mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-07-26 04:20:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make the intrinsics more readable

Browse source
This commit is contained in:
Justine Tunney 2023-05-15 23:11:47 -07:00
parent 210187cf77
commit 80db9de173
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
75 changed files with 12444 additions and 21493 deletions
Download patch file Download diff file Expand all files Collapse all files

80
third_party/intel/avx5124fmapsintrin.internal.h vendored
View file

@ -12,109 +12,93 @@
#define __DISABLE_AVX5124FMAPS__
#endif /* __AVX5124FMAPS__ */
extern __inline __m512
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_4fmadd_ps(__m512 __A, __m512 __B, __m512 __C, __m512 __D, __m512 __E,
__m128 *__F) {
__funline __m512 _mm512_4fmadd_ps(__m512 __A, __m512 __B, __m512 __C, __m512 __D,
__m512 __E, __m128 *__F) {
return (__m512)__builtin_ia32_4fmaddps((__v16sf)__B, (__v16sf)__C,
(__v16sf)__D, (__v16sf)__E,
(__v16sf)__A, (const __v4sf *)__F);
}
extern __inline __m512
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_4fmadd_ps(__m512 __A, __mmask16 __U, __m512 __B, __m512 __C,
__m512 __D, __m512 __E, __m128 *__F) {
__funline __m512 _mm512_mask_4fmadd_ps(__m512 __A, __mmask16 __U, __m512 __B,
__m512 __C, __m512 __D, __m512 __E,
__m128 *__F) {
return (__m512)__builtin_ia32_4fmaddps_mask(
(__v16sf)__B, (__v16sf)__C, (__v16sf)__D, (__v16sf)__E, (__v16sf)__A,
(const __v4sf *)__F, (__v16sf)__A, (__mmask16)__U);
}
extern __inline __m512
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_4fmadd_ps(__mmask16 __U, __m512 __A, __m512 __B, __m512 __C,
__m512 __D, __m512 __E, __m128 *__F) {
__funline __m512 _mm512_maskz_4fmadd_ps(__mmask16 __U, __m512 __A, __m512 __B,
__m512 __C, __m512 __D, __m512 __E,
__m128 *__F) {
return (__m512)__builtin_ia32_4fmaddps_mask(
(__v16sf)__B, (__v16sf)__C, (__v16sf)__D, (__v16sf)__E, (__v16sf)__A,
(const __v4sf *)__F, (__v16sf)_mm512_setzero_ps(), (__mmask16)__U);
}
extern __inline __m128
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_4fmadd_ss(__m128 __A, __m128 __B, __m128 __C, __m128 __D, __m128 __E,
__m128 *__F) {
__funline __m128 _mm_4fmadd_ss(__m128 __A, __m128 __B, __m128 __C, __m128 __D,
__m128 __E, __m128 *__F) {
return (__m128)__builtin_ia32_4fmaddss((__v4sf)__B, (__v4sf)__C, (__v4sf)__D,
(__v4sf)__E, (__v4sf)__A,
(const __v4sf *)__F);
}
extern __inline __m128
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_4fmadd_ss(__m128 __A, __mmask8 __U, __m128 __B, __m128 __C,
__m128 __D, __m128 __E, __m128 *__F) {
__funline __m128 _mm_mask_4fmadd_ss(__m128 __A, __mmask8 __U, __m128 __B,
__m128 __C, __m128 __D, __m128 __E,
__m128 *__F) {
return (__m128)__builtin_ia32_4fmaddss_mask(
(__v4sf)__B, (__v4sf)__C, (__v4sf)__D, (__v4sf)__E, (__v4sf)__A,
(const __v4sf *)__F, (__v4sf)__A, (__mmask8)__U);
}
extern __inline __m128
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_4fmadd_ss(__mmask8 __U, __m128 __A, __m128 __B, __m128 __C,
