derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
294 lines
17 KiB
C
294 lines
17 KiB
C
// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +fma -emit-llvm -o - -Wall -Werror | FileCheck %s
|
|
// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=i386-apple-darwin -target-feature +fma -emit-llvm -o - -Wall -Werror | FileCheck %s
|
|
// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +fma -emit-llvm -o - -Wall -Werror | FileCheck %s
|
|
// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=i386-apple-darwin -target-feature +fma -emit-llvm -o - -Wall -Werror | FileCheck %s
|
|
|
|
// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +fma -emit-llvm -o - -Wall -Werror -fexperimental-new-constant-interpreter | FileCheck %s
|
|
// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=i386-apple-darwin -target-feature +fma -emit-llvm -o - -Wall -Werror -fexperimental-new-constant-interpreter | FileCheck %s
|
|
// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +fma -emit-llvm -o - -Wall -Werror -fexperimental-new-constant-interpreter | FileCheck %s
|
|
// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=i386-apple-darwin -target-feature +fma -emit-llvm -o - -Wall -Werror -fexperimental-new-constant-interpreter | FileCheck %s
|
|
|
|
|
|
#include <immintrin.h>
|
|
#include "builtin_test_helpers.h"
|
|
|
|
__m128 test_mm_fmadd_ps(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fmadd_ps
|
|
// CHECK: call {{.*}}<4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
|
|
return _mm_fmadd_ps(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128(_mm_fmadd_ps((__m128){ 0.0f, 1.0f, -2.0f, -4.0f }, (__m128){ -0.0f, 4.0f, 2.0f, 1.0f }, (__m128){ -0.0f, -4.0f, 2.0f, 1.0f }), -0.0f, 0.0f, -2.0f, -3.0f));
|
|
|
|
__m128d test_mm_fmadd_pd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fmadd_pd
|
|
// CHECK: call {{.*}}<2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
|
|
return _mm_fmadd_pd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128d(_mm_fmadd_pd((__m128d){ 0.0, -4.0 }, (__m128d){ -0.0, 1.0 }, (__m128d){ -0.0, 1.0 }), -0.0, -3.0));
|
|
|
|
__m128 test_mm_fmadd_ss(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fmadd_ss
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: call float @llvm.fma.f32(float %{{.*}}, float %{{.*}}, float %{{.*}})
|
|
// CHECK: insertelement <4 x float> %{{.*}}, float %{{.*}}, i32 0
|
|
return _mm_fmadd_ss(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128(_mm_fmadd_ss((__m128){ -4.0f, 1.0f, -2.0f, -0.0f }, (__m128){ 2.0f, 4.0f, 2.0f, -0.0f }, (__m128){ 1.0f, -4.0f, 2.0f, 1.0f }), -7.0f, 1.0f, -2.0f, -0.0f));
|
|
|
|
__m128d test_mm_fmadd_sd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fmadd_sd
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: call double @llvm.fma.f64(double %{{.*}}, double %{{.*}}, double %{{.*}})
|
|
// CHECK: insertelement <2 x double> %{{.*}}, double %{{.*}}, i32 0
|
|
return _mm_fmadd_sd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128d(_mm_fmadd_sd((__m128d){ -4.0, 1.0 }, (__m128d){ 1.0, 2.0 }, (__m128d){ -8.0, 3.0 }), -12.0, 1.0));
|
|
|
|
__m128 test_mm_fmsub_ps(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fmsub_ps
|
|
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
|
|
