mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-08-03 08:20:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add Intel intrinsics headers

Browse source
This commit is contained in:
Justine Tunney 2023-04-27 02:56:41 -07:00
parent 369f9740de
commit b7bf052a4b
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
121 changed files with 47114 additions and 849 deletions
Download patch file Download diff file Expand all files Collapse all files

75
third_party/intel/f16cintrin.internal.h vendored Normal file
View file

@ -0,0 +1,75 @@
#if !defined _X86INTRIN_H_INCLUDED && !defined _IMMINTRIN_H_INCLUDED
#error \
"Never use <f16intrin.h> directly; include <x86intrin.h> or <immintrin.h> instead."
#endif
#ifndef _F16CINTRIN_H_INCLUDED
#define _F16CINTRIN_H_INCLUDED
#ifndef __F16C__
#pragma GCC push_options
#pragma GCC target("f16c")
#define __DISABLE_F16C__
#endif /* __F16C__ */
extern __inline float
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_cvtsh_ss(unsigned short __S) {
__v8hi __H = __extension__(__v8hi){(short)__S, 0, 0, 0, 0, 0, 0, 0};
__v4sf __A = __builtin_ia32_vcvtph2ps(__H);
return __builtin_ia32_vec_ext_v4sf(__A, 0);
}
extern __inline __m128
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtph_ps(__m128i __A) {
return (__m128)__builtin_ia32_vcvtph2ps((__v8hi)__A);
}
extern __inline __m256
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtph_ps(__m128i __A) {
return (__m256)__builtin_ia32_vcvtph2ps256((__v8hi)__A);
}
#ifdef __OPTIMIZE__
extern __inline unsigned short
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_cvtss_sh(float __F, const int __I) {
__v4sf __A = __extension__(__v4sf){__F, 0, 0, 0};
__v8hi __H = __builtin_ia32_vcvtps2ph(__A, __I);
return (unsigned short)__builtin_ia32_vec_ext_v8hi(__H, 0);
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtps_ph(__m128 __A, const int __I) {
return (__m128i)__builtin_ia32_vcvtps2ph((__v4sf)__A, __I);
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtps_ph(__m256 __A, const int __I) {
return (__m128i)__builtin_ia32_vcvtps2ph256((__v8sf)__A, __I);
}
#else
#define _cvtss_sh(__F, __I) \
(__extension__({ \
__v4sf __A = __extension__(__v4sf){__F, 0, 0, 0}; \
__v8hi __H = __builtin_ia32_vcvtps2ph(__A, __I); \
(unsigned short)__builtin_ia32_vec_ext_v8hi(__H, 0); \
}))
#define _mm_cvtps_ph(A, I) \
((__m128i)__builtin_ia32_vcvtps2ph((__v4sf)(__m128)A, (int)(I)))
#define _mm256_cvtps_ph(A, I) \
((__m128i)__builtin_ia32_vcvtps2ph256((__v8sf)(__m256)A, (int)(I)))
#endif /* __OPTIMIZE */
#ifdef __DISABLE_F16C__
#undef __DISABLE_F16C__
#pragma GCC pop_options
#endif /* __DISABLE_F16C__ */
#endif /* _F16CINTRIN_H_INCLUDED */