__m128 __D, __m128 __E, __m128 *__F) {
__funline __m128 _mm_maskz_4fmadd_ss(__mmask8 __U, __m128 __A, __m128 __B,
__m128 __C, __m128 __D, __m128 __E,
__m128 *__F) {
return (__m128)__builtin_ia32_4fmaddss_mask(
(__v4sf)__B, (__v4sf)__C, (__v4sf)__D, (__v4sf)__E, (__v4sf)__A,
(const __v4sf *)__F, (__v4sf)_mm_setzero_ps(), (__mmask8)__U);
}
extern __inline __m512
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_4fnmadd_ps(__m512 __A, __m512 __B, __m512 __C, __m512 __D,
__m512 __E, __m128 *__F) {
__funline __m512 _mm512_4fnmadd_ps(__m512 __A, __m512 __B, __m512 __C, __m512 __D,
__m512 __E, __m128 *__F) {
return (__m512)__builtin_ia32_4fnmaddps((__v16sf)__B, (__v16sf)__C,
(__v16sf)__D, (__v16sf)__E,
(__v16sf)__A, (const __v4sf *)__F);
}
extern __inline __m512
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_4fnmadd_ps(__m512 __A, __mmask16 __U, __m512 __B, __m512 __C,
__m512 __D, __m512 __E, __m128 *__F) {
__funline __m512 _mm512_mask_4fnmadd_ps(__m512 __A, __mmask16 __U, __m512 __B,
__m512 __C, __m512 __D, __m512 __E,
__m128 *__F) {
return (__m512)__builtin_ia32_4fnmaddps_mask(
(__v16sf)__B, (__v16sf)__C, (__v16sf)__D, (__v16sf)__E, (__v16sf)__A,
(const __v4sf *)__F, (__v16sf)__A, (__mmask16)__U);
}
extern __inline __m512
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_4fnmadd_ps(__mmask16 __U, __m512 __A, __m512 __B, __m512 __C,
__m512 __D, __m512 __E, __m128 *__F) {
__funline __m512 _mm512_maskz_4fnmadd_ps(__mmask16 __U, __m512 __A, __m512 __B,
__m512 __C, __m512 __D, __m512 __E,
__m128 *__F) {
return (__m512)__builtin_ia32_4fnmaddps_mask(
(__v16sf)__B, (__v16sf)__C, (__v16sf)__D, (__v16sf)__E, (__v16sf)__A,
(const __v4sf *)__F, (__v16sf)_mm512_setzero_ps(), (__mmask16)__U);
}
extern __inline __m128
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_4fnmadd_ss(__m128 __A, __m128 __B, __m128 __C, __m128 __D, __m128 __E,
__m128 *__F) {
__funline __m128 _mm_4fnmadd_ss(__m128 __A, __m128 __B, __m128 __C, __m128 __D,
__m128 __E, __m128 *__F) {
return (__m128)__builtin_ia32_4fnmaddss((__v4sf)__B, (__v4sf)__C, (__v4sf)__D,
(__v4sf)__E, (__v4sf)__A,
(const __v4sf *)__F);
}
extern __inline __m128
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_4fnmadd_ss(__m128 __A, __mmask8 __U, __m128 __B, __m128 __C,
__m128 __D, __m128 __E, __m128 *__F) {
__funline __m128 _mm_mask_4fnmadd_ss(__m128 __A, __mmask8 __U, __m128 __B,
__m128 __C, __m128 __D, __m128 __E,
__m128 *__F) {
return (__m128)__builtin_ia32_4fnmaddss_mask(
(__v4sf)__B, (__v4sf)__C, (__v4sf)__D, (__v4sf)__E, (__v4sf)__A,
(const __v4sf *)__F, (__v4sf)__A, (__mmask8)__U);
}
extern __inline __m128
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_4fnmadd_ss(__mmask8 __U, __m128 __A, __m128 __B, __m128 __C,
__m128 __D, __m128 __E, __m128 *__F) {
__funline __m128 _mm_maskz_4fnmadd_ss(__mmask8 __U, __m128 __A, __m128 __B,
__m128 __C, __m128 __D, __m128 __E,
__m128 *__F) {
return (__m128)__builtin_ia32_4fnmaddss_mask(
(__v4sf)__B, (__v4sf)__C, (__v4sf)__D, (__v4sf)__E, (__v4sf)__A,
(const __v4sf *)__F, (__v4sf)_mm_setzero_ps(), (__mmask8)__U);