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
62 lines
2.6 KiB
C
62 lines
2.6 KiB
C
// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +sse4a -emit-llvm -o - -Wall -Werror | FileCheck %s
|
|
// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=i386-apple-darwin -target-feature +sse4a -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 +sse4a -emit-llvm -o - -Wall -Werror | FileCheck %s
|
|
// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=i386-apple-darwin -target-feature +sse4a -emit-llvm -o - -Wall -Werror | FileCheck %s
|
|
|
|
|
|
#include <x86intrin.h>
|
|
|
|
// NOTE: This should match the tests in llvm/test/CodeGen/X86/sse4a-intrinsics-fast-isel.ll
|
|
|
|
__m128i test_mm_extracti_si64(__m128i x) {
|
|
// CHECK-LABEL: test_mm_extracti_si64
|
|
// CHECK: call {{.*}}<2 x i64> @llvm.x86.sse4a.extrqi(<2 x i64> %{{[^,]+}}, i8 3, i8 2)
|
|
return _mm_extracti_si64(x, 3, 2);
|
|
}
|
|
|
|
__m128i test_mm_extract_si64(__m128i x, __m128i y) {
|
|
// CHECK-LABEL: test_mm_extract_si64
|
|
// CHECK: call {{.*}}<2 x i64> @llvm.x86.sse4a.extrq(<2 x i64> %{{[^,]+}}, <16 x i8> %{{[^,]+}})
|
|
return _mm_extract_si64(x, y);
|
|
}
|
|
|
|
__m128i test_mm_inserti_si64(__m128i x, __m128i y) {
|
|
// CHECK-LABEL: test_mm_inserti_si64
|
|
// CHECK: call {{.*}}<2 x i64> @llvm.x86.sse4a.insertqi(<2 x i64> %{{[^,]+}}, <2 x i64> %{{[^,]+}}, i8 5, i8 6)
|
|
return _mm_inserti_si64(x, y, 5, 6);
|
|
}
|
|
|
|
__m128i test_mm_insert_si64(__m128i x, __m128i y) {
|
|
// CHECK-LABEL: test_mm_insert_si64
|
|
// CHECK: call {{.*}}<2 x i64> @llvm.x86.sse4a.insertq(<2 x i64> %{{[^,]+}}, <2 x i64> %{{[^,]+}})
|
|
return _mm_insert_si64(x, y);
|
|
}
|
|
|
|
void test_mm_stream_sd(double *p, __m128d a) {
|
|
// CHECK-LABEL: test_mm_stream_sd
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
|
|
// CHECK: store double %{{.*}}, ptr %{{.*}}, align 1, !nontemporal
|
|
_mm_stream_sd(p, a);
|
|
}
|
|
|
|
void test_mm_stream_sd_void(void *p, __m128d a) {
|
|
// CHECK-LABEL: test_mm_stream_sd_void
|
|
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
|
|
// CHECK: store double %{{.*}}, ptr %{{.*}}, align 1, !nontemporal
|
|
_mm_stream_sd(p, a);
|
|
}
|
|
|
|
void test_mm_stream_ss(float *p, __m128 a) {
|
|
// CHECK-LABEL: test_mm_stream_ss
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
|
|
// CHECK: store float %{{.*}}, ptr %{{.*}}, align 1, !nontemporal
|
|
_mm_stream_ss(p, a);
|
|
}
|
|
|
|
void test_mm_stream_s_void(void *p, __m128 a) {
|
|
// CHECK-LABEL: test_mm_stream_s_void
|
|
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
|
|
// CHECK: store float %{{.*}}, ptr %{{.*}}, align 1, !nontemporal
|
|
_mm_stream_ss(p, a);
|
|
}
|