 to <4 x i32>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 16 +; AVX256-NEXT: [[TMP3:%.*]] = sitofp <4 x i32> [[TMP1]] to <4 x double> +; AVX256-NEXT: [[TMP4:%.*]] = sitofp <4 x i32> [[TMP2]] to <4 x double> +; AVX256-NEXT: store <4 x double> [[TMP3]], <4 x double>* bitcast ([8 x double]* @dst64 to <4 x double>*), align 64 +; AVX256-NEXT: store <4 x double> [[TMP4]], <4 x double>* bitcast (double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4) to <4 x double>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @sitofp_8i32_8f64( +; AVX512-NEXT: [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* bitcast ([16 x i32]* @src32 to <8 x i32>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = sitofp <8 x i32> [[TMP1]] to <8 x double> +; AVX512-NEXT: store <8 x double> [[TMP2]], <8 x double>* bitcast ([8 x double]* @dst64 to <8 x double>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 0), align 64 + %ld1 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 1), align 4 + %ld2 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 2), align 8 + %ld3 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 3), align 4 + %ld4 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4), align 16 + %ld5 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 5), align 4 + %ld6 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 6), align 8 + %ld7 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 7), align 4 + %cvt0 = sitofp i32 %ld0 to double + %cvt1 = sitofp i32 %ld1 to double + %cvt2 = sitofp i32 %ld2 to double + %cvt3 = sitofp i32 %ld3 to double + %cvt4 = sitofp i32 %ld4 to double + %cvt5 = sitofp i32 %ld5 to double + %cvt6 = sitofp i32 %ld6 to double + %cvt7 = sitofp i32 %ld7 to double + store double %cvt0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 + store double %cvt1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %cvt2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 + store double %cvt3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + store double %cvt4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 + store double %cvt5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 + store double %cvt6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 + store double %cvt7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 + ret void +} + define void @sitofp_2i16_2f64() #0 { ; CHECK-LABEL: @sitofp_2i16_2f64( ; CHECK-NEXT: [[LD0:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0), align 64 @@ -181,6 +306,76 @@ define void @sitofp_4i16_4f64() #0 { ret void } +define void @sitofp_8i16_8f64() #0 { +; SSE-LABEL: @sitofp_8i16_8f64( +; SSE-NEXT: [[LD0:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0), align 64 +; SSE-NEXT: [[LD1:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1), align 2 +; SSE-NEXT: [[LD2:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2), align 4 +; SSE-NEXT: [[LD3:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3), align 2 +; SSE-NEXT: [[LD4:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4), align 8 +; SSE-NEXT: [[LD5:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5), align 2 +; SSE-NEXT: [[LD6:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6), align 4 +; SSE-NEXT: [[LD7:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7), align 2 +; SSE-NEXT: [[CVT0:%.*]] = sitofp i16 [[LD0]] to double +; SSE-NEXT: [[CVT1:%.*]] = sitofp i16 [[LD1]] to double +; SSE-NEXT: [[CVT2:%.*]] = sitofp i16 [[LD2]] to double +; SSE-NEXT: [[CVT3:%.*]] = sitofp i16 [[LD3]] to double +; SSE-NEXT: [[CVT4:%.*]] = sitofp i16 [[LD4]] to double +; SSE-NEXT: [[CVT5:%.*]] = sitofp i16 [[LD5]] to double +; SSE-NEXT: [[CVT6:%.*]] = sitofp i16 [[LD6]] to double +; SSE-NEXT: [[CVT7:%.*]] = sitofp i16 [[LD7]] to double +; SSE-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; SSE-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; SSE-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; SSE-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; SSE-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; SSE-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; SSE-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; SSE-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @sitofp_8i16_8f64( +; AVX256-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* bitcast ([32 x i16]* @src16 to <4 x i16>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4) to <4 x i16>*), align 8 +; AVX256-NEXT: [[TMP3:%.*]] = sitofp <4 x i16> [[TMP1]] to <4 x double> +; AVX256-NEXT: [[TMP4:%.*]] = sitofp <4 x i16> [[TMP2]] to <4 x double> +; AVX256-NEXT: store <4 x double> [[TMP3]], <4 x double>* bitcast ([8 x double]* @dst64 to <4 x double>*), align 64 +; AVX256-NEXT: store <4 x double> [[TMP4]], <4 x double>* bitcast (double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4) to <4 x double>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @sitofp_8i16_8f64( +; AVX512-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @src16 to <8 x i16>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = sitofp <8 x i16> [[TMP1]] to <8 x double> +; AVX512-NEXT: store <8 x double> [[TMP2]], <8 x double>* bitcast ([8 x double]* @dst64 to <8 x double>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0), align 64 + %ld1 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1), align 2 + %ld2 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2), align 4 + %ld3 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3), align 2 + %ld4 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4), align 8 + %ld5 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5), align 2 + %ld6 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6), align 4 + %ld7 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7), align 2 + %cvt0 = sitofp i16 %ld0 to double + %cvt1 = sitofp i16 %ld1 to double + %cvt2 = sitofp i16 %ld2 to double + %cvt3 = sitofp i16 %ld3 to double + %cvt4 = sitofp i16 %ld4 to double + %cvt5 = sitofp i16 %ld5 to double + %cvt6 = sitofp i16 %ld6 to double + %cvt7 = sitofp i16 %ld7 to double + store double %cvt0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 + store double %cvt1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %cvt2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 + store double %cvt3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + store double %cvt4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 + store double %cvt5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 + store double %cvt6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 + store double %cvt7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 + ret void +} + define void @sitofp_2i8_2f64() #0 { ; CHECK-LABEL: @sitofp_2i8_2f64( ; CHECK-NEXT: [[LD0:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 0), align 64 @@ -237,6 +432,76 @@ define void @sitofp_4i8_4f64() #0 { ret void } +define void @sitofp_8i8_8f64() #0 { +; SSE-LABEL: @sitofp_8i8_8f64( +; SSE-NEXT: [[LD0:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 0), align 64 +; SSE-NEXT: [[LD1:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 1), align 1 +; SSE-NEXT: [[LD2:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 2), align 2 +; SSE-NEXT: [[LD3:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 3), align 1 +; SSE-NEXT: [[LD4:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4), align 4 +; SSE-NEXT: [[LD5:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 5), align 1 +; SSE-NEXT: [[LD6:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 6), align 2 +; SSE-NEXT: [[LD7:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 7), align 1 +; SSE-NEXT: [[CVT0:%.*]] = sitofp i8 [[LD0]] to double +; SSE-NEXT: [[CVT1:%.*]] = sitofp i8 [[LD1]] to double +; SSE-NEXT: [[CVT2:%.*]] = sitofp i8 [[LD2]] to double +; SSE-NEXT: [[CVT3:%.*]] = sitofp i8 [[LD3]] to double +; SSE-NEXT: [[CVT4:%.*]] = sitofp i8 [[LD4]] to double +; SSE-NEXT: [[CVT5:%.*]] = sitofp i8 [[LD5]] to double +; SSE-NEXT: [[CVT6:%.*]] = sitofp i8 [[LD6]] to double +; SSE-NEXT: [[CVT7:%.*]] = sitofp i8 [[LD7]] to double +; SSE-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; SSE-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; SSE-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; SSE-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; SSE-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; SSE-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; SSE-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; SSE-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @sitofp_8i8_8f64( +; AVX256-NEXT: [[TMP1:%.*]] = load <4 x i8>, <4 x i8>* bitcast ([64 x i8]* @src8 to <4 x i8>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4) to <4 x i8>*), align 4 +; AVX256-NEXT: [[TMP3:%.*]] = sitofp <4 x i8> [[TMP1]] to <4 x double> +; AVX256-NEXT: [[TMP4:%.