// CHECK: call {{.*}}<4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
|
|
return _mm_fmsub_ps(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128(_mm_fmsub_ps((__m128){ 0.0f, 1.0f, -2.0f, -4.0f }, (__m128){ -0.0f, 4.0f, 2.0f, 1.0f }, (__m128){ -0.0f, -4.0f, 2.0f, 1.0f }), 0.0f, 8.0f, -6.0f, -5.0f));
|
|
|
|
__m128d test_mm_fmsub_pd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fmsub_pd
|
|
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
|
|
// CHECK: call {{.*}}<2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
|
|
return _mm_fmsub_pd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128d(_mm_fmsub_pd((__m128d){ 0.0, -4.0 }, (__m128d){ -0.0, 1.0 }, (__m128d){ -0.0, 1.0 }), 0.0, -5.0));
|
|
|
|
__m128 test_mm_fmsub_ss(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fmsub_ss
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: [[NEG:%.+]] = fneg float %{{.+}}
|
|
// CHECK: call float @llvm.fma.f32(float %{{.*}}, float %{{.*}}, float [[NEG]])
|
|
// CHECK: insertelement <4 x float> %{{.*}}, float %{{.*}}, i32 0
|
|
return _mm_fmsub_ss(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128(_mm_fmsub_ss((__m128){ -4.0f, 1.0f, -2.0f, -0.0f }, (__m128){ 2.0f, 4.0f, 2.0f, -0.0f }, (__m128){ 1.0f, -4.0f, 2.0f, 1.0f }), -9.0f, 1.0f, -2.0f, -0.0f));
|
|
|
|
__m128d test_mm_fmsub_sd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fmsub_sd
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: [[NEG:%.+]] = fneg double %{{.+}}
|
|
// CHECK: call double @llvm.fma.f64(double %{{.*}}, double %{{.*}}, double [[NEG]])
|
|
// CHECK: insertelement <2 x double> %{{.*}}, double %{{.*}}, i32 0
|
|
return _mm_fmsub_sd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128d(_mm_fmsub_sd((__m128d){ -4.0, 1.0 }, (__m128d){ 1.0, 2.0 }, (__m128d){ -8.0, 3.0 }), 4.0, 1.0));
|
|
|
|
__m128 test_mm_fnmadd_ps(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fnmadd_ps
|
|
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
|
|
// CHECK: call {{.*}}<4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
|
|
return _mm_fnmadd_ps(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128(_mm_fnmadd_ps((__m128){ 0.0f, 1.0f, -2.0f, -4.0f }, (__m128){ -0.0f, 4.0f, 2.0f, 1.0f }, (__m128){ -0.0f, -4.0f, 2.0f, 1.0f }), 0.0f, -8.0f, 6.0f, 5.0f));
|
|
|
|
__m128d test_mm_fnmadd_pd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fnmadd_pd
|
|
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
|
|
// CHECK: call {{.*}}<2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
|
|
return _mm_fnmadd_pd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128d(_mm_fnmadd_pd((__m128d){ 0.0, -4.0 }, (__m128d){ -0.0, 1.0 }, (__m128d){ -0.0, 1.0 }), 0.0, 5.0));
|
|
|
|
__m128 test_mm_fnmadd_ss(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fnmadd_ss
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: [[NEG:%.+]] = fneg float %{{.+}}
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: call float @llvm.fma.f32(float %{{.*}}, float [[NEG]], float %{{.*}})
|
|
// CHECK: insertelement <4 x float> %{{.*}}, float %{{.*}}, i32 0
|
|
return _mm_fnmadd_ss(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128(_mm_fnmadd_ss((__m128){ -4.0f, 1.0f, -2.0f, -0.0f }, (__m128){ 2.0f, 4.0f, 2.0f, -0.0f }, (__m128){ 1.0f, -4.0f, 2.0f, 1.0f }), 9.0f, 1.0f, -2.0f, -0.0f));
