mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-07-04 02:08:30 +00:00
Add Intel intrinsics headers
This commit is contained in:
Justine Tunney
parent
369f9740de
commit
b7bf052a4b
121 changed files with 47114 additions and 849 deletions
248
third_party/intel/fma4intrin.internal.h
vendored
Normal file
248
third_party/intel/fma4intrin.internal.h
vendored
Normal file
|
|
@ -0,0 +1,248 @@
|
|||
#ifndef _X86INTRIN_H_INCLUDED
|
||||
#error "Never use <fma4intrin.h> directly; include <x86intrin.h> instead."
|
||||
#endif
|
||||
|
||||
#ifndef _FMA4INTRIN_H_INCLUDED
|
||||
#define _FMA4INTRIN_H_INCLUDED
|
||||
|
||||
#include "third_party/intel/ammintrin.internal.h"
|
||||
|
||||
#ifndef __FMA4__
|
||||
#pragma GCC push_options
|
||||
#pragma GCC target("fma4")
|
||||
#define __DISABLE_FMA4__
|
||||
#endif /* __FMA4__ */
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_macc_ps(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddps((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_macc_pd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddpd((__v2df)__A, (__v2df)__B,
|
||||
(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_macc_ss(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_macc_sd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddsd((__v2df)__A, (__v2df)__B,
|
||||
(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_msub_ps(__m128 __A, __m128 __B, __m128 __C)
|
||||
|
||||
{
|
||||
return (__m128)__builtin_ia32_vfmaddps((__v4sf)__A, (__v4sf)__B,
|
||||
-(__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_msub_pd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddpd((__v2df)__A, (__v2df)__B,
|
||||
-(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_msub_ss(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddss((__v4sf)__A, (__v4sf)__B,
|
||||
-(__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_msub_sd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddsd((__v2df)__A, (__v2df)__B,
|
||||
-(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_nmacc_ps(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddps(-(__v4sf)__A, (__v4sf)__B,
|
||||
(__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_nmacc_pd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddpd(-(__v2df)__A, (__v2df)__B,
|
||||
(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_nmacc_ss(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddss(-(__v4sf)__A, (__v4sf)__B,
|
||||
(__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_nmacc_sd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddsd(-(__v2df)__A, (__v2df)__B,
|
||||
(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_nmsub_ps(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddps(-(__v4sf)__A, (__v4sf)__B,
|
||||
-(__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_nmsub_pd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddpd(-(__v2df)__A, (__v2df)__B,
|
||||
-(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_nmsub_ss(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddss(-(__v4sf)__A, (__v4sf)__B,
|
||||
-(__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_nmsub_sd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddsd(-(__v2df)__A, (__v2df)__B,
|
||||
-(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maddsub_ps(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddsubps((__v4sf)__A, (__v4sf)__B,
|
||||
(__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maddsub_pd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddsubpd((__v2df)__A, (__v2df)__B,
|
||||
(__v2df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_msubadd_ps(__m128 __A, __m128 __B, __m128 __C) {
|
||||
return (__m128)__builtin_ia32_vfmaddsubps((__v4sf)__A, (__v4sf)__B,
|
||||
-(__v4sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m128d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_msubadd_pd(__m128d __A, __m128d __B, __m128d __C) {
|
||||
return (__m128d)__builtin_ia32_vfmaddsubpd((__v2df)__A, (__v2df)__B,
|
||||
-(__v2df)__C);
|
||||
}
|
||||
|
||||
/* 256b Floating point multiply/add type instructions. */
|
||||
extern __inline __m256
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_macc_ps(__m256 __A, __m256 __B, __m256 __C) {
|
||||
return (__m256)__builtin_ia32_vfmaddps256((__v8sf)__A, (__v8sf)__B,
|
||||
(__v8sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_macc_pd(__m256d __A, __m256d __B, __m256d __C) {
|
||||
return (__m256d)__builtin_ia32_vfmaddpd256((__v4df)__A, (__v4df)__B,
|
||||
(__v4df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_msub_ps(__m256 __A, __m256 __B, __m256 __C)
|
||||
|
||||
{
|
||||
return (__m256)__builtin_ia32_vfmaddps256((__v8sf)__A, (__v8sf)__B,
|
||||
-(__v8sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_msub_pd(__m256d __A, __m256d __B, __m256d __C) {
|
||||
return (__m256d)__builtin_ia32_vfmaddpd256((__v4df)__A, (__v4df)__B,
|
||||
-(__v4df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_nmacc_ps(__m256 __A, __m256 __B, __m256 __C) {
|
||||
return (__m256)__builtin_ia32_vfmaddps256(-(__v8sf)__A, (__v8sf)__B,
|
||||
(__v8sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_nmacc_pd(__m256d __A, __m256d __B, __m256d __C) {
|
||||
return (__m256d)__builtin_ia32_vfmaddpd256(-(__v4df)__A, (__v4df)__B,
|
||||
(__v4df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_nmsub_ps(__m256 __A, __m256 __B, __m256 __C) {
|
||||
return (__m256)__builtin_ia32_vfmaddps256(-(__v8sf)__A, (__v8sf)__B,
|
||||
-(__v8sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_nmsub_pd(__m256d __A, __m256d __B, __m256d __C) {
|
||||
return (__m256d)__builtin_ia32_vfmaddpd256(-(__v4df)__A, (__v4df)__B,
|
||||
-(__v4df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_maddsub_ps(__m256 __A, __m256 __B, __m256 __C) {
|
||||
return (__m256)__builtin_ia32_vfmaddsubps256((__v8sf)__A, (__v8sf)__B,
|
||||
(__v8sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_maddsub_pd(__m256d __A, __m256d __B, __m256d __C) {
|
||||
return (__m256d)__builtin_ia32_vfmaddsubpd256((__v4df)__A, (__v4df)__B,
|
||||
(__v4df)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_msubadd_ps(__m256 __A, __m256 __B, __m256 __C) {
|
||||
return (__m256)__builtin_ia32_vfmaddsubps256((__v8sf)__A, (__v8sf)__B,
|
||||
-(__v8sf)__C);
|
||||
}
|
||||
|
||||
extern __inline __m256d
|
||||
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_msubadd_pd(__m256d __A, __m256d __B, __m256d __C) {
|
||||
return (__m256d)__builtin_ia32_vfmaddsubpd256((__v4df)__A, (__v4df)__B,
|
||||
-(__v4df)__C);
|
||||
}
|
||||
|
||||
#ifdef __DISABLE_FMA4__
|
||||
#undef __DISABLE_FMA4__
|
||||
#pragma GCC pop_options
|
||||
#endif /* __DISABLE_FMA4__ */
|
||||
|
||||
#endif
|
||||
Loading…
Add table
Add a link
Reference in a new issue