*]] = sitofp <4 x i8> [[TMP2]] to <4 x double> +; AVX256-NEXT: store <4 x double> [[TMP3]], <4 x double>* bitcast ([8 x double]* @dst64 to <4 x double>*), align 64 +; AVX256-NEXT: store <4 x double> [[TMP4]], <4 x double>* bitcast (double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4) to <4 x double>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @sitofp_8i8_8f64( +; AVX512-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* bitcast ([64 x i8]* @src8 to <8 x i8>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = sitofp <8 x i8> [[TMP1]] to <8 x double> +; AVX512-NEXT: store <8 x double> [[TMP2]], <8 x double>* bitcast ([8 x double]* @dst64 to <8 x double>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 0), align 64 + %ld1 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 1), align 1 + %ld2 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 2), align 2 + %ld3 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 3), align 1 + %ld4 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4), align 4 + %ld5 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 5), align 1 + %ld6 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 6), align 2 + %ld7 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 7), align 1 + %cvt0 = sitofp i8 %ld0 to double + %cvt1 = sitofp i8 %ld1 to double + %cvt2 = sitofp i8 %ld2 to double + %cvt3 = sitofp i8 %ld3 to double + %cvt4 = sitofp i8 %ld4 to double + %cvt5 = sitofp i8 %ld5 to double + %cvt6 = sitofp i8 %ld6 to double + %cvt7 = sitofp i8 %ld7 to double + store double %cvt0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 + store double %cvt1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %cvt2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 + store double %cvt3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + store double %cvt4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 + store double %cvt5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 + store double %cvt6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 + store double %cvt7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 + ret void +} + ; ; SITOFP to vXf32 ; @@ -291,6 +556,61 @@ define void @sitofp_4i64_4f32() #0 { ret void } +define void @sitofp_8i64_8f32() #0 { +; CHECK-LABEL: @sitofp_8i64_8f32( +; CHECK-NEXT: [[LD0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 +; CHECK-NEXT: [[LD1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 +; CHECK-NEXT: [[LD2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 +; CHECK-NEXT: [[LD3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 +; CHECK-NEXT: [[LD4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 +; CHECK-NEXT: [[LD5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 +; CHECK-NEXT: [[LD6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 +; CHECK-NEXT: [[LD7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 +; CHECK-NEXT: [[CVT0:%.*]] = sitofp i64 [[LD0]] to float +; CHECK-NEXT: [[CVT1:%.*]] = sitofp i64 [[LD1]] to float +; CHECK-NEXT: [[CVT2:%.*]] = sitofp i64 [[LD2]] to float +; CHECK-NEXT: [[CVT3:%.*]] = sitofp i64 [[LD3]] to float +; CHECK-NEXT: [[CVT4:%.*]] = sitofp i64 [[LD4]] to float +; CHECK-NEXT: [[CVT5:%.*]] = sitofp i64 [[LD5]] to float +; CHECK-NEXT: [[CVT6:%.*]] = sitofp i64 [[LD6]] to float +; CHECK-NEXT: [[CVT7:%.*]] = sitofp i64 [[LD7]] to float +; CHECK-NEXT: store float [[CVT0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 64 +; CHECK-NEXT: store float [[CVT1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; CHECK-NEXT: store float [[CVT2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 8 +; CHECK-NEXT: store float [[CVT3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; CHECK-NEXT: store float [[CVT4]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 16 +; CHECK-NEXT: store float [[CVT5]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 +; CHECK-NEXT: store float [[CVT6]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 8 +; CHECK-NEXT: store float [[CVT7]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 +; CHECK-NEXT: ret void +; + %ld0 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 + %ld1 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 + %ld2 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 + %ld3 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 + %ld4 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 + %ld5 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 + %ld6 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 + %ld7 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 + %cvt0 = sitofp i64 %ld0 to float + %cvt1 = sitofp i64 %ld1 to float + %cvt2 = sitofp i64 %ld2 to float + %cvt3 = sitofp i64 %ld3 to float + %cvt4 = sitofp i64 %ld4 to float + %cvt5 = sitofp i64 %ld5 to float + %cvt6 = sitofp i64 %ld6 to float + %cvt7 = sitofp i64 %ld7 to float + store float %cvt0, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 64 + store float %cvt1, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 + store float %cvt2, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 8 + store float %cvt3, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 + store float %cvt4, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 16 + store float %cvt5, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 + store float %cvt6, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 8 + store float %cvt7, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 + ret void +} + define void @sitofp_4i32_4f32() #0 { ; CHECK-LABEL: @sitofp_4i32_4f32( ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @src32 to <4 x i32>*), align 64 @@ -356,6 +676,88 @@ define void @sitofp_8i32_8f32() #0 { ret void } +define void @sitofp_16i32_16f32() #0 { +; SSE-LABEL: @sitofp_16i32_16f32( +; SSE-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @src32 to <4 x i32>*), align 64 +; SSE-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 16 +; SSE-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 8) to <4 x i32>*), align 32 +; SSE-NEXT: [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 12) to <4 x i32>*), align 16 +; SSE-NEXT: [[TMP5:%.*]] = sitofp <4 x i32> [[TMP1]] to <4 x float> +; SSE-NEXT: [[TMP6:%.*]] = sitofp <4 x i32> [[TMP2]] to <4 x float> +; SSE-NEXT: [[TMP7:%.*]] = sitofp <4 x i32> [[TMP3]] to <4 x float> +; SSE-NEXT: [[TMP8:%.*]] = sitofp <4 x i32> [[TMP4]] to <4 x float> +; SSE-NEXT: store <4 x float> [[TMP5]], <4 x float>* bitcast ([16 x float]* @dst32 to <4 x float>*), align 64 +; SSE-NEXT: store <4 x float> [[TMP6]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4) to <4 x float>*), align 16 +; SSE-NEXT: store <4 x float> [[TMP7]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <4 x float>*), align 32 +; SSE-NEXT: store <4 x float> [[TMP8]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12) to <4 x float>*), align 16 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @sitofp_16i32_16f32( +; AVX256-NEXT: [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* bitcast ([16 x i32]* @src32 to <8 x i32>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <8 x i32>, <8 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 8) to <8 x i32>*), align 32 +; AVX256-NEXT: [[TMP3:%.*]] = sitofp <8 x i32> [[TMP1]] to <8 x float> +; AVX256-NEXT: [[TMP4:%.*]] = sitofp <8 x i32> [[TMP2]] to <8 x float> +; AVX256-NEXT: store <8 x float> [[TMP3]], <8 x float>* bitcast ([16 x float]* @dst32 to <8 x float>*), align 64 +; AVX256-NEXT: store <8 x float> [[TMP4]], <8 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <8 x float>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @sitofp_16i32_16f32( +; AVX512-NEXT: [[TMP1:%.*]] = load <16 x i32>, <16 x i32>* bitcast ([16 x i32]* @src32 to <16 x i32>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = sitofp <16 x i32> [[TMP1]] to <16 x float> +; AVX512-NEXT: store <16 x float> [[TMP2]], <16 x float>* bitcast ([16 x float]* @dst32 to <16 x float>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 0 ), align 64 + %ld1 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 1 ), align 4 + %ld2 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 2 ), align 8 + %ld3 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 3 ), align 4 + %ld4 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4 ), align 16 + %ld5 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 5 ), align 4 + %ld6 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 6 ), align 8 + %ld7 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 7 ), align 4 + %ld8 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 8 ), align 32 + %ld9 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 9 ), align 4 + %ld10 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 10), align 8 + %ld11 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 11), align 4 + %ld12 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 12), align 16 + %ld13 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 13), align 4 + %ld14 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 14), align 8 + %ld15 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 15), align 4 + %cvt0 = sitofp i32 %ld0 to float + %cvt1 = sitofp i32 %ld1 to float + %cvt2 = sitofp i32 %ld2 to float + %cvt3 = sitofp i32 %ld3 to float + %cvt4 = sitofp i32 %ld4 to float + %cvt5 = sitofp i32 %ld5 to float + %cvt6 = sitofp i32 %ld6 to float + %cvt7 = sitofp i32 %ld7 to float + %cvt8 = sitofp i32 %ld8 to float + %cvt9 = sitofp i32 %ld9 to float + %cvt10 = sitofp i32 %ld10 to float + %cvt11 = sitofp i32 %ld11 to float + %cvt12 = sitofp i32 %ld12 to float + %cvt13 = sitofp i32 %ld13 to float + %cvt14 = sitofp i32 %ld14 to float + %cvt15 = sitofp i32 %ld15 to float + store float %cvt0 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0 ), align 64 + store float %cvt1 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1 ), align 4 + store float %cvt2 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2 ), align 8 + store float %cvt3 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3 ), align 4 + store float %cvt4 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4 ), align 16 + store