diff options
Diffstat (limited to 'test/CodeGen/fma4-builtins.c')
-rw-r--r-- | test/CodeGen/fma4-builtins.c | 76 |
1 files changed, 52 insertions, 24 deletions
diff --git a/test/CodeGen/fma4-builtins.c b/test/CodeGen/fma4-builtins.c index 3ca5fac68892..c848d4a751da 100644 --- a/test/CodeGen/fma4-builtins.c +++ b/test/CodeGen/fma4-builtins.c @@ -17,85 +17,101 @@ __m128d test_mm_macc_pd(__m128d a, __m128d b, __m128d c) { __m128 test_mm_macc_ss(__m128 a, __m128 b, __m128 c) { // CHECK-LABEL: test_mm_macc_ss - // CHECK: @llvm.x86.fma.vfmadd.ss + // CHECK: @llvm.x86.fma4.vfmadd.ss return _mm_macc_ss(a, b, c); } __m128d test_mm_macc_sd(__m128d a, __m128d b, __m128d c) { // CHECK-LABEL: test_mm_macc_sd - // CHECK: @llvm.x86.fma.vfmadd.sd + // CHECK: @llvm.x86.fma4.vfmadd.sd return _mm_macc_sd(a, b, c); } __m128 test_mm_msub_ps(__m128 a, __m128 b, __m128 c) { // CHECK-LABEL: test_mm_msub_ps - // CHECK: @llvm.x86.fma.vfmsub.ps + // CHECK: [[NEG:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.ps(<4 x float> %{{.+}}, <4 x float> %{{.+}}, <4 x float> [[NEG]]) return _mm_msub_ps(a, b, c); } __m128d test_mm_msub_pd(__m128d a, __m128d b, __m128d c) { // CHECK-LABEL: test_mm_msub_pd - // CHECK: @llvm.x86.fma.vfmsub.pd + // CHECK: [[NEG:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.pd(<2 x double> %{{.+}}, <2 x double> %{{.+}}, <2 x double> [[NEG]]) return _mm_msub_pd(a, b, c); } __m128 test_mm_msub_ss(__m128 a, __m128 b, __m128 c) { // CHECK-LABEL: test_mm_msub_ss - // CHECK: @llvm.x86.fma.vfmsub.ss + // CHECK: [[NEG:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma4.vfmadd.ss(<4 x float> %{{.+}}, <4 x float> %{{.+}}, <4 x float> [[NEG]]) return _mm_msub_ss(a, b, c); } __m128d test_mm_msub_sd(__m128d a, __m128d b, __m128d c) { // CHECK-LABEL: test_mm_msub_sd - // CHECK: @llvm.x86.fma.vfmsub.sd + // CHECK: [[NEG:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma4.vfmadd.sd(<2 x double> %{{.+}}, <2 x double> %{{.+}}, <2 x double> [[NEG]]) return _mm_msub_sd(a, b, c); } __m128 test_mm_nmacc_ps(__m128 a, __m128 b, __m128 c) { // CHECK-LABEL: test_mm_nmacc_ps - // CHECK: @llvm.x86.fma.vfnmadd.ps + // CHECK: [[NEG:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.ps(<4 x float> [[NEG]], <4 x float> %{{.+}}, <4 x float> %{{.+}}) return _mm_nmacc_ps(a, b, c); } __m128d test_mm_nmacc_pd(__m128d a, __m128d b, __m128d c) { // CHECK-LABEL: test_mm_nmacc_pd - // CHECK: @llvm.x86.fma.vfnmadd.pd + // CHECK: [[NEG:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.pd(<2 x double> [[NEG]], <2 x double> %{{.+}}, <2 x double> %{{.+}}) return _mm_nmacc_pd(a, b, c); } __m128 test_mm_nmacc_ss(__m128 a, __m128 b, __m128 c) { // CHECK-LABEL: test_mm_nmacc_ss - // CHECK: @llvm.x86.fma.vfnmadd.ss + // CHECK: [[NEG:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma4.vfmadd.ss(<4 x float> [[NEG]], <4 x float> %{{.