mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-07-11 21:49:12 +00:00
Release Cosmopolitan v3.6.0
This release is an atomic upgrade to GCC 14.1.0 with C23 and C++23
This commit is contained in:
Justine Tunney
parent
62ace3623a
commit
5660ec4741
1585 changed files with 117353 additions and 271644 deletions
644
third_party/intel/avx512dqintrin.internal.h
vendored
644
third_party/intel/avx512dqintrin.internal.h
vendored
|
|
@ -4,9 +4,9 @@
|
|||
#endif
|
||||
#ifndef _AVX512DQINTRIN_H_INCLUDED
|
||||
#define _AVX512DQINTRIN_H_INCLUDED
|
||||
#ifndef __AVX512DQ__
|
||||
#if !defined (__AVX512DQ__) || defined (__EVEX512__)
|
||||
#pragma GCC push_options
|
||||
#pragma GCC target("avx512dq")
|
||||
#pragma GCC target("avx512dq,no-evex512")
|
||||
#define __DISABLE_AVX512DQ__
|
||||
#endif
|
||||
extern __inline unsigned char
|
||||
|
|
@ -138,6 +138,330 @@ _kandn_mask8 (__mmask8 __A, __mmask8 __B)
|
|||
{
|
||||
return (__mmask8) __builtin_ia32_kandnqi ((__mmask8) __A, (__mmask8) __B);
|
||||
}
|
||||
#ifdef __OPTIMIZE__
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_kshiftli_mask8 (__mmask8 __A, unsigned int __B)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_kshiftliqi ((__mmask8) __A, (__mmask8) __B);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_kshiftri_mask8 (__mmask8 __A, unsigned int __B)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_kshiftriqi ((__mmask8) __A, (__mmask8) __B);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_reduce_sd (__m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) _mm_avx512_setzero_pd (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_reduce_round_sd (__m128d __A, __m128d __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_avx512_setzero_pd (),
|
||||
(__mmask8) -1, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_reduce_sd (__m128d __W, __mmask8 __U, __m128d __A,
|
||||
__m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) __W,
|
||||
(__mmask8) __U);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_reduce_round_sd (__m128d __W, __mmask8 __U, __m128d __A,
|
||||
__m128d __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) __W,
|
||||
__U, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_reduce_sd (__mmask8 __U, __m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) _mm_avx512_setzero_pd (),
|
||||
(__mmask8) __U);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_reduce_round_sd (__mmask8 __U, __m128d __A, __m128d __B,
|
||||
int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_avx512_setzero_pd (),
|
||||
__U, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_reduce_ss (__m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) _mm_avx512_setzero_ps (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_reduce_round_ss (__m128 __A, __m128 __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_avx512_setzero_ps (),
|
||||
(__mmask8) -1, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_reduce_ss (__m128 __W, __mmask8 __U, __m128 __A,
|
||||
__m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) __W,
|
||||
(__mmask8) __U);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_reduce_round_ss (__m128 __W, __mmask8 __U, __m128 __A,
|
||||
__m128 __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) __W,
|
||||
__U, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_reduce_ss (__mmask8 __U, __m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) _mm_avx512_setzero_ps (),
|
||||
(__mmask8) __U);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_reduce_round_ss (__mmask8 __U, __m128 __A, __m128 __B,
|
||||
int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_avx512_setzero_ps (),
|
||||
__U, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_range_sd (__m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_avx512_setzero_pd (),
|
||||
(__mmask8) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_range_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) __W,
|
||||
(__mmask8) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_range_sd (__mmask8 __U, __m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_avx512_setzero_pd (),
|
||||
(__mmask8) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_range_ss (__m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_avx512_setzero_ps (),
|
||||
(__mmask8) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_range_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) __W,
|
||||
(__mmask8) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_range_ss (__mmask8 __U, __m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_avx512_setzero_ps (),
|
||||
(__mmask8) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_range_round_sd (__m128d __A, __m128d __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_avx512_setzero_pd (),
|
||||
(__mmask8) -1, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_range_round_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B,
|
||||
int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) __W,
|
||||