float %cvt5 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5 ), align 4 + store float %cvt6 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6 ), align 8 + store float %cvt7 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7 ), align 4 + store float %cvt8 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8 ), align 32 + store float %cvt9 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9 ), align 4 + store float %cvt10, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 8 + store float %cvt11, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 + store float %cvt12, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 16 + store float %cvt13, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 + store float %cvt14, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 8 + store float %cvt15, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 + ret void +} + define void @sitofp_4i16_4f32() #0 { ; CHECK-LABEL: @sitofp_4i16_4f32( ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* bitcast ([32 x i16]* @src16 to <4 x i16>*), align 64 @@ -381,7 +783,7 @@ define void @sitofp_4i16_4f32() #0 { define void @sitofp_8i16_8f32() #0 { ; SSE-LABEL: @sitofp_8i16_8f32( ; SSE-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* bitcast ([32 x i16]* @src16 to <4 x i16>*), align 64 -; SSE-NEXT: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4) to <4 x i16>*), align 4 +; SSE-NEXT: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4) to <4 x i16>*), align 8 ; SSE-NEXT: [[TMP3:%.*]] = sitofp <4 x i16> [[TMP1]] to <4 x float> ; SSE-NEXT: [[TMP4:%.*]] = sitofp <4 x i16> [[TMP2]] to <4 x float> ; SSE-NEXT: store <4 x float> [[TMP3]], <4 x float>* bitcast ([16 x float]* @dst32 to <4 x float>*), align 64 @@ -395,13 +797,13 @@ define void @sitofp_8i16_8f32() #0 { ; AVX-NEXT: ret void ; %ld0 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0), align 64 - %ld1 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1), align 1 - %ld2 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2), align 2 - %ld3 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3), align 1 - %ld4 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4), align 4 - %ld5 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5), align 1 - %ld6 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6), align 2 - %ld7 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7), align 1 + %ld1 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1), align 2 + %ld2 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2), align 4 + %ld3 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3), align 2 + %ld4 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4), align 8 + %ld5 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5), align 2 + %ld6 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6), align 4 + %ld7 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7), align 2 %cvt0 = sitofp i16 %ld0 to float %cvt1 = sitofp i16 %ld1 to float %cvt2 = sitofp i16 %ld2 to float @@ -421,6 +823,88 @@ define void @sitofp_8i16_8f32() #0 { ret void } +define void @sitofp_16i16_16f32() #0 { +; SSE-LABEL: @sitofp_16i16_16f32( +; SSE-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* bitcast ([32 x i16]* @src16 to <4 x i16>*), align 64 +; SSE-NEXT: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4) to <4 x i16>*), align 8 +; SSE-NEXT: [[TMP3:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 8) to <4 x i16>*), align 16 +; SSE-NEXT: [[TMP4:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 12) to <4 x i16>*), align 8 +; SSE-NEXT: [[TMP5:%.*]] = sitofp <4 x i16> [[TMP1]] to <4 x float> +; SSE-NEXT: [[TMP6:%.*]] = sitofp <4 x i16> [[TMP2]] to <4 x float> +; SSE-NEXT: [[TMP7:%.*]] = sitofp <4 x i16> [[TMP3]] to <4 x float> +; SSE-NEXT: [[TMP8:%.*]] = sitofp <4 x i16> [[TMP4]] to <4 x float> +; SSE-NEXT: store <4 x float> [[TMP5]], <4 x float>* bitcast ([16 x float]* @dst32 to <4 x float>*), align 64 +; SSE-NEXT: store <4 x float> [[TMP6]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4) to <4 x float>*), align 16 +; SSE-NEXT: store <4 x float> [[TMP7]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <4 x float>*), align 32 +; SSE-NEXT: store <4 x float> [[TMP8]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12) to <4 x float>*), align 16 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @sitofp_16i16_16f32( +; AVX256-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @src16 to <8 x i16>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 8) to <8 x i16>*), align 16 +; AVX256-NEXT: [[TMP3:%.*]] = sitofp <8 x i16> [[TMP1]] to <8 x float> +; AVX256-NEXT: [[TMP4:%.*]] = sitofp <8 x i16> [[TMP2]] to <8 x float> +; AVX256-NEXT: store <8 x float> [[TMP3]], <8 x float>* bitcast ([16 x float]* @dst32 to <8 x float>*), align 64 +; AVX256-NEXT: store <8 x float> [[TMP4]], <8 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <8 x float>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @sitofp_16i16_16f32( +; AVX512-NEXT: [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @src16 to <16 x i16>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = sitofp <16 x i16> [[TMP1]] to <16 x float> +; AVX512-NEXT: store <16 x float> [[TMP2]], <16 x float>* bitcast ([16 x float]* @dst32 to <16 x float>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0 ), align 64 + %ld1 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1 ), align 2 + %ld2 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2 ), align 4 + %ld3 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3 ), align 2 + %ld4 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4 ), align 8 + %ld5 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5 ), align 2 + %ld6 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6 ), align 4 + %ld7 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7 ), align 2 + %ld8 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 8 ), align 16 + %ld9 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 9 ), align 2 + %ld10 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 10), align 4 + %ld11 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 11), align 2 + %ld12 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 12), align 8 + %ld13 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 13), align 2 + %ld14 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 14), align 4 + %ld15 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 15), align 2 + %cvt0 = sitofp i16 %ld0 to float + %cvt1 = sitofp i16 %ld1 to float + %cvt2 = sitofp i16 %ld2 to float + %cvt3 = sitofp i16 %ld3 to float + %cvt4 = sitofp i16 %ld4 to float + %cvt5 = sitofp i16 %ld5 to float + %cvt6 = sitofp i16 %ld6 to float + %cvt7 = sitofp i16 %ld7 to float + %cvt8 = sitofp i16 %ld8 to float + %cvt9 = sitofp i16 %ld9 to float + %cvt10 = sitofp i16 %ld10 to float + %cvt11 = sitofp i16 %ld11 to float + %cvt12 = sitofp i16 %ld12 to float + %cvt13 = sitofp i16 %ld13 to float + %cvt14 = sitofp i16 %ld14 to float + %cvt15 = sitofp i16 %ld15 to float + store float %cvt0 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0 ), align 64 + store float %cvt1 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1 ), align 4 + store float %cvt2 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2 ), align 8 + store float %cvt3 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3 ), align 4 + store float %cvt4 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4 ), align 16 + store float %cvt5 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5 ), align 4 + store float %cvt6 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6 ), align 8 + store float %cvt7 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7 ), align 4 + store float %cvt8 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8 ), align 32 + store float %cvt9 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9 ), align 4 + store float %cvt10, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 8 + store float %cvt11, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 + store float %cvt12, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 16 + store float %cvt13, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 + store float %cvt14, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 8 + store float %cvt15, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 + ret void +} + define void @sitofp_4i8_4f32() #0 { ; CHECK-LABEL: @sitofp_4i8_4f32( ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i8>, <4 x i8>* bitcast ([64 x i8]* @src8 to <4 x i8>*), align 64 @@ -486,4 +970,86 @@ define void @sitofp_8i8_8f32() #0 { ret void } +define void @sitofp_16i8_16f32() #0 { +; SSE-LABEL: @sitofp_16i8_16f32( +; SSE-NEXT: [[TMP1:%.*]] = load <4 x i8>, <4 x i8>* bitcast ([64 x i8]* @src8 to <4 x i8>*), align 64 +; SSE-NEXT: [[TMP2:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4) to <4 x i8>*), align 4 +; SSE-NEXT: [[TMP3:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 8) to <4 x i8>*), align 8 +; SSE-NEXT: [[TMP4:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 12) to <4 x i8>*), align 4 +; SSE-NEXT: [[TMP5:%.*]] = sitofp <4 x i8> [[TMP1]] to <4 x float> +; SSE-NEXT: [[TMP6:%.*]] = sitofp <4 x i8> [[TMP2]] to <4 x float> +; SSE-NEXT: [[TMP7:%.*]] = sitofp <4 x i8> [[TMP3]] to <4 x float> +; SSE-NEXT: [[TMP8:%.