1 // 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
2 // 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
3 // 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
4 // 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
9 // NOTE: This should match the tests in llvm/test/CodeGen/X86/sse4a-intrinsics-fast-isel.ll
11 __m128i
test_mm_extracti_si64(__m128i x
) {
12 // CHECK-LABEL: test_mm_extracti_si64
13 // CHECK: call {{.*}}<2 x i64> @llvm.x86.sse4a.extrqi(<2 x i64> %{{[^,]+}}, i8 3, i8 2)
14 return _mm_extracti_si64(x
, 3, 2);
17 __m128i
test_mm_extract_si64(__m128i x
, __m128i y
) {
18 // CHECK-LABEL: test_mm_extract_si64
19 // CHECK: call {{.*}}<2 x i64> @llvm.x86.sse4a.extrq(<2 x i64> %{{[^,]+}}, <16 x i8> %{{[^,]+}})
20 return _mm_extract_si64(x
, y
);
23 __m128i
test_mm_inserti_si64(__m128i x
, __m128i y
) {
24 // CHECK-LABEL: test_mm_inserti_si64
25 // CHECK: call {{.*}}<2 x i64> @llvm.x86.sse4a.insertqi(<2 x i64> %{{[^,]+}}, <2 x i64> %{{[^,]+}}, i8 5, i8 6)
26 return _mm_inserti_si64(x
, y
, 5, 6);
29 __m128i
test_mm_insert_si64(__m128i x
, __m128i y
) {
30 // CHECK-LABEL: test_mm_insert_si64
31 // CHECK: call {{.*}}<2 x i64> @llvm.x86.sse4a.insertq(<2 x i64> %{{[^,]+}}, <2 x i64> %{{[^,]+}})
32 return _mm_insert_si64(x
, y
);
35 void test_mm_stream_sd(double *p
, __m128d a
) {
36 // CHECK-LABEL: test_mm_stream_sd
37 // CHECK: extractelement <2 x double> %{{.*}}, i64 0
38 // CHECK: store double %{{.*}}, ptr %{{.*}}, align 1, !nontemporal
42 void test_mm_stream_sd_void(void *p
, __m128d a
) {
43 // CHECK-LABEL: test_mm_stream_sd_void
44 // CHECK: extractelement <2 x double> %{{.*}}, i64 0
45 // CHECK: store double %{{.*}}, ptr %{{.*}}, align 1, !nontemporal
49 void test_mm_stream_ss(float *p
, __m128 a
) {
50 // CHECK-LABEL: test_mm_stream_ss
51 // CHECK: extractelement <4 x float> %{{.*}}, i64 0
52 // CHECK: store float %{{.*}}, ptr %{{.*}}, align 1, !nontemporal
56 void test_mm_stream_s_void(void *p
, __m128 a
) {
57 // CHECK-LABEL: test_mm_stream_s_void
58 // CHECK: extractelement <4 x float> %{{.*}}, i64 0
59 // CHECK: store float %{{.*}}, ptr %{{.*}}, align 1, !nontemporal