+}}, <4 x float> %{{.+}}) return _mm_nmacc_ss(a, b, c); } __m128d test_mm_nmacc_sd(__m128d a, __m128d b, __m128d c) { // CHECK-LABEL: test_mm_nmacc_sd - // CHECK: @llvm.x86.fma.vfnmadd.sd + // CHECK: [[NEG:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma4.vfmadd.sd(<2 x double> [[NEG]], <2 x double> %{{.+}}, <2 x double> %{{.+}}) return _mm_nmacc_sd(a, b, c); } __m128 test_mm_nmsub_ps(__m128 a, __m128 b, __m128 c) { // CHECK-LABEL: test_mm_nmsub_ps - // CHECK: @llvm.x86.fma.vfnmsub.ps + // CHECK: [[NEG:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: [[NEG2:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.ps(<4 x float> [[NEG]], <4 x float> %{{.+}}, <4 x float> [[NEG2]]) return _mm_nmsub_ps(a, b, c); } __m128d test_mm_nmsub_pd(__m128d a, __m128d b, __m128d c) { // CHECK-LABEL: test_mm_nmsub_pd - // CHECK: @llvm.x86.fma.vfnmsub.pd + // CHECK: [[NEG:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: [[NEG2:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.pd(<2 x double> [[NEG]], <2 x double> %{{.+}}, <2 x double> [[NEG2]]) return _mm_nmsub_pd(a, b, c); } __m128 test_mm_nmsub_ss(__m128 a, __m128 b, __m128 c) { // CHECK-LABEL: test_mm_nmsub_ss - // CHECK: @llvm.x86.fma.vfnmsub.ss + // CHECK: [[NEG:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: [[NEG2:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma4.vfmadd.ss(<4 x float> [[NEG]], <4 x float> %{{.+}}, <4 x float> [[NEG2]]) return _mm_nmsub_ss(a, b, c); } __m128d test_mm_nmsub_sd(__m128d a, __m128d b, __m128d c) { // CHECK-LABEL: test_mm_nmsub_sd - // CHECK: @llvm.x86.fma.vfnmsub.sd + // CHECK: [[NEG:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: [[NEG2:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma4.vfmadd.sd(<2 x double> [[NEG]], <2 x double> %{{.+}}, <2 x double> [[NEG2]]) return _mm_nmsub_sd(a, b, c); } @@ -113,13 +129,15 @@ __m128d test_mm_maddsub_pd(__m128d a, __m128d b, __m128d c) { __m128 test_mm_msubadd_ps(__m128 a, __m128 b, __m128 c) { // CHECK-LABEL: test_mm_msubadd_ps - // CHECK: @llvm.x86.fma.vfmsubadd.ps + // CHECK: [[NEG:%.+]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmaddsub.ps(<4 x float> %{{.+}}, <4 x float> %{{.+}}, <4 x float> [[NEG]]) return _mm_msubadd_ps(a, b, c); } __m128d test_mm_msubadd_pd(__m128d a, __m128d b, __m128d c) { // CHECK-LABEL: test_mm_msubadd_pd - // CHECK: @llvm.x86.fma.vfmsubadd.pd + // CHECK: [[NEG:%.+]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmaddsub.pd(<2 x double> %{{.+}}, <2 x double> %{{.+}}, <2 x double> [[NEG]]) return _mm_msubadd_pd(a, b, c); } @@ -137,37 +155,45 @@ __m256d test_mm256_macc_pd(__m256d a, __m256d b, __m256d c) { __m256 test_mm256_msub_ps(__m256 a, __m256 b, __m256 c) { // CHECK-LABEL: test_mm256_msub_ps - // CHECK: @llvm.x86.fma.vfmsub.ps.256 + // CHECK: [[NEG:%.+]] = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.