*]] = sitofp <4 x i8> [[TMP4]] to <4 x float> +; SSE-NEXT: store <4 x float> [[TMP5]], <4 x float>* bitcast ([16 x float]* @dst32 to <4 x float>*), align 64 +; SSE-NEXT: store <4 x float> [[TMP6]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4) to <4 x float>*), align 16 +; SSE-NEXT: store <4 x float> [[TMP7]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <4 x float>*), align 32 +; SSE-NEXT: store <4 x float> [[TMP8]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12) to <4 x float>*), align 16 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @sitofp_16i8_16f32( +; AVX256-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* bitcast ([64 x i8]* @src8 to <8 x i8>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <8 x i8>, <8 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 8) to <8 x i8>*), align 8 +; AVX256-NEXT: [[TMP3:%.*]] = sitofp <8 x i8> [[TMP1]] to <8 x float> +; AVX256-NEXT: [[TMP4:%.*]] = sitofp <8 x i8> [[TMP2]] to <8 x float> +; AVX256-NEXT: store <8 x float> [[TMP3]], <8 x float>* bitcast ([16 x float]* @dst32 to <8 x float>*), align 64 +; AVX256-NEXT: store <8 x float> [[TMP4]], <8 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <8 x float>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @sitofp_16i8_16f32( +; AVX512-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @src8 to <16 x i8>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = sitofp <16 x i8> [[TMP1]] to <16 x float> +; AVX512-NEXT: store <16 x float> [[TMP2]], <16 x float>* bitcast ([16 x float]* @dst32 to <16 x float>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 0 ), align 64 + %ld1 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 1 ), align 1 + %ld2 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 2 ), align 2 + %ld3 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 3 ), align 1 + %ld4 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4 ), align 4 + %ld5 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 5 ), align 1 + %ld6 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 6 ), align 2 + %ld7 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 7 ), align 1 + %ld8 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 8 ), align 8 + %ld9 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 9 ), align 1 + %ld10 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 10), align 2 + %ld11 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 11), align 1 + %ld12 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 12), align 4 + %ld13 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 13), align 1 + %ld14 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 14), align 2 + %ld15 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 15), align 1 + %cvt0 = sitofp i8 %ld0 to float + %cvt1 = sitofp i8 %ld1 to float + %cvt2 = sitofp i8 %ld2 to float + %cvt3 = sitofp i8 %ld3 to float + %cvt4 = sitofp i8 %ld4 to float + %cvt5 = sitofp i8 %ld5 to float + %cvt6 = sitofp i8 %ld6 to float + %cvt7 = sitofp i8 %ld7 to float + %cvt8 = sitofp i8 %ld8 to float + %cvt9 = sitofp i8 %ld9 to float + %cvt10 = sitofp i8 %ld10 to float + %cvt11 = sitofp i8 %ld11 to float + %cvt12 = sitofp i8 %ld12 to float + %cvt13 = sitofp i8 %ld13 to float + %cvt14 = sitofp i8 %ld14 to float + %cvt15 = sitofp i8 %ld15 to float + store float %cvt0 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0 ), align 64 + store float %cvt1 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1 ), align 4 + store float %cvt2 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2 ), align 8 + store float %cvt3 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3 ), align 4 + store float %cvt4 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4 ), align 16 + store float %cvt5 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5 ), align 4 + store float %cvt6 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6 ), align 8 + store float %cvt7 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7 ), align 4 + store float %cvt8 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8 ), align 32 + store float %cvt9 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9 ), align 4 + store float %cvt10, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 8 + store float %cvt11, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 + store float %cvt12, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 16 + store float %cvt13, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 + store float %cvt14, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 8 + store float %cvt15, 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/uitofp.ll b/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll index de4f4635da7b..ff63fe35bddf 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll @@ -105,6 +105,94 @@ define void @uitofp_4i64_4f64() #0 { ret void } +define void @uitofp_8i64_8f64() #0 { +; SSE-LABEL: @uitofp_8i64_8f64( +; SSE-NEXT: [[LD0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 +; SSE-NEXT: [[LD1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 +; SSE-NEXT: [[LD2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 +; SSE-NEXT: [[LD3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 +; SSE-NEXT: [[LD4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 +; SSE-NEXT: [[LD5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 +; SSE-NEXT: [[LD6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 +; SSE-NEXT: [[LD7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 +; SSE-NEXT: [[CVT0:%.*]] = uitofp i64 [[LD0]] to double +; SSE-NEXT: [[CVT1:%.*]] = uitofp i64 [[LD1]] to double +; SSE-NEXT: [[CVT2:%.*]] = uitofp i64 [[LD2]] to double +; SSE-NEXT: [[CVT3:%.*]] = uitofp i64 [[LD3]] to double +; SSE-NEXT: [[CVT4:%.*]] = uitofp i64 [[LD4]] to double +; SSE-NEXT: [[CVT5:%.*]] = uitofp i64 [[LD5]] to double +; SSE-NEXT: [[CVT6:%.*]] = uitofp i64 [[LD6]] to double +; SSE-NEXT: [[CVT7:%.*]] = uitofp i64 [[LD7]] to double +; SSE-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; SSE-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; SSE-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; SSE-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; SSE-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; SSE-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; SSE-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; SSE-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @uitofp_8i64_8f64( +; AVX256-NEXT: [[LD0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 +; AVX256-NEXT: [[LD1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 +; AVX256-NEXT: [[LD2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 +; AVX256-NEXT: [[LD3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 +; AVX256-NEXT: [[LD4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 +; AVX256-NEXT: [[LD5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 +; AVX256-NEXT: [[LD6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 +; AVX256-NEXT: [[LD7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 +; AVX256-NEXT: [[CVT0:%.*]] = uitofp i64 [[LD0]] to double +; AVX256-NEXT: [[CVT1:%.*]] = uitofp i64 [[LD1]] to double +; AVX256-NEXT: [[CVT2:%.*]] = uitofp i64 [[LD2]] to double +; AVX256-NEXT: [[CVT3:%.*]] = uitofp i64 [[LD3]] to double +; AVX256-NEXT: [[CVT4:%.*]] = uitofp i64 [[LD4]] to double +; AVX256-NEXT: [[CVT5:%.*]] = uitofp i64 [[LD5]] to double +; AVX256-NEXT: [[CVT6:%.*]] = uitofp i64 [[LD6]] to double +; AVX256-NEXT: [[CVT7:%.*]] = uitofp i64 [[LD7]] to double +; AVX256-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; AVX256-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; AVX256-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; AVX256-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; AVX256-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; AVX256-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; AVX256-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; AVX256-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @uitofp_8i64_8f64( +; AVX512-NEXT: [[TMP1:%.*]] = load <8 x i64>, <8 x i64>* bitcast ([8 x i64]* @src64 to <8 x i64>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = uitofp <8 x i64> [[TMP1]] to <8 x double> +; AVX512-NEXT: store <8 x double> [[TMP2]], <8 x double>* bitcast ([8 x double]* @dst64 to <8 x double>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 + %ld1 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 + %ld2 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 + %ld3 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 + %ld4 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 + %ld5 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 + %ld6 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 + %ld7 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 + %cvt0 = uitofp i64 %ld0 to double + %cvt1 = uitofp i64 %ld1 to double + %cvt2 = uitofp i64 %ld2 to double + %cvt3 = uitofp i64 %ld3 to double + %cvt4 = uitofp i64 %ld4 to double + %cvt5 = uitofp i64 %ld5 to double + %cvt6 = uitofp i64 %ld6 to double + %cvt7 = uitofp i64 %ld7 to double + store double %cvt0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 + store double %cvt1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %cvt2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 + store double %cvt3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + store double %cvt4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 + store double %cvt5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 + store double %cvt6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 + store double %cvt7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 + ret void +} + define void @uitofp_2i32_2f64() #0 { ; SSE-LABEL: @uitofp_2i32_2f64( ; SSE-NEXT: [[LD0:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 0), align 64 @@ -176,6 +264,76 @@ define void @uitofp_4i32_4f64() #0 { ret void } +define void @uitofp_8i32_8f64() #0 { +; SSE-LABEL: @uitofp_8i32_8f64( +; SSE-NEXT: [[LD0:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 0), align 64 +; SSE-NEXT: [[LD1:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 1), align 4 +; SSE-NEXT: [[LD2:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 2), align 8 +; SSE-NEXT: [[LD3:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 3), align 4 +; SSE-NEXT: [[LD4:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4), align 16 +; SSE-NEXT: [[LD5:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 5), align 4 +; SSE-NEXT: [[LD6:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 6), align 8 +; SSE-NEXT: [[LD7:%.