diff options
Diffstat (limited to 'gcc/config/i386/avxintrin.h')
| -rw-r--r-- | gcc/config/i386/avxintrin.h | 20 |
1 files changed, 12 insertions, 8 deletions
diff --git a/gcc/config/i386/avxintrin.h b/gcc/config/i386/avxintrin.h index 2ea327c..65e2145 100644 --- a/gcc/config/i386/avxintrin.h +++ b/gcc/config/i386/avxintrin.h @@ -41,9 +41,13 @@ typedef double __v4df __attribute__ ((__vector_size__ (32))); typedef float __v8sf __attribute__ ((__vector_size__ (32))); typedef long long __v4di __attribute__ ((__vector_size__ (32))); +typedef unsigned long long __v4du __attribute__ ((__vector_size__ (32))); typedef int __v8si __attribute__ ((__vector_size__ (32))); +typedef unsigned int __v8su __attribute__ ((__vector_size__ (32))); typedef short __v16hi __attribute__ ((__vector_size__ (32))); +typedef unsigned short __v16hu __attribute__ ((__vector_size__ (32))); typedef char __v32qi __attribute__ ((__vector_size__ (32))); +typedef unsigned char __v32qu __attribute__ ((__vector_size__ (32))); /* The Intel API is flexible enough that we must allow aliasing with other vector types, and their scalar components. */ @@ -124,13 +128,13 @@ typedef double __m256d __attribute__ ((__vector_size__ (32), extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm256_add_pd (__m256d __A, __m256d __B) { - return (__m256d) __builtin_ia32_addpd256 ((__v4df)__A, (__v4df)__B); + return (__m256d) ((__v4df)__A + (__v4df)__B); } extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm256_add_ps (__m256 __A, __m256 __B) { - return (__m256) __builtin_ia32_addps256 ((__v8sf)__A, (__v8sf)__B); + return (__m256) ((__v8sf)__A + (__v8sf)__B); } extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__)) @@ -218,13 +222,13 @@ _mm256_blendv_ps (__m256 __X, __m256 __Y, __m256 __M) extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm256_div_pd (__m256d __A, __m256d __B) { - return (__m256d) __builtin_ia32_divpd256 ((__v4df)__A, (__v4df)__B); + return (__m256d) ((__v4df)__A / (__v4df)__B); } extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm256_div_ps (__m256 __A, __m256 __B) { - return (__m256) __builtin_ia32_divps256 ((__v8sf)__A, (__v8sf)__B); + return (__m256) ((__v8sf)__A / (__v8sf)__B); } /* Dot product instructions with mask-defined summing and zeroing parts @@ -295,13 +299,13 @@ _mm256_min_ps (__m256 __A, __m256 __B) extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mul_pd (__m256d __A, __m256d __B) { - return (__m256d) __builtin_ia32_mulpd256 ((__v4df)__A, (__v4df)__B); + return (__m256d) ((__v4df)__A * (__v4df)__B); } extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mul_ps (__m256 __A, __m256 __B) { - return (__m256) __builtin_ia32_mulps256 ((__v8sf)__A, (__v8sf)__B); + return (__m256) ((__v8sf)__A * (__v8sf)__B); } extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__)) @@ -343,13 +347,13 @@ _mm256_shuffle_ps (__m256 __A, __m256 __B, const int __mask) extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm256_sub_pd (__m256d __A, __m256d __B) { - return (__m256d) __builtin_ia32_subpd256 ((__v4df)__A, (__v4df)__B); + return (__m256d) ((__v4df)__A - (__v4df)__B); } extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm256_sub_ps (__m256 __A, __m256 __B) { - return (__m256) __builtin_ia32_subps256 ((__v8sf)__A, (__v8sf)__B); + return (__m256) ((__v8sf)__A - (__v8sf)__B); } extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__)) |