|
|
|
|
__m128d test_mm_fnmadd_sd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fnmadd_sd
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: [[NEG:%.+]] = fneg double %{{.+}}
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: call double @llvm.fma.f64(double %{{.*}}, double [[NEG]], double %{{.*}})
|
|
// CHECK: insertelement <2 x double> %{{.*}}, double %{{.*}}, i32 0
|
|
return _mm_fnmadd_sd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128d(_mm_fnmadd_sd((__m128d){ -4.0, 1.0 }, (__m128d){ 1.0, 2.0 }, (__m128d){ -8.0, 3.0 }), -4.0, 1.0));
|
|
|
|
__m128 test_mm_fnmsub_ps(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fnmsub_ps
|
|
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
|
|
// CHECK: [[NEG2:%.+]] = fneg <4 x float> %{{.+}}
|
|
// CHECK: call {{.*}}<4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
|
|
return _mm_fnmsub_ps(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128(_mm_fnmsub_ps((__m128){ 0.0f, 1.0f, -2.0f, -4.0f }, (__m128){ -0.0f, 4.0f, 2.0f, 1.0f }, (__m128){ -0.0f, -4.0f, 2.0f, 1.0f }), 0.0f, 0.0f, 2.0f, 3.0f));
|
|
|
|
__m128d test_mm_fnmsub_pd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fnmsub_pd
|
|
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
|
|
// CHECK: [[NEG2:%.+]] = fneg <2 x double> %{{.+}}
|
|
// CHECK: call {{.*}}<2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
|
|
return _mm_fnmsub_pd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128d(_mm_fnmsub_pd((__m128d){ 0.0, -4.0 }, (__m128d){ -0.0, 1.0 }, (__m128d){ -0.0, 1.0 }), 0.0, 3.0));
|
|
|
|
__m128 test_mm_fnmsub_ss(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fnmsub_ss
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: [[NEG:%.+]] = fneg float %{{.+}}
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i32 0
|
|
// CHECK: [[NEG2:%.+]] = fneg float %{{.+}}
|
|
// CHECK: call float @llvm.fma.f32(float %{{.*}}, float [[NEG]], float [[NEG2]])
|
|
// CHECK: insertelement <4 x float> %{{.*}}, float %{{.*}}, i32 0
|
|
return _mm_fnmsub_ss(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128(_mm_fnmsub_ss((__m128){ -4.0f, 1.0f, -2.0f, -0.0f }, (__m128){ 2.0f, 4.0f, 2.0f, -0.0f }, (__m128){ 1.0f, -4.0f, 2.0f, 1.0f }), 7.0f, 1.0f, -2.0f, -0.0f));
|
|
|
|
__m128d test_mm_fnmsub_sd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fnmsub_sd
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: [[NEG:%.+]] = fneg double %{{.+}}
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i32 0
|
|
// CHECK: [[NEG2:%.+]] = fneg double %{{.+}}
|
|
// CHECK: call double @llvm.fma.f64(double %{{.*}}, double [[NEG]], double [[NEG2]])
|
|
// CHECK: insertelement <2 x double> %{{.*}}, double %{{.*}}, i32 0
|
|
return _mm_fnmsub_sd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m128d(_mm_fnmsub_sd((__m128d){ -4.0, 1.0 }, (__m128d){ 1.0, 2.0 }, (__m128d){ -8.0, 3.0 }), 12.0, 1.0));
|
|
|
|
__m128 test_mm_fmaddsub_ps(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fmaddsub_ps
|
|
// CHECK-NOT: fneg
|
|
// CHECK: call {{.*}}<4 x float> @llvm.x86.fma.vfmaddsub.ps(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
|
|
return _mm_fmaddsub_ps(a, b, c);
|
|
}
|
|
|
|
__m128d test_mm_fmaddsub_pd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fmaddsub_pd
|