*]] = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 7), align 4 +; SSE-NEXT: [[CVT0:%.*]] = uitofp i32 [[LD0]] to double +; SSE-NEXT: [[CVT1:%.*]] = uitofp i32 [[LD1]] to double +; SSE-NEXT: [[CVT2:%.*]] = uitofp i32 [[LD2]] to double +; SSE-NEXT: [[CVT3:%.*]] = uitofp i32 [[LD3]] to double +; SSE-NEXT: [[CVT4:%.*]] = uitofp i32 [[LD4]] to double +; SSE-NEXT: [[CVT5:%.*]] = uitofp i32 [[LD5]] to double +; SSE-NEXT: [[CVT6:%.*]] = uitofp i32 [[LD6]] to double +; SSE-NEXT: [[CVT7:%.*]] = uitofp i32 [[LD7]] to double +; SSE-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; SSE-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; SSE-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; SSE-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; SSE-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; SSE-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; SSE-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; SSE-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @uitofp_8i32_8f64( +; AVX256-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @src32 to <4 x i32>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 16 +; AVX256-NEXT: [[TMP3:%.*]] = uitofp <4 x i32> [[TMP1]] to <4 x double> +; AVX256-NEXT: [[TMP4:%.*]] = uitofp <4 x i32> [[TMP2]] to <4 x double> +; AVX256-NEXT: store <4 x double> [[TMP3]], <4 x double>* bitcast ([8 x double]* @dst64 to <4 x double>*), align 64 +; AVX256-NEXT: store <4 x double> [[TMP4]], <4 x double>* bitcast (double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4) to <4 x double>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @uitofp_8i32_8f64( +; AVX512-NEXT: [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* bitcast ([16 x i32]* @src32 to <8 x i32>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = uitofp <8 x i32> [[TMP1]] to <8 x double> +; AVX512-NEXT: store <8 x double> [[TMP2]], <8 x double>* bitcast ([8 x double]* @dst64 to <8 x double>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 0), align 64 + %ld1 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 1), align 4 + %ld2 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 2), align 8 + %ld3 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 3), align 4 + %ld4 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4), align 16 + %ld5 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 5), align 4 + %ld6 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 6), align 8 + %ld7 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 7), align 4 + %cvt0 = uitofp i32 %ld0 to double + %cvt1 = uitofp i32 %ld1 to double + %cvt2 = uitofp i32 %ld2 to double + %cvt3 = uitofp i32 %ld3 to double + %cvt4 = uitofp i32 %ld4 to double + %cvt5 = uitofp i32 %ld5 to double + %cvt6 = uitofp i32 %ld6 to double + %cvt7 = uitofp i32 %ld7 to double + store double %cvt0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 + store double %cvt1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %cvt2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 + store double %cvt3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + store double %cvt4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 + store double %cvt5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 + store double %cvt6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 + store double %cvt7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 + ret void +} + define void @uitofp_2i16_2f64() #0 { ; CHECK-LABEL: @uitofp_2i16_2f64( ; CHECK-NEXT: [[LD0:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0), align 64 @@ -232,6 +390,76 @@ define void @uitofp_4i16_4f64() #0 { ret void } +define void @uitofp_8i16_8f64() #0 { +; SSE-LABEL: @uitofp_8i16_8f64( +; SSE-NEXT: [[LD0:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0), align 64 +; SSE-NEXT: [[LD1:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1), align 2 +; SSE-NEXT: [[LD2:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2), align 4 +; SSE-NEXT: [[LD3:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3), align 2 +; SSE-NEXT: [[LD4:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4), align 8 +; SSE-NEXT: [[LD5:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5), align 2 +; SSE-NEXT: [[LD6:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6), align 4 +; SSE-NEXT: [[LD7:%.*]] = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7), align 2 +; SSE-NEXT: [[CVT0:%.*]] = uitofp i16 [[LD0]] to double +; SSE-NEXT: [[CVT1:%.*]] = uitofp i16 [[LD1]] to double +; SSE-NEXT: [[CVT2:%.*]] = uitofp i16 [[LD2]] to double +; SSE-NEXT: [[CVT3:%.*]] = uitofp i16 [[LD3]] to double +; SSE-NEXT: [[CVT4:%.*]] = uitofp i16 [[LD4]] to double +; SSE-NEXT: [[CVT5:%.*]] = uitofp i16 [[LD5]] to double +; SSE-NEXT: [[CVT6:%.*]] = uitofp i16 [[LD6]] to double +; SSE-NEXT: [[CVT7:%.*]] = uitofp i16 [[LD7]] to double +; SSE-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; SSE-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; SSE-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; SSE-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; SSE-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; SSE-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; SSE-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; SSE-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @uitofp_8i16_8f64( +; AVX256-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* bitcast ([32 x i16]* @src16 to <4 x i16>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4) to <4 x i16>*), align 8 +; AVX256-NEXT: [[TMP3:%.*]] = uitofp <4 x i16> [[TMP1]] to <4 x double> +; AVX256-NEXT: [[TMP4:%.*]] = uitofp <4 x i16> [[TMP2]] to <4 x double> +; AVX256-NEXT: store <4 x double> [[TMP3]], <4 x double>* bitcast ([8 x double]* @dst64 to <4 x double>*), align 64 +; AVX256-NEXT: store <4 x double> [[TMP4]], <4 x double>* bitcast (double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4) to <4 x double>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @uitofp_8i16_8f64( +; AVX512-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @src16 to <8 x i16>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = uitofp <8 x i16> [[TMP1]] to <8 x double> +; AVX512-NEXT: store <8 x double> [[TMP2]], <8 x double>* bitcast ([8 x double]* @dst64 to <8 x double>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0), align 64 + %ld1 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1), align 2 + %ld2 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2), align 4 + %ld3 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3), align 2 + %ld4 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4), align 8 + %ld5 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5), align 2 + %ld6 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6), align 4 + %ld7 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7), align 2 + %cvt0 = uitofp i16 %ld0 to double + %cvt1 = uitofp i16 %ld1 to double + %cvt2 = uitofp i16 %ld2 to double + %cvt3 = uitofp i16 %ld3 to double + %cvt4 = uitofp i16 %ld4 to double + %cvt5 = uitofp i16 %ld5 to double + %cvt6 = uitofp i16 %ld6 to double + %cvt7 = uitofp i16 %ld7 to double + store double %cvt0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 + store double %cvt1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %cvt2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 + store double %cvt3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + store double %cvt4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 + store double %cvt5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 + store double %cvt6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 + store double %cvt7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 + ret void +} + define void @uitofp_2i8_2f64() #0 { ; SSE-LABEL: @uitofp_2i8_2f64( ; SSE-NEXT: [[LD0:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 0), align 64 @@ -303,6 +531,76 @@ define void @uitofp_4i8_4f64() #0 { ret void } +define void @uitofp_8i8_8f64() #0 { +; SSE-LABEL: @uitofp_8i8_8f64( +; SSE-NEXT: [[LD0:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 0), align 64 +; SSE-NEXT: [[LD1:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 1), align 1 +; SSE-NEXT: [[LD2:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 2), align 2 +; SSE-NEXT: [[LD3:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 3), align 1 +; SSE-NEXT: [[LD4:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4), align 4 +; SSE-NEXT: [[LD5:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 5), align 1 +; SSE-NEXT: [[LD6:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 6), align 2 +; SSE-NEXT: [[LD7:%.