(__mmask8) __U, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_range_round_sd (__mmask8 __U, __m128d __A, __m128d __B, int __C,
|
||||
const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_avx512_setzero_pd (),
|
||||
(__mmask8) __U, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_range_round_ss (__m128 __A, __m128 __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_avx512_setzero_ps (),
|
||||
(__mmask8) -1, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_range_round_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B,
|
||||
int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) __W,
|
||||
(__mmask8) __U, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_range_round_ss (__mmask8 __U, __m128 __A, __m128 __B, int __C,
|
||||
const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_avx512_setzero_ps (),
|
||||
(__mmask8) __U, __R);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_fpclass_ss_mask (__m128 __A, const int __imm)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_fpclassss_mask ((__v4sf) __A, __imm,
|
||||
(__mmask8) -1);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_fpclass_sd_mask (__m128d __A, const int __imm)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_fpclasssd_mask ((__v2df) __A, __imm,
|
||||
(__mmask8) -1);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_fpclass_ss_mask (__mmask8 __U, __m128 __A, const int __imm)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_fpclassss_mask ((__v4sf) __A, __imm, __U);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_fpclass_sd_mask (__mmask8 __U, __m128d __A, const int __imm)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_fpclasssd_mask ((__v2df) __A, __imm, __U);
|
||||
}
|
||||
#else
|
||||
#define _kshiftli_mask8(X, Y) ((__mmask8) __builtin_ia32_kshiftliqi ((__mmask8)(X), (__mmask8)(Y)))
|
||||
#define _kshiftri_mask8(X, Y) ((__mmask8) __builtin_ia32_kshiftriqi ((__mmask8)(X), (__mmask8)(Y)))
|
||||
#define _mm_range_sd(A, B, C) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_avx512_setzero_pd (), (__mmask8) -1, _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_mask_range_sd(W, U, A, B, C) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df)(__m128d)(W), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_maskz_range_sd(U, A, B, C) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_avx512_setzero_pd (), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_range_ss(A, B, C) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_avx512_setzero_ps (), (__mmask8) -1, _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_mask_range_ss(W, U, A, B, C) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf)(__m128)(W), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_maskz_range_ss(U, A, B, C) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_avx512_setzero_ps (), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_range_round_sd(A, B, C, R) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_avx512_setzero_pd (), (__mmask8) -1, (R)))
|
||||
#define _mm_mask_range_round_sd(W, U, A, B, C, R) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df)(__m128d)(W), (__mmask8)(U), (R)))
|
||||
#define _mm_maskz_range_round_sd(U, A, B, C, R) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_avx512_setzero_pd (), (__mmask8)(U), (R)))
|
||||
#define _mm_range_round_ss(A, B, C, R) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_avx512_setzero_ps (), (__mmask8) -1, (R)))
|
||||
#define _mm_mask_range_round_ss(W, U, A, B, C, R) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf)(__m128)(W), (__mmask8)(U), (R)))
|
||||
#define _mm_maskz_range_round_ss(U, A, B, C, R) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_avx512_setzero_ps (), (__mmask8)(U), (R)))
|
||||
#define _mm_fpclass_ss_mask(X, C) ((__mmask8) __builtin_ia32_fpclassss_mask ((__v4sf) (__m128) (X), (int) (C), (__mmask8) (-1)))
|
||||
#define _mm_fpclass_sd_mask(X, C) ((__mmask8) __builtin_ia32_fpclasssd_mask ((__v2df) (__m128d) (X), (int) (C), (__mmask8) (-1)))
|
||||
#define _mm_mask_fpclass_ss_mask(X, C, U) ((__mmask8) __builtin_ia32_fpclassss_mask ((__v4sf) (__m128) (X), (int) (C), (__mmask8) (U)))
|
||||
#define _mm_mask_fpclass_sd_mask(X, C, U) ((__mmask8) __builtin_ia32_fpclasssd_mask ((__v2df) (__m128d) (X), (int) (C), (__mmask8) (U)))
|
||||
#define _mm_reduce_sd(A, B, C) ((__m128d) __builtin_ia32_reducesd_mask ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_avx512_setzero_pd (), (__mmask8)-1))
|
||||
#define _mm_mask_reduce_sd(W, U, A, B, C) ((__m128d) __builtin_ia32_reducesd_mask ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df)(__m128d)(W), (__mmask8)(U)))
|
||||
#define _mm_maskz_reduce_sd(U, A, B, C) ((__m128d) __builtin_ia32_reducesd_mask ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_avx512_setzero_pd (), (__mmask8)(U)))
|
||||