*}} + // CHECK: @llvm.x86.fma.vfmadd.ps.256(<8 x float> %{{.+}}, <8 x float> %{{.+}}, <8 x float> [[NEG]]) return _mm256_msub_ps(a, b, c); } __m256d test_mm256_msub_pd(__m256d a, __m256d b, __m256d c) { // CHECK-LABEL: test_mm256_msub_pd - // CHECK: @llvm.x86.fma.vfmsub.pd.256 + // CHECK: [[NEG:%.+]] = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.pd.256(<4 x double> %{{.+}}, <4 x double> %{{.+}}, <4 x double> [[NEG]]) return _mm256_msub_pd(a, b, c); } __m256 test_mm256_nmacc_ps(__m256 a, __m256 b, __m256 c) { // CHECK-LABEL: test_mm256_nmacc_ps - // CHECK: @llvm.x86.fma.vfnmadd.ps.256 + // CHECK: [[NEG:%.+]] = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.*}} + // CHECK: @llvm.x86.fma.vfmadd.ps.256(<8 x float> [[NEG]], <8 x float> %{{.+}}, <8 x float> %{{.+}}) return _mm256_nmacc_ps(a, b, c); } __m256d test_mm256_nmacc_pd(__m256d a, __m256d b, __m256d c) { // CHECK-LABEL: test_mm256_nmacc_pd - // CHECK: @llvm.x86.fma.vfnmadd.pd.256 + // CHECK: [[NEG:%.+]] = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.pd.256(<4 x double> [[NEG]], <4 x double> %{{.+}}, <4 x double> %{{.+}}) return _mm256_nmacc_pd(a, b, c); } __m256 test_mm256_nmsub_ps(__m256 a, __m256 b, __m256 c) { // CHECK-LABEL: test_mm256_nmsub_ps - // CHECK: @llvm.x86.fma.vfnmsub.ps.256 + // CHECK: [[NEG:%.+]] = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.*}} + // CHECK: [[NEG2:%.+]] = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.*}} + // CHECK: @llvm.x86.fma.vfmadd.ps.256(<8 x float> [[NEG]], <8 x float> %{{.+}}, <8 x float> [[NEG2]]) return _mm256_nmsub_ps(a, b, c); } __m256d test_mm256_nmsub_pd(__m256d a, __m256d b, __m256d c) { // CHECK-LABEL: test_mm256_nmsub_pd - // CHECK: @llvm.x86.fma.vfnmsub.pd.256 + // CHECK: [[NEG:%.+]] = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: [[NEG2:%.+]] = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmadd.pd.256(<4 x double> [[NEG]], <4 x double> %{{.+}}, <4 x double> [[NEG2]]) return _mm256_nmsub_pd(a, b, c); } @@ -185,12 +211,14 @@ __m256d test_mm256_maddsub_pd(__m256d a, __m256d b, __m256d c) { __m256 test_mm256_msubadd_ps(__m256 a, __m256 b, __m256 c) { // CHECK-LABEL: test_mm256_msubadd_ps - // CHECK: @llvm.x86.fma.vfmsubadd.ps.256 + // CHECK: [[NEG:%.+]] = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{.*}} + // CHECK: @llvm.x86.fma.vfmaddsub.ps.256(<8 x float> %{{.*}}, <8 x float> %{{.+}}, <8 x float> [[NEG]]) return _mm256_msubadd_ps(a, b, c); } __m256d test_mm256_msubadd_pd(__m256d a, __m256d b, __m256d c) { // CHECK-LABEL: test_mm256_msubadd_pd - // CHECK: @llvm.x86.fma.vfmsubadd.pd.256 + // CHECK: [[NEG:%.+]] = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %{{.+}} + // CHECK: @llvm.x86.fma.vfmaddsub.pd.256(<4 x double> %{{.+}}, <4 x double> %{{.+}}, <4 x double> [[NEG]]) return _mm256_msubadd_pd(a, b, c); } |