*]] = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 7), align 1 +; SSE-NEXT: [[CVT0:%.*]] = uitofp i8 [[LD0]] to double +; SSE-NEXT: [[CVT1:%.*]] = uitofp i8 [[LD1]] to double +; SSE-NEXT: [[CVT2:%.*]] = uitofp i8 [[LD2]] to double +; SSE-NEXT: [[CVT3:%.*]] = uitofp i8 [[LD3]] to double +; SSE-NEXT: [[CVT4:%.*]] = uitofp i8 [[LD4]] to double +; SSE-NEXT: [[CVT5:%.*]] = uitofp i8 [[LD5]] to double +; SSE-NEXT: [[CVT6:%.*]] = uitofp i8 [[LD6]] to double +; SSE-NEXT: [[CVT7:%.*]] = uitofp i8 [[LD7]] to double +; SSE-NEXT: store double [[CVT0]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 +; SSE-NEXT: store double [[CVT1]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 +; SSE-NEXT: store double [[CVT2]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 +; SSE-NEXT: store double [[CVT3]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 +; SSE-NEXT: store double [[CVT4]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 +; SSE-NEXT: store double [[CVT5]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 +; SSE-NEXT: store double [[CVT6]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 +; SSE-NEXT: store double [[CVT7]], double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @uitofp_8i8_8f64( +; AVX256-NEXT: [[TMP1:%.*]] = load <4 x i8>, <4 x i8>* bitcast ([64 x i8]* @src8 to <4 x i8>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4) to <4 x i8>*), align 4 +; AVX256-NEXT: [[TMP3:%.*]] = uitofp <4 x i8> [[TMP1]] to <4 x double> +; AVX256-NEXT: [[TMP4:%.*]] = uitofp <4 x i8> [[TMP2]] to <4 x double> +; AVX256-NEXT: store <4 x double> [[TMP3]], <4 x double>* bitcast ([8 x double]* @dst64 to <4 x double>*), align 64 +; AVX256-NEXT: store <4 x double> [[TMP4]], <4 x double>* bitcast (double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4) to <4 x double>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @uitofp_8i8_8f64( +; AVX512-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* bitcast ([64 x i8]* @src8 to <8 x i8>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = uitofp <8 x i8> [[TMP1]] to <8 x double> +; AVX512-NEXT: store <8 x double> [[TMP2]], <8 x double>* bitcast ([8 x double]* @dst64 to <8 x double>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 0), align 64 + %ld1 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 1), align 1 + %ld2 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 2), align 2 + %ld3 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 3), align 1 + %ld4 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4), align 4 + %ld5 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 5), align 1 + %ld6 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 6), align 2 + %ld7 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 7), align 1 + %cvt0 = uitofp i8 %ld0 to double + %cvt1 = uitofp i8 %ld1 to double + %cvt2 = uitofp i8 %ld2 to double + %cvt3 = uitofp i8 %ld3 to double + %cvt4 = uitofp i8 %ld4 to double + %cvt5 = uitofp i8 %ld5 to double + %cvt6 = uitofp i8 %ld6 to double + %cvt7 = uitofp i8 %ld7 to double + store double %cvt0, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 0), align 64 + store double %cvt1, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 1), align 8 + store double %cvt2, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 2), align 16 + store double %cvt3, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 3), align 8 + store double %cvt4, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 4), align 32 + store double %cvt5, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 5), align 8 + store double %cvt6, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 6), align 16 + store double %cvt7, double* getelementptr inbounds ([8 x double], [8 x double]* @dst64, i32 0, i64 7), align 8 + ret void +} + ; ; UITOFP to vXf32 ; @@ -378,6 +676,94 @@ define void @uitofp_4i64_4f32() #0 { ret void } +define void @uitofp_8i64_8f32() #0 { +; SSE-LABEL: @uitofp_8i64_8f32( +; SSE-NEXT: [[LD0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 +; SSE-NEXT: [[LD1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 +; SSE-NEXT: [[LD2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 +; SSE-NEXT: [[LD3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 +; SSE-NEXT: [[LD4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 +; SSE-NEXT: [[LD5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 +; SSE-NEXT: [[LD6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 +; SSE-NEXT: [[LD7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 +; SSE-NEXT: [[CVT0:%.*]] = uitofp i64 [[LD0]] to float +; SSE-NEXT: [[CVT1:%.*]] = uitofp i64 [[LD1]] to float +; SSE-NEXT: [[CVT2:%.*]] = uitofp i64 [[LD2]] to float +; SSE-NEXT: [[CVT3:%.*]] = uitofp i64 [[LD3]] to float +; SSE-NEXT: [[CVT4:%.*]] = uitofp i64 [[LD4]] to float +; SSE-NEXT: [[CVT5:%.*]] = uitofp i64 [[LD5]] to float +; SSE-NEXT: [[CVT6:%.*]] = uitofp i64 [[LD6]] to float +; SSE-NEXT: [[CVT7:%.*]] = uitofp i64 [[LD7]] to float +; SSE-NEXT: store float [[CVT0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 64 +; SSE-NEXT: store float [[CVT1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; SSE-NEXT: store float [[CVT2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 8 +; SSE-NEXT: store float [[CVT3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; SSE-NEXT: store float [[CVT4]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 16 +; SSE-NEXT: store float [[CVT5]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 +; SSE-NEXT: store float [[CVT6]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 8 +; SSE-NEXT: store float [[CVT7]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @uitofp_8i64_8f32( +; AVX256-NEXT: [[LD0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 +; AVX256-NEXT: [[LD1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 +; AVX256-NEXT: [[LD2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 +; AVX256-NEXT: [[LD3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 +; AVX256-NEXT: [[LD4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 +; AVX256-NEXT: [[LD5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 +; AVX256-NEXT: [[LD6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 +; AVX256-NEXT: [[LD7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 +; AVX256-NEXT: [[CVT0:%.*]] = uitofp i64 [[LD0]] to float +; AVX256-NEXT: [[CVT1:%.*]] = uitofp i64 [[LD1]] to float +; AVX256-NEXT: [[CVT2:%.*]] = uitofp i64 [[LD2]] to float +; AVX256-NEXT: [[CVT3:%.*]] = uitofp i64 [[LD3]] to float +; AVX256-NEXT: [[CVT4:%.*]] = uitofp i64 [[LD4]] to float +; AVX256-NEXT: [[CVT5:%.*]] = uitofp i64 [[LD5]] to float +; AVX256-NEXT: [[CVT6:%.*]] = uitofp i64 [[LD6]] to float +; AVX256-NEXT: [[CVT7:%.*]] = uitofp i64 [[LD7]] to float +; AVX256-NEXT: store float [[CVT0]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 64 +; AVX256-NEXT: store float [[CVT1]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 +; AVX256-NEXT: store float [[CVT2]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 8 +; AVX256-NEXT: store float [[CVT3]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 +; AVX256-NEXT: store float [[CVT4]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 16 +; AVX256-NEXT: store float [[CVT5]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 +; AVX256-NEXT: store float [[CVT6]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 8 +; AVX256-NEXT: store float [[CVT7]], float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @uitofp_8i64_8f32( +; AVX512-NEXT: [[TMP1:%.*]] = load <8 x i64>, <8 x i64>* bitcast ([8 x i64]* @src64 to <8 x i64>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = uitofp <8 x i64> [[TMP1]] to <8 x float> +; AVX512-NEXT: store <8 x float> [[TMP2]], <8 x float>* bitcast ([16 x float]* @dst32 to <8 x float>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 0), align 64 + %ld1 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 1), align 8 + %ld2 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 2), align 16 + %ld3 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 3), align 8 + %ld4 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 4), align 32 + %ld5 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 5), align 8 + %ld6 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 6), align 16 + %ld7 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @src64, i32 0, i64 7), align 8 + %cvt0 = uitofp i64 %ld0 to float + %cvt1 = uitofp i64 %ld1 to float + %cvt2 = uitofp i64 %ld2 to float + %cvt3 = uitofp i64 %ld3 to float + %cvt4 = uitofp i64 %ld4 to float + %cvt5 = uitofp i64 %ld5 to float + %cvt6 = uitofp i64 %ld6 to float + %cvt7 = uitofp i64 %ld7 to float + store float %cvt0, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0), align 64 + store float %cvt1, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1), align 4 + store float %cvt2, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2), align 8 + store float %cvt3, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3), align 4 + store float %cvt4, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4), align 16 + store float %cvt5, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5), align 4 + store float %cvt6, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6), align 8 + store float %cvt7, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7), align 4 + ret void +} + define void @uitofp_4i32_4f32() #0 { ; CHECK-LABEL: @uitofp_4i32_4f32( ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @src32 to <4 x i32>*), align 64 @@ -443,6 +829,88 @@ define void @uitofp_8i32_8f32() #0 { ret void } +define void @uitofp_16i32_16f32() #0 { +; SSE-LABEL: @uitofp_16i32_16f32( +; SSE-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @src32 to <4 x i32>*), align 64 +; SSE-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 16 +; SSE-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 8) to <4 x i32>*), align 32 +; SSE-NEXT: [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 12) to <4 x i32>*), align 16 +; SSE-NEXT: [[TMP5:%.