#define _mm_reduce_round_sd(A, B, C, R) ((__m128d) __builtin_ia32_reducesd_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_mask_reduce_round_sd(W, U, A, B, C, R) ((__m128d) __builtin_ia32_reducesd_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df)(__m128d)(W), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_maskz_reduce_round_sd(U, A, B, C, R) ((__m128d) __builtin_ia32_reducesd_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_avx512_setzero_pd (), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_reduce_ss(A, B, C) ((__m128) __builtin_ia32_reducess_mask ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_avx512_setzero_ps (), (__mmask8)-1))
|
||||
#define _mm_mask_reduce_ss(W, U, A, B, C) ((__m128) __builtin_ia32_reducess_mask ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf)(__m128)(W), (__mmask8)(U)))
|
||||
#define _mm_maskz_reduce_ss(U, A, B, C) ((__m128) __builtin_ia32_reducess_mask ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_avx512_setzero_ps (), (__mmask8)(U)))
|
||||
#define _mm_reduce_round_ss(A, B, C, R) ((__m128) __builtin_ia32_reducess_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_mask_reduce_round_ss(W, U, A, B, C, R) ((__m128) __builtin_ia32_reducess_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf)(__m128)(W), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_maskz_reduce_round_ss(U, A, B, C, R) ((__m128) __builtin_ia32_reducesd_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_avx512_setzero_ps (), (__mmask8)(U), (int)(R)))
|
||||
#endif
|
||||
#ifdef __DISABLE_AVX512DQ__
|
||||
#undef __DISABLE_AVX512DQ__
|
||||
#pragma GCC pop_options
|
||||
#endif
|
||||
#if !defined (__AVX512DQ__) || !defined (__EVEX512__)
|
||||
#pragma GCC push_options
|
||||
#pragma GCC target("avx512dq,evex512")
|
||||
#define __DISABLE_AVX512DQ_512__
|
||||
#endif
|
||||
extern __inline __m512d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_broadcast_f64x2 (__m128d __A)
|
||||
|
|
@ -939,18 +1263,6 @@ _mm512_maskz_cvtepu64_pd (__mmask8 __U, __m512i __A)
|
|||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
#ifdef __OPTIMIZE__
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_kshiftli_mask8 (__mmask8 __A, unsigned int __B)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_kshiftliqi ((__mmask8) __A, (__mmask8) __B);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_kshiftri_mask8 (__mmask8 __A, unsigned int __B)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_kshiftriqi ((__mmask8) __A, (__mmask8) __B);
|
||||
}
|
||||
extern __inline __m512d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_range_pd (__m512d __A, __m512d __B, int __C)
|
||||
|
|
@ -1017,276 +1329,6 @@ _mm512_maskz_range_ps (__mmask16 __U, __m512 __A, __m512 __B, int __C)
|
|||
(__mmask16) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_reduce_sd (__m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) _mm_setzero_pd (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_reduce_round_sd (__m128d __A, __m128d __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_setzero_pd (),
|
||||
(__mmask8) -1, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_reduce_sd (__m128d __W, __mmask8 __U, __m128d __A,
|
||||
__m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) __W,
|
||||
(__mmask8) __U);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_reduce_round_sd (__m128d __W, __mmask8 __U, __m128d __A,
|
||||
__m128d __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) __W,
|
||||
__U, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_reduce_sd (__mmask8 __U, __m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) _mm_setzero_pd (),
|
||||
(__mmask8) __U);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_reduce_round_sd (__mmask8 __U, __m128d __A, __m128d __B,
|
||||
int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_reducesd_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_setzero_pd (),
|
||||
__U, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_reduce_ss (__m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) _mm_setzero_ps (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_reduce_round_ss (__m128 __A, __m128 __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_setzero_ps (),
|
||||
(__mmask8) -1, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_reduce_ss (__m128 __W, __mmask8 __U, __m128 __A,
|
||||
__m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) __W,
|
||||
(__mmask8) __U);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_reduce_round_ss (__m128 __W, __mmask8 __U, __m128 __A,
|
||||
__m128 __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) __W,
|
||||
__U, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_reduce_ss (__mmask8 __U, __m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) _mm_setzero_ps (),
|
||||
(__mmask8) __U);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_reduce_round_ss (__mmask8 __U, __m128 __A, __m128 __B,
|
||||
int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_reducess_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_setzero_ps (),
|
||||
__U, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_range_sd (__m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_setzero_pd (),
|