|
// CHECK-NOT: fneg
|
|
// CHECK: call {{.*}}<2 x double> @llvm.x86.fma.vfmaddsub.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
|
|
return _mm_fmaddsub_pd(a, b, c);
|
|
}
|
|
|
|
__m128 test_mm_fmsubadd_ps(__m128 a, __m128 b, __m128 c) {
|
|
// CHECK-LABEL: test_mm_fmsubadd_ps
|
|
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
|
|
// CHECK: call {{.*}}<4 x float> @llvm.x86.fma.vfmaddsub.ps(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> [[NEG]])
|
|
return _mm_fmsubadd_ps(a, b, c);
|
|
}
|
|
|
|
__m128d test_mm_fmsubadd_pd(__m128d a, __m128d b, __m128d c) {
|
|
// CHECK-LABEL: test_mm_fmsubadd_pd
|
|
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
|
|
// CHECK: call {{.*}}<2 x double> @llvm.x86.fma.vfmaddsub.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> [[NEG]])
|
|
return _mm_fmsubadd_pd(a, b, c);
|
|
}
|
|
|
|
__m256 test_mm256_fmadd_ps(__m256 a, __m256 b, __m256 c) {
|
|
// CHECK-LABEL: test_mm256_fmadd_ps
|
|
// CHECK: call {{.*}}<8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
|
|
return _mm256_fmadd_ps(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m256(_mm256_fmadd_ps((__m256){ 0.0f, 1.0f, -2.0f, -4.0f, -8.0f, -16.0f, 32.0f, 64.0f }, (__m256){ -0.0f, 64.0f, 32.0f, 16.0f, -8.0f, -4.0f, -2.0f, -1.0f }, (__m256){ -0.0f, -4.0f, 2.0f, 1.0f, -8.0f, -16.0f, 32.0f, 64.0f }), -0.0f, 60.0f, -62.0f, -63.0f, +56.0f, +48.0f, -32.0f, 0.0f));
|
|
|
|
__m256d test_mm256_fmadd_pd(__m256d a, __m256d b, __m256d c) {
|
|
// CHECK-LABEL: test_mm256_fmadd_pd
|
|
// CHECK: call {{.*}}<4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
|
|
return _mm256_fmadd_pd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m256d(_mm256_fmadd_pd((__m256d){ 0.0, 1.0, -2.0, -4.0 }, (__m256d){ -0.0, 4.0, 2.0, 1.0 }, (__m256d){ -0.0, -4.0, 2.0, 1.0 }), -0.0, 0.0, -2.0, -3.0));
|
|
|
|
__m256 test_mm256_fmsub_ps(__m256 a, __m256 b, __m256 c) {
|
|
// CHECK-LABEL: test_mm256_fmsub_ps
|
|
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.*}}
|
|
// CHECK: call {{.*}}<8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
|
|
return _mm256_fmsub_ps(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m256(_mm256_fmsub_ps((__m256){ 0.0f, 1.0f, -2.0f, -4.0f, -8.0f, -16.0f, 32.0f, 64.0f }, (__m256){ -0.0f, 64.0f, 32.0f, 16.0f, -8.0f, -4.0f, -2.0f, -1.0f }, (__m256){ -0.0f, -4.0f, 2.0f, 1.0f, -8.0f, -16.0f, 32.0f, 64.0f }), 0.0f, 68.0f, -66.0f, -65.0f, 72.0f, 80.0f, -96.0f, -128.0f));
|
|
|
|
__m256d test_mm256_fmsub_pd(__m256d a, __m256d b, __m256d c) {
|
|
// CHECK-LABEL: test_mm256_fmsub_pd
|
|
// CHECK: [[NEG:%.+]] = fneg <4 x double> %{{.+}}
|
|
// CHECK: call {{.*}}<4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
|
|
return _mm256_fmsub_pd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m256d(_mm256_fmsub_pd((__m256d){ 0.0, 1.0, -2.0, -4.0 }, (__m256d){ -0.0, 4.0, 2.0, 1.0 }, (__m256d){ -0.0, -4.0, 2.0, 1.0 }), 0.0, 8.0, -6.0, -5.0));
|
|
|
|
__m256 test_mm256_fnmadd_ps(__m256 a, __m256 b, __m256 c) {
|
|
// CHECK-LABEL: test_mm256_fnmadd_ps
|
|
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.*}}
|
|
// CHECK: call {{.*}}<8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
|
|