*]] = uitofp <4 x i32> [[TMP1]] to <4 x float> +; SSE-NEXT: [[TMP6:%.*]] = uitofp <4 x i32> [[TMP2]] to <4 x float> +; SSE-NEXT: [[TMP7:%.*]] = uitofp <4 x i32> [[TMP3]] to <4 x float> +; SSE-NEXT: [[TMP8:%.*]] = uitofp <4 x i32> [[TMP4]] to <4 x float> +; SSE-NEXT: store <4 x float> [[TMP5]], <4 x float>* bitcast ([16 x float]* @dst32 to <4 x float>*), align 64 +; SSE-NEXT: store <4 x float> [[TMP6]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4) to <4 x float>*), align 16 +; SSE-NEXT: store <4 x float> [[TMP7]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <4 x float>*), align 32 +; SSE-NEXT: store <4 x float> [[TMP8]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12) to <4 x float>*), align 16 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @uitofp_16i32_16f32( +; AVX256-NEXT: [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* bitcast ([16 x i32]* @src32 to <8 x i32>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <8 x i32>, <8 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 8) to <8 x i32>*), align 32 +; AVX256-NEXT: [[TMP3:%.*]] = uitofp <8 x i32> [[TMP1]] to <8 x float> +; AVX256-NEXT: [[TMP4:%.*]] = uitofp <8 x i32> [[TMP2]] to <8 x float> +; AVX256-NEXT: store <8 x float> [[TMP3]], <8 x float>* bitcast ([16 x float]* @dst32 to <8 x float>*), align 64 +; AVX256-NEXT: store <8 x float> [[TMP4]], <8 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <8 x float>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @uitofp_16i32_16f32( +; AVX512-NEXT: [[TMP1:%.*]] = load <16 x i32>, <16 x i32>* bitcast ([16 x i32]* @src32 to <16 x i32>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = uitofp <16 x i32> [[TMP1]] to <16 x float> +; AVX512-NEXT: store <16 x float> [[TMP2]], <16 x float>* bitcast ([16 x float]* @dst32 to <16 x float>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 0 ), align 64 + %ld1 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 1 ), align 4 + %ld2 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 2 ), align 8 + %ld3 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 3 ), align 4 + %ld4 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 4 ), align 16 + %ld5 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 5 ), align 4 + %ld6 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 6 ), align 8 + %ld7 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 7 ), align 4 + %ld8 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 8 ), align 32 + %ld9 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 9 ), align 4 + %ld10 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 10), align 8 + %ld11 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 11), align 4 + %ld12 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 12), align 16 + %ld13 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 13), align 4 + %ld14 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 14), align 8 + %ld15 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @src32, i32 0, i64 15), align 4 + %cvt0 = uitofp i32 %ld0 to float + %cvt1 = uitofp i32 %ld1 to float + %cvt2 = uitofp i32 %ld2 to float + %cvt3 = uitofp i32 %ld3 to float + %cvt4 = uitofp i32 %ld4 to float + %cvt5 = uitofp i32 %ld5 to float + %cvt6 = uitofp i32 %ld6 to float + %cvt7 = uitofp i32 %ld7 to float + %cvt8 = uitofp i32 %ld8 to float + %cvt9 = uitofp i32 %ld9 to float + %cvt10 = uitofp i32 %ld10 to float + %cvt11 = uitofp i32 %ld11 to float + %cvt12 = uitofp i32 %ld12 to float + %cvt13 = uitofp i32 %ld13 to float + %cvt14 = uitofp i32 %ld14 to float + %cvt15 = uitofp i32 %ld15 to float + store float %cvt0 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0 ), align 64 + store float %cvt1 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1 ), align 4 + store float %cvt2 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2 ), align 8 + store float %cvt3 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3 ), align 4 + store float %cvt4 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4 ), align 16 + store float %cvt5 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5 ), align 4 + store float %cvt6 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6 ), align 8 + store float %cvt7 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7 ), align 4 + store float %cvt8 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8 ), align 32 + store float %cvt9 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9 ), align 4 + store float %cvt10, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 8 + store float %cvt11, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 + store float %cvt12, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 16 + store float %cvt13, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 + store float %cvt14, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 8 + store float %cvt15, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 + ret void +} + define void @uitofp_4i16_4f32() #0 { ; CHECK-LABEL: @uitofp_4i16_4f32( ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* bitcast ([32 x i16]* @src16 to <4 x i16>*), align 64 @@ -468,7 +936,7 @@ define void @uitofp_4i16_4f32() #0 { define void @uitofp_8i16_8f32() #0 { ; SSE-LABEL: @uitofp_8i16_8f32( ; SSE-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* bitcast ([32 x i16]* @src16 to <4 x i16>*), align 64 -; SSE-NEXT: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4) to <4 x i16>*), align 4 +; SSE-NEXT: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4) to <4 x i16>*), align 8 ; SSE-NEXT: [[TMP3:%.*]] = uitofp <4 x i16> [[TMP1]] to <4 x float> ; SSE-NEXT: [[TMP4:%.*]] = uitofp <4 x i16> [[TMP2]] to <4 x float> ; SSE-NEXT: store <4 x float> [[TMP3]], <4 x float>* bitcast ([16 x float]* @dst32 to <4 x float>*), align 64 @@ -482,13 +950,13 @@ define void @uitofp_8i16_8f32() #0 { ; AVX-NEXT: ret void ; %ld0 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0), align 64 - %ld1 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1), align 1 - %ld2 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2), align 2 - %ld3 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3), align 1 - %ld4 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4), align 4 - %ld5 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5), align 1 - %ld6 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6), align 2 - %ld7 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7), align 1 + %ld1 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1), align 2 + %ld2 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2), align 4 + %ld3 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3), align 2 + %ld4 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4), align 8 + %ld5 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5), align 2 + %ld6 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6), align 4 + %ld7 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7), align 2 %cvt0 = uitofp i16 %ld0 to float %cvt1 = uitofp i16 %ld1 to float %cvt2 = uitofp i16 %ld2 to float @@ -508,6 +976,88 @@ define void @uitofp_8i16_8f32() #0 { ret void } +define void @uitofp_16i16_16f32() #0 { +; SSE-LABEL: @uitofp_16i16_16f32( +; SSE-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* bitcast ([32 x i16]* @src16 to <4 x i16>*), align 64 +; SSE-NEXT: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4) to <4 x i16>*), align 8 +; SSE-NEXT: [[TMP3:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 8) to <4 x i16>*), align 16 +; SSE-NEXT: [[TMP4:%.*]] = load <4 x i16>, <4 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 12) to <4 x i16>*), align 8 +; SSE-NEXT: [[TMP5:%.*]] = uitofp <4 x i16> [[TMP1]] to <4 x float> +; SSE-NEXT: [[TMP6:%.*]] = uitofp <4 x i16> [[TMP2]] to <4 x float> +; SSE-NEXT: [[TMP7:%.*]] = uitofp <4 x i16> [[TMP3]] to <4 x float> +; SSE-NEXT: [[TMP8:%.*]] = uitofp <4 x i16> [[TMP4]] to <4 x float> +; SSE-NEXT: store <4 x float> [[TMP5]], <4 x float>* bitcast ([16 x float]* @dst32 to <4 x float>*), align 64 +; SSE-NEXT: store <4 x float> [[TMP6]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4) to <4 x float>*), align 16 +; SSE-NEXT: store <4 x float> [[TMP7]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <4 x float>*), align 32 +; SSE-NEXT: store <4 x float> [[TMP8]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12) to <4 x float>*), align 16 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @uitofp_16i16_16f32( +; AVX256-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @src16 to <8 x i16>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 8) to <8 x i16>*), align 16 +; AVX256-NEXT: [[TMP3:%.*]] = uitofp <8 x i16> [[TMP1]] to <8 x float> +; AVX256-NEXT: [[TMP4:%.