diff options
Diffstat (limited to 'gcc/config/i386/avx10_2minmaxintrin.h')
| -rw-r--r-- | gcc/config/i386/avx10_2minmaxintrin.h | 330 |
1 files changed, 75 insertions, 255 deletions
diff --git a/gcc/config/i386/avx10_2minmaxintrin.h b/gcc/config/i386/avx10_2minmaxintrin.h index 278ad05..0a4a253 100644 --- a/gcc/config/i386/avx10_2minmaxintrin.h +++ b/gcc/config/i386/avx10_2minmaxintrin.h @@ -23,11 +23,11 @@ #ifndef _AVX10_2MINMAXINTRIN_H_INCLUDED #define _AVX10_2MINMAXINTRIN_H_INCLUDED -#if !defined(__AVX10_2_256__) +#if !defined(__AVX10_2__) #pragma GCC push_options #pragma GCC target("avx10.2") -#define __DISABLE_AVX10_2_256__ -#endif /* __AVX10_2_256__ */ +#define __DISABLE_AVX10_2__ +#endif /* __AVX10_2__ */ #ifdef __OPTIMIZE__ extern __inline __m128bh @@ -143,10 +143,10 @@ extern __inline __m256d __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_minmax_pd (__m256d __A, __m256d __B, const int __C) { - return (__m256d) __builtin_ia32_minmaxpd256_mask_round ( + return (__m256d) __builtin_ia32_minmaxpd256_mask ( (__v4df) __A, (__v4df) __B, __C, (__v4df) (__m256d) _mm256_undefined_pd (), - (__mmask8) -1, _MM_FROUND_CUR_DIRECTION); + (__mmask8) -1); } extern __inline __m256d @@ -154,50 +154,19 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_minmax_pd (__m256d __W, __mmask8 __U, __m256d __A, __m256d __B, const int __C) { - return (__m256d) __builtin_ia32_minmaxpd256_mask_round ( + return (__m256d) __builtin_ia32_minmaxpd256_mask ( (__v4df) __A, (__v4df) __B, __C, (__v4df) __W, - (__mmask8) __U, _MM_FROUND_CUR_DIRECTION); + (__mmask8) __U); } extern __inline __m256d __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_maskz_minmax_pd (__mmask8 __U, __m256d __A, __m256d __B, const int __C) { - return (__m256d) __builtin_ia32_minmaxpd256_mask_round ( + return (__m256d) __builtin_ia32_minmaxpd256_mask ( (__v4df) __A, (__v4df) __B, __C, (__v4df) (__m256d) _mm256_setzero_pd (), - (__mmask8) __U, _MM_FROUND_CUR_DIRECTION); -} - -extern __inline __m256d -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_minmax_round_pd (__m256d __A, __m256d __B, const int __C, const int __R) -{ - return (__m256d) __builtin_ia32_minmaxpd256_mask_round ( - (__v4df) __A, (__v4df) __B, __C, - (__v4df) (__m256d) _mm256_undefined_pd (), - (__mmask8) -1, __R); -} - -extern __inline __m256d -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_mask_minmax_round_pd (__m256d __W, __mmask8 __U, __m256d __A, - __m256d __B, const int __C, const int __R) -{ - return (__m256d) __builtin_ia32_minmaxpd256_mask_round ( - (__v4df) __A, (__v4df) __B, __C, (__v4df) __W, - (__mmask8) __U, __R); -} - -extern __inline __m256d -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_minmax_round_pd (__mmask8 __U, __m256d __A, __m256d __B, - const int __C, const int __R) -{ - return (__m256d) __builtin_ia32_minmaxpd256_mask_round ( - (__v4df) __A, (__v4df) __B, __C, - (__v4df) (__m256d) _mm256_setzero_pd (), - (__mmask8) __U, __R); + (__mmask8) __U); } extern __inline __m128h @@ -240,10 +209,10 @@ extern __inline __m256h __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_minmax_ph (__m256h __A, __m256h __B, const int __C) { - return (__m256h) __builtin_ia32_minmaxph256_mask_round ( + return (__m256h) __builtin_ia32_minmaxph256_mask ( (__v16hf) __A, (__v16hf) __B, __C, (__v16hf) (__m256h) _mm256_undefined_ph (), - (__mmask16) -1, _MM_FROUND_CUR_DIRECTION); + (__mmask16) -1); } extern __inline __m256h @@ -251,50 +220,19 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_minmax_ph (__m256h __W, __mmask16 __U, __m256h __A, __m256h __B, const int __C) { - return (__m256h) __builtin_ia32_minmaxph256_mask_round ( + return (__m256h) __builtin_ia32_minmaxph256_mask ( (__v16hf) __A, (__v16hf) __B, __C, (__v16hf) __W, - (__mmask16) __U, _MM_FROUND_CUR_DIRECTION); + (__mmask16) __U); } extern __inline __m256h __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_maskz_minmax_ph (__mmask16 __U, __m256h __A, __m256h __B, const int __C) { - return (__m256h) __builtin_ia32_minmaxph256_mask_round ( + return (__m256h) __builtin_ia32_minmaxph256_mask ( (__v16hf) __A, (__v16hf) __B, __C, (__v16hf) (__m256h) _mm256_setzero_ph (), - (__mmask16) __U, _MM_FROUND_CUR_DIRECTION); -} - -extern __inline __m256h -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_minmax_round_ph (__m256h __A, __m256h __B, const int __C, const int __R) -{ - return (__m256h) __builtin_ia32_minmaxph256_mask_round ( - (__v16hf) __A, (__v16hf) __B, __C, - (__v16hf) (__m256h) _mm256_undefined_ph (), - (__mmask16) -1, __R); -} - -extern __inline __m256h -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_mask_minmax_round_ph (__m256h __W, __mmask16 __U, __m256h __A, - __m256h __B, const int __C, const int __R) -{ - return (__m256h) __builtin_ia32_minmaxph256_mask_round ( - (__v16hf) __A, (__v16hf) __B, __C, (__v16hf) __W, - (__mmask16) __U, __R); -} - -extern __inline __m256h -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_minmax_round_ph (__mmask16 __U, __m256h __A, __m256h __B, - const int __C, const int __R) -{ - return (__m256h) __builtin_ia32_minmaxph256_mask_round ( - (__v16hf) __A, (__v16hf) __B, __C, - (__v16hf) (__m256h) _mm256_setzero_ph (), - (__mmask16) __U, __R); + (__mmask16) __U); } extern __inline __m128 @@ -337,10 +275,10 @@ extern __inline __m256 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_minmax_ps (__m256 __A, __m256 __B, const int __C) { - return (__m256) __builtin_ia32_minmaxps256_mask_round ( + return (__m256) __builtin_ia32_minmaxps256_mask ( (__v8sf) __A, (__v8sf) __B, __C, (__v8sf) (__m256) _mm256_undefined_ps (), - (__mmask8) -1, _MM_FROUND_CUR_DIRECTION); + (__mmask8) -1); } extern __inline __m256 @@ -348,50 +286,19 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_mask_minmax_ps (__m256 __W, __mmask8 __U, __m256 __A, __m256 __B, const int __C) { - return (__m256) __builtin_ia32_minmaxps256_mask_round ( + return (__m256) __builtin_ia32_minmaxps256_mask ( (__v8sf) __A, (__v8sf) __B, __C, (__v8sf) __W, - (__mmask8) __U, _MM_FROUND_CUR_DIRECTION); + (__mmask8) __U); } extern __inline __m256 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm256_maskz_minmax_ps (__mmask8 __U, __m256 __A, __m256 __B, const int __C) { - return (__m256) __builtin_ia32_minmaxps256_mask_round ( + return (__m256) __builtin_ia32_minmaxps256_mask ( (__v8sf) __A, (__v8sf) __B, __C, (__v8sf) (__m256) _mm256_setzero_ps (), - (__mmask8) __U, _MM_FROUND_CUR_DIRECTION); -} - -extern __inline __m256 -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_minmax_round_ps (__m256 __A, __m256 __B, const int __C, const int __R) -{ - return (__m256) __builtin_ia32_minmaxps256_mask_round ( - (__v8sf) __A, (__v8sf) __B, __C, - (__v8sf) (__m256) _mm256_undefined_ps (), - (__mmask8) -1, __R); -} - -extern __inline __m256 -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_mask_minmax_round_ps (__m256 __W, __mmask8 __U, __m256 __A, __m256 __B, - const int __C, const int __R) -{ - return (__m256) __builtin_ia32_minmaxps256_mask_round ( - (__v8sf) __A, (__v8sf) __B, __C, (__v8sf) __W, - (__mmask8) __U, __R); -} - -extern __inline __m256 -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_maskz_minmax_round_ps (__mmask8 __U, __m256 __A, __m256 __B, - const int __C, const int __R) -{ - return (__m256) __builtin_ia32_minmaxps256_mask_round ( - (__v8sf) __A, (__v8sf) __B, __C, - (__v8sf) (__m256) _mm256_setzero_ps (), - (__mmask8) __U, __R); + (__mmask8) __U); } extern __inline __m128d @@ -697,56 +604,27 @@ _mm_maskz_minmax_round_ss (__mmask8 __U, __m128 __A, __m128 __B, (__mmask8) (U))) #define _mm256_minmax_pd(A, B, C) \ - ((__m256d) __builtin_ia32_minmaxpd256_mask_round ((__v4df) (A), \ - (__v4df) (B), \ - (int) (C), \ - (__v4df) (__m256d) \ - _mm256_undefined_pd (), \ - (__mmask8) (-1), \ - _MM_FROUND_CUR_DIRECTION)) + ((__m256d) __builtin_ia32_minmaxpd256_mask ((__v4df) (A), \ + (__v4df) (B), \ + (int) (C), \ + (__v4df) (__m256d) \ + _mm256_undefined_pd (), \ + (__mmask8) (-1))) #define _mm256_mask_minmax_pd(W, U, A, B, C) \ - ((__m256d) __builtin_ia32_minmaxpd256_mask_round ((__v4df) (A), \ - (__v4df) (B), \ - (int) (C), \ - (__v4df) (__m256d) (W), \ - (__mmask8) (U), \ - _MM_FROUND_CUR_DIRECTION)) + ((__m256d) __builtin_ia32_minmaxpd256_mask ((__v4df) (A), \ + (__v4df) (B), \ + (int) (C), \ + (__v4df) (__m256d) (W), \ + (__mmask8) (U))) #define _mm256_maskz_minmax_pd(U, A, B, C) \ - ((__m256d) __builtin_ia32_minmaxpd256_mask_round ((__v4df) (A), \ - (__v4df) (B), \ - (int) (C), \ - (__v4df) (__m256d) \ - _mm256_setzero_pd (), \ - (__mmask8) (U), \ - _MM_FROUND_CUR_DIRECTION)) - -#define _mm256_minmax_round_pd(A, B, C, R) \ - ((__m256d) __builtin_ia32_minmaxpd256_mask_round ((__v4df) (A), \ - (__v4df) (B), \ - (int) (C), \ - (__v4df) (__m256d) \ - _mm256_undefined_pd (), \ - (__mmask8) (-1), \ - (int) (R))) - -#define _mm256_mask_minmax_round_pd(W, U, A, B, C, R) \ - ((__m256d) __builtin_ia32_minmaxpd256_mask_round ((__v4df) (A), \ - (__v4df) (B), \ - (int) (C), \ - (__v4df) (__m256d) (W), \ - (__mmask8) (U), \ - (int) (R))) - -#define _mm256_maskz_minmax_round_pd(U, A, B, C, R) \ - ((__m256d) __builtin_ia32_minmaxpd256_mask_round ((__v4df) (A), \ - (__v4df) (B), \ - (int) (C), \ - (__v4df) (__m256d) \ - _mm256_setzero_pd (), \ - (__mmask8) (U), \ - (int) (R))) + ((__m256d) __builtin_ia32_minmaxpd256_mask ((__v4df) (A), \ + (__v4df) (B), \ + (int) (C), \ + (__v4df) (__m256d) \ + _mm256_setzero_pd (), \ + (__mmask8) (U))) #define _mm_minmax_ph(A, B, C) \ ((__m128h) __builtin_ia32_minmaxph128_mask ((__v8hf) (A), \ @@ -772,56 +650,27 @@ _mm_maskz_minmax_round_ss (__mmask8 __U, __m128 __A, __m128 __B, (__mmask8) (U))) #define _mm256_minmax_ph(A, B, C) \ - ((__m256h) __builtin_ia32_minmaxph256_mask_round ((__v16hf) (A), \ - (__v16hf) (B), \ - (int) (C), \ - (__v16hf) (__m256h) \ - _mm256_undefined_ph (), \ - (__mmask16) (-1), \ - _MM_FROUND_CUR_DIRECTION)) + ((__m256h) __builtin_ia32_minmaxph256_mask ((__v16hf) (A), \ + (__v16hf) (B), \ + (int) (C), \ + (__v16hf) (__m256h) \ + _mm256_undefined_ph (), \ + (__mmask16) (-1))) #define _mm256_mask_minmax_ph(W, U, A, B, C) \ - ((__m256h) __builtin_ia32_minmaxph256_mask_round ((__v16hf) (A), \ - (__v16hf) (B), \ - (int) (C), \ - (__v16hf) (__m256h) (W), \ - (__mmask16) (U), \ - _MM_FROUND_CUR_DIRECTION)) + ((__m256h) __builtin_ia32_minmaxph256_mask ((__v16hf) (A), \ + (__v16hf) (B), \ + (int) (C), \ + (__v16hf) (__m256h) (W), \ + (__mmask16) (U))) #define _mm256_maskz_minmax_ph(U, A, B, C) \ - ((__m256h) __builtin_ia32_minmaxph256_mask_round ((__v16hf) (A), \ - (__v16hf) (B), \ - (int) (C), \ - (__v16hf) (__m256h) \ - _mm256_setzero_ph (), \ - (__mmask16) (U), \ - _MM_FROUND_CUR_DIRECTION)) - -#define _mm256_minmax_round_ph(A, B, C, R) \ - ((__m256h) __builtin_ia32_minmaxph256_mask_round ((__v16hf) (A), \ - (__v16hf) (B), \ - (int) (C), \ - (__v16hf) (__m256h) \ - _mm256_undefined_ph (), \ - (__mmask16) (-1), \ - (int) (R))) - -#define _mm256_mask_minmax_round_ph(W, U, A, B, C, R) \ - ((__m256h) __builtin_ia32_minmaxph256_mask_round ((__v16hf) (A), \ - (__v16hf) (B), \ - (int) (C), \ - (__v16hf) (__m256h) (W), \ - (__mmask16) (U), \ - (int) (R))) - -#define _mm256_maskz_minmax_round_ph(U, A, B, C, R) \ - ((__m256h) __builtin_ia32_minmaxph256_mask_round ((__v16hf) (A), \ - (__v16hf) (B), \ - (int) (C), \ - (__v16hf) (__m256h) \ - _mm256_setzero_ph (), \ - (__mmask16) (U), \ - (int) (R))) + ((__m256h) __builtin_ia32_minmaxph256_mask ((__v16hf) (A), \ + (__v16hf) (B), \ + (int) (C), \ + (__v16hf) (__m256h) \ + _mm256_setzero_ph (), \ + (__mmask16) (U))) #define _mm_minmax_ps(A, B, C) \ ((__m128) __builtin_ia32_minmaxps128_mask ((__v4sf) (A), \ @@ -847,56 +696,27 @@ _mm_maskz_minmax_round_ss (__mmask8 __U, __m128 __A, __m128 __B, (__mmask8) (U))) #define _mm256_minmax_ps(A, B, C) \ - ((__m256) __builtin_ia32_minmaxps256_mask_round ((__v8sf) (A), \ - (__v8sf) (B), \ - (int) (C), \ - (__v8sf) (__m256) \ - _mm256_undefined_ps (), \ - (__mmask8) (-1), \ - _MM_FROUND_CUR_DIRECTION)) + ((__m256) __builtin_ia32_minmaxps256_mask ((__v8sf) (A), \ + (__v8sf) (B), \ + (int) (C), \ + (__v8sf) (__m256) \ + _mm256_undefined_ps (), \ + (__mmask8) (-1))) #define _mm256_mask_minmax_ps(W, U, A, B, C) \ - ((__m256) __builtin_ia32_minmaxps256_mask_round ((__v8sf) (A), \ - (__v8sf) (B), \ - (int) (C), \ - (__v8sf) (__m256) (W), \ - (__mmask8) (U), \ - _MM_FROUND_CUR_DIRECTION)) + ((__m256) __builtin_ia32_minmaxps256_mask ((__v8sf) (A), \ + (__v8sf) (B), \ + (int) (C), \ + (__v8sf) (__m256) (W), \ + (__mmask8) (U))) #define _mm256_maskz_minmax_ps(U, A, B, C) \ - ((__m256) __builtin_ia32_minmaxps256_mask_round ((__v8sf) (A), \ - (__v8sf) (B), \ - (int) (C), \ - (__v8sf) (__m256) \ - _mm256_setzero_ps (), \ - (__mmask8) (U), \ - _MM_FROUND_CUR_DIRECTION)) - -#define _mm256_minmax_round_ps(A, B, C, R) \ - ((__m256) __builtin_ia32_minmaxps256_mask_round ((__v8sf) (A), \ - (__v8sf) (B), \ - (int) (C), \ - (__v8sf) (__m256) \ - _mm256_undefined_ps (), \ - (__mmask8) (-1), \ - (int) (R))) - -#define _mm256_mask_minmax_round_ps(W, U, A, B, C, R) \ - ((__m256) __builtin_ia32_minmaxps256_mask_round ((__v8sf) (A), \ - (__v8sf) (B), \ - (int) (C), \ - (__v8sf) (__m256) (W), \ - (__mmask8) (U), \ - (int) (R))) - -#define _mm256_maskz_minmax_round_ps(U, A, B, C, R) \ - ((__m256) __builtin_ia32_minmaxps256_mask_round ((__v8sf) (A), \ - (__v8sf) (B), \ - (int) (C), \ - (__v8sf) (__m256) \ - _mm256_setzero_ps (), \ - (__mmask8) (U), \ - (int) (R))) + ((__m256) __builtin_ia32_minmaxps256_mask ((__v8sf) (A), \ + (__v8sf) (B), \ + (int) (C), \ + (__v8sf) (__m256) \ + _mm256_setzero_ps (), \ + (__mmask8) (U))) #define _mm_minmax_round_sd(A, B, C, R) \ ((__m128d) __builtin_ia32_minmaxsd_mask_round ((__v2df) (A), \ @@ -1056,9 +876,9 @@ _mm_maskz_minmax_round_ss (__mmask8 __U, __m128 __A, __m128 __B, #endif -#ifdef __DISABLE_AVX10_2_256__ -#undef __DISABLE_AVX10_2_256__ +#ifdef __DISABLE_AVX10_2__ +#undef __DISABLE_AVX10_2__ #pragma GCC pop_options -#endif /* __DISABLE_AVX10_2_256__ */ +#endif /* __DISABLE_AVX10_2__ */ #endif /* _AVX10_2MINMAXINTRIN_H_INCLUDED */ |