return _mm256_fnmadd_ps(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m256(_mm256_fnmadd_ps((__m256){ 0.0f, 1.0f, -2.0f, -4.0f, -8.0f, -16.0f, 32.0f, 64.0f }, (__m256){ -0.0f, 64.0f, 32.0f, 16.0f, -8.0f, -4.0f, -2.0f, -1.0f }, (__m256){ -0.0f, -4.0f, 2.0f, 1.0f, -8.0f, -16.0f, 32.0f, 64.0f }), 0.0f, -68.0f, 66.0f, 65.0f, -72.0f, -80.0f, 96.0f, 128.0f));
|
|
|
|
__m256d test_mm256_fnmadd_pd(__m256d a, __m256d b, __m256d c) {
|
|
// CHECK-LABEL: test_mm256_fnmadd_pd
|
|
// CHECK: [[NEG:%.+]] = fneg <4 x double> %{{.+}}
|
|
// CHECK: call {{.*}}<4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
|
|
return _mm256_fnmadd_pd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m256d(_mm256_fnmadd_pd((__m256d){ 0.0, 1.0, -2.0, -4.0 }, (__m256d){ -0.0, 4.0, 2.0, 1.0 }, (__m256d){ -0.0, -4.0, 2.0, 1.0 }), 0.0, -8.0, 6.0, 5.0));
|
|
|
|
__m256 test_mm256_fnmsub_ps(__m256 a, __m256 b, __m256 c) {
|
|
// CHECK-LABEL: test_mm256_fnmsub_ps
|
|
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.*}}
|
|
// CHECK: [[NEG2:%.+]] = fneg <8 x float> %{{.*}}
|
|
// CHECK: call {{.*}}<8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
|
|
return _mm256_fnmsub_ps(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m256(_mm256_fnmsub_ps((__m256){ 0.0f, 1.0f, -2.0f, -4.0f, -8.0f, -16.0f, 32.0f, 64.0f }, (__m256){ -0.0f, 64.0f, 32.0f, 16.0f, -8.0f, -4.0f, -2.0f, -1.0f }, (__m256){ -0.0f, -4.0f, 2.0f, 1.0f, -8.0f, -16.0f, 32.0f, 64.0f }), 0.0f, -60.0f, 62.0f, 63.0f, -56.0f, -48.0f, 32.0f, 0.0f));
|
|
|
|
__m256d test_mm256_fnmsub_pd(__m256d a, __m256d b, __m256d c) {
|
|
// CHECK-LABEL: test_mm256_fnmsub_pd
|
|
// CHECK: [[NEG:%.+]] = fneg <4 x double> %{{.+}}
|
|
// CHECK: [[NEG2:%.+]] = fneg <4 x double> %{{.+}}
|
|
// CHECK: call {{.*}}<4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
|
|
return _mm256_fnmsub_pd(a, b, c);
|
|
}
|
|
TEST_CONSTEXPR(match_m256d(_mm256_fnmsub_pd((__m256d){ 0.0, 1.0, -2.0, -4.0 }, (__m256d){ -0.0, 4.0, 2.0, 1.0 }, (__m256d){ -0.0, -4.0, 2.0, 1.0 }), 0.0, 0.0, 2.0, 3.0));
|
|
|
|
__m256 test_mm256_fmaddsub_ps(__m256 a, __m256 b, __m256 c) {
|
|
// CHECK-LABEL: test_mm256_fmaddsub_ps
|
|
// CHECK-NOT: fneg
|
|
// CHECK: call {{.*}}<8 x float> @llvm.x86.fma.vfmaddsub.ps.256(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
|
|
return _mm256_fmaddsub_ps(a, b, c);
|
|
}
|
|
|
|
__m256d test_mm256_fmaddsub_pd(__m256d a, __m256d b, __m256d c) {
|
|
// CHECK-LABEL: test_mm256_fmaddsub_pd
|
|
// CHECK-NOT: fneg
|
|
// CHECK: call {{.*}}<4 x double> @llvm.x86.fma.vfmaddsub.pd.256(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
|
|
return _mm256_fmaddsub_pd(a, b, c);
|
|
}
|
|
|
|
__m256 test_mm256_fmsubadd_ps(__m256 a, __m256 b, __m256 c) {
|
|
// CHECK-LABEL: test_mm256_fmsubadd_ps
|
|
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.+}}
|
|
// CHECK: call {{.*}}<8 x float> @llvm.x86.fma.vfmaddsub.ps.256(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> [[NEG]])
|
|
return _mm256_fmsubadd_ps(a, b, c);
|
|
}
|
|
|
|
__m256d test_mm256_fmsubadd_pd(__m256d a, __m256d b, __m256d c) {
|
|
// CHECK-LABEL: test_mm256_fmsubadd_pd
|
|
// CHECK: [[NEG:%.+]] = fneg <4 x double> %{{.+}}
|
|
// CHECK: call {{.*}}<4 x double> @llvm.x86.fma.vfmaddsub.pd.256(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> [[NEG]])
|
|
return _mm256_fmsubadd_pd(a, b, c);
|
|
}
|