*]] = uitofp <8 x i16> [[TMP2]] to <8 x float> +; AVX256-NEXT: store <8 x float> [[TMP3]], <8 x float>* bitcast ([16 x float]* @dst32 to <8 x float>*), align 64 +; AVX256-NEXT: store <8 x float> [[TMP4]], <8 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <8 x float>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @uitofp_16i16_16f32( +; AVX512-NEXT: [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @src16 to <16 x i16>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = uitofp <16 x i16> [[TMP1]] to <16 x float> +; AVX512-NEXT: store <16 x float> [[TMP2]], <16 x float>* bitcast ([16 x float]* @dst32 to <16 x float>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 0 ), align 64 + %ld1 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 1 ), align 2 + %ld2 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 2 ), align 4 + %ld3 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 3 ), align 2 + %ld4 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 4 ), align 8 + %ld5 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 5 ), align 2 + %ld6 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 6 ), align 4 + %ld7 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 7 ), align 2 + %ld8 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 8 ), align 16 + %ld9 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 9 ), align 2 + %ld10 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 10), align 4 + %ld11 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 11), align 2 + %ld12 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 12), align 8 + %ld13 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 13), align 2 + %ld14 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 14), align 4 + %ld15 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @src16, i32 0, i64 15), align 2 + %cvt0 = uitofp i16 %ld0 to float + %cvt1 = uitofp i16 %ld1 to float + %cvt2 = uitofp i16 %ld2 to float + %cvt3 = uitofp i16 %ld3 to float + %cvt4 = uitofp i16 %ld4 to float + %cvt5 = uitofp i16 %ld5 to float + %cvt6 = uitofp i16 %ld6 to float + %cvt7 = uitofp i16 %ld7 to float + %cvt8 = uitofp i16 %ld8 to float + %cvt9 = uitofp i16 %ld9 to float + %cvt10 = uitofp i16 %ld10 to float + %cvt11 = uitofp i16 %ld11 to float + %cvt12 = uitofp i16 %ld12 to float + %cvt13 = uitofp i16 %ld13 to float + %cvt14 = uitofp i16 %ld14 to float + %cvt15 = uitofp i16 %ld15 to float + store float %cvt0 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0 ), align 64 + store float %cvt1 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1 ), align 4 + store float %cvt2 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2 ), align 8 + store float %cvt3 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3 ), align 4 + store float %cvt4 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4 ), align 16 + store float %cvt5 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5 ), align 4 + store float %cvt6 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6 ), align 8 + store float %cvt7 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7 ), align 4 + store float %cvt8 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8 ), align 32 + store float %cvt9 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9 ), align 4 + store float %cvt10, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 8 + store float %cvt11, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 + store float %cvt12, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 16 + store float %cvt13, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 + store float %cvt14, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 8 + store float %cvt15, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 + ret void +} + define void @uitofp_4i8_4f32() #0 { ; CHECK-LABEL: @uitofp_4i8_4f32( ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i8>, <4 x i8>* bitcast ([64 x i8]* @src8 to <4 x i8>*), align 64 @@ -573,4 +1123,86 @@ define void @uitofp_8i8_8f32() #0 { ret void } +define void @uitofp_16i8_16f32() #0 { +; SSE-LABEL: @uitofp_16i8_16f32( +; SSE-NEXT: [[TMP1:%.*]] = load <4 x i8>, <4 x i8>* bitcast ([64 x i8]* @src8 to <4 x i8>*), align 64 +; SSE-NEXT: [[TMP2:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4) to <4 x i8>*), align 4 +; SSE-NEXT: [[TMP3:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 8) to <4 x i8>*), align 8 +; SSE-NEXT: [[TMP4:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 12) to <4 x i8>*), align 4 +; SSE-NEXT: [[TMP5:%.*]] = uitofp <4 x i8> [[TMP1]] to <4 x float> +; SSE-NEXT: [[TMP6:%.*]] = uitofp <4 x i8> [[TMP2]] to <4 x float> +; SSE-NEXT: [[TMP7:%.*]] = uitofp <4 x i8> [[TMP3]] to <4 x float> +; SSE-NEXT: [[TMP8:%.*]] = uitofp <4 x i8> [[TMP4]] to <4 x float> +; SSE-NEXT: store <4 x float> [[TMP5]], <4 x float>* bitcast ([16 x float]* @dst32 to <4 x float>*), align 64 +; SSE-NEXT: store <4 x float> [[TMP6]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4) to <4 x float>*), align 16 +; SSE-NEXT: store <4 x float> [[TMP7]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <4 x float>*), align 32 +; SSE-NEXT: store <4 x float> [[TMP8]], <4 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12) to <4 x float>*), align 16 +; SSE-NEXT: ret void +; +; AVX256-LABEL: @uitofp_16i8_16f32( +; AVX256-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* bitcast ([64 x i8]* @src8 to <8 x i8>*), align 64 +; AVX256-NEXT: [[TMP2:%.*]] = load <8 x i8>, <8 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 8) to <8 x i8>*), align 8 +; AVX256-NEXT: [[TMP3:%.*]] = uitofp <8 x i8> [[TMP1]] to <8 x float> +; AVX256-NEXT: [[TMP4:%.*]] = uitofp <8 x i8> [[TMP2]] to <8 x float> +; AVX256-NEXT: store <8 x float> [[TMP3]], <8 x float>* bitcast ([16 x float]* @dst32 to <8 x float>*), align 64 +; AVX256-NEXT: store <8 x float> [[TMP4]], <8 x float>* bitcast (float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8) to <8 x float>*), align 32 +; AVX256-NEXT: ret void +; +; AVX512-LABEL: @uitofp_16i8_16f32( +; AVX512-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @src8 to <16 x i8>*), align 64 +; AVX512-NEXT: [[TMP2:%.*]] = uitofp <16 x i8> [[TMP1]] to <16 x float> +; AVX512-NEXT: store <16 x float> [[TMP2]], <16 x float>* bitcast ([16 x float]* @dst32 to <16 x float>*), align 64 +; AVX512-NEXT: ret void +; + %ld0 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 0 ), align 64 + %ld1 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 1 ), align 1 + %ld2 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 2 ), align 2 + %ld3 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 3 ), align 1 + %ld4 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 4 ), align 4 + %ld5 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 5 ), align 1 + %ld6 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 6 ), align 2 + %ld7 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 7 ), align 1 + %ld8 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 8 ), align 8 + %ld9 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 9 ), align 1 + %ld10 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 10), align 2 + %ld11 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 11), align 1 + %ld12 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 12), align 4 + %ld13 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 13), align 1 + %ld14 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 14), align 2 + %ld15 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @src8, i32 0, i64 15), align 1 + %cvt0 = uitofp i8 %ld0 to float + %cvt1 = uitofp i8 %ld1 to float + %cvt2 = uitofp i8 %ld2 to float + %cvt3 = uitofp i8 %ld3 to float + %cvt4 = uitofp i8 %ld4 to float + %cvt5 = uitofp i8 %ld5 to float + %cvt6 = uitofp i8 %ld6 to float + %cvt7 = uitofp i8 %ld7 to float + %cvt8 = uitofp i8 %ld8 to float + %cvt9 = uitofp i8 %ld9 to float + %cvt10 = uitofp i8 %ld10 to float + %cvt11 = uitofp i8 %ld11 to float + %cvt12 = uitofp i8 %ld12 to float + %cvt13 = uitofp i8 %ld13 to float + %cvt14 = uitofp i8 %ld14 to float + %cvt15 = uitofp i8 %ld15 to float + store float %cvt0 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 0 ), align 64 + store float %cvt1 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 1 ), align 4 + store float %cvt2 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 2 ), align 8 + store float %cvt3 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 3 ), align 4 + store float %cvt4 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 4 ), align 16 + store float %cvt5 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 5 ), align 4 + store float %cvt6 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 6 ), align 8 + store float %cvt7 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 7 ), align 4 + store float %cvt8 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 8 ), align 32 + store float %cvt9 , float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 9 ), align 4 + store float %cvt10, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 10), align 8 + store float %cvt11, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 11), align 4 + store float %cvt12, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 12), align 16 + store float %cvt13, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 13), align 4 + store float %cvt14, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 14), align 8 + store float %cvt15, float* getelementptr inbounds ([16 x float], [16 x float]* @dst32, i32 0, i64 15), align 4 + ret void +} + attributes #0 = { nounwind }