||||
(__mmask8) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_range_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) __W,
|
||||
(__mmask8) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_range_sd (__mmask8 __U, __m128d __A, __m128d __B, int __C)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_setzero_pd (),
|
||||
(__mmask8) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_range_ss (__m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_setzero_ps (),
|
||||
(__mmask8) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_range_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) __W,
|
||||
(__mmask8) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_range_ss (__mmask8 __U, __m128 __A, __m128 __B, int __C)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_setzero_ps (),
|
||||
(__mmask8) __U,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_range_round_sd (__m128d __A, __m128d __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_setzero_pd (),
|
||||
(__mmask8) -1, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_range_round_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B,
|
||||
int __C, const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df) __W,
|
||||
(__mmask8) __U, __R);
|
||||
}
|
||||
extern __inline __m128d
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_range_round_sd (__mmask8 __U, __m128d __A, __m128d __B, int __C,
|
||||
const int __R)
|
||||
{
|
||||
return (__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df) __A,
|
||||
(__v2df) __B, __C,
|
||||
(__v2df)
|
||||
_mm_setzero_pd (),
|
||||
(__mmask8) __U, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_range_round_ss (__m128 __A, __m128 __B, int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_setzero_ps (),
|
||||
(__mmask8) -1, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_range_round_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B,
|
||||
int __C, const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf) __W,
|
||||
(__mmask8) __U, __R);
|
||||
}
|
||||
extern __inline __m128
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_range_round_ss (__mmask8 __U, __m128 __A, __m128 __B, int __C,
|
||||
const int __R)
|
||||
{
|
||||
return (__m128) __builtin_ia32_rangess128_mask_round ((__v4sf) __A,
|
||||
(__v4sf) __B, __C,
|
||||
(__v4sf)
|
||||
_mm_setzero_ps (),
|
||||
(__mmask8) __U, __R);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_fpclass_ss_mask (__m128 __A, const int __imm)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_fpclassss_mask ((__v4sf) __A, __imm,
|
||||
(__mmask8) -1);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_fpclass_sd_mask (__m128d __A, const int __imm)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_fpclasssd_mask ((__v2df) __A, __imm,
|
||||
(__mmask8) -1);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_fpclass_ss_mask (__mmask8 __U, __m128 __A, const int __imm)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_fpclassss_mask ((__v4sf) __A, __imm, __U);
|
||||
}
|
||||
extern __inline __mmask8
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_fpclass_sd_mask (__mmask8 __U, __m128d __A, const int __imm)
|
||||
{
|
||||
return (__mmask8) __builtin_ia32_fpclasssd_mask ((__v2df) __A, __imm, __U);
|
||||
}
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvtt_roundpd_epi64 (__m512d __A, const int __R)
|
||||
|
|
@ -2145,20 +2187,6 @@ _mm512_fpclass_ps_mask (__m512 __A, const int __imm)
|
|||
(__mmask16) -1);
|
||||
}
|
||||
#else
|
||||
#define _kshiftli_mask8(X, Y) ((__mmask8) __builtin_ia32_kshiftliqi ((__mmask8)(X), (__mmask8)(Y)))
|
||||
#define _kshiftri_mask8(X, Y) ((__mmask8) __builtin_ia32_kshiftriqi ((__mmask8)(X), (__mmask8)(Y)))
|
||||
#define _mm_range_sd(A, B, C) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_setzero_pd (), (__mmask8) -1, _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_mask_range_sd(W, U, A, B, C) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df)(__m128d)(W), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_maskz_range_sd(U, A, B, C) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_setzero_pd (), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_range_ss(A, B, C) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_setzero_ps (), (__mmask8) -1, _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_mask_range_ss(W, U, A, B, C) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf)(__m128)(W), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_maskz_range_ss(U, A, B, C) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_setzero_ps (), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
|
||||
#define _mm_range_round_sd(A, B, C, R) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_setzero_pd (), (__mmask8) -1, (R)))
|
||||
#define _mm_mask_range_round_sd(W, U, A, B, C, R) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df)(__m128d)(W), (__mmask8)(U), (R)))
|
||||
#define _mm_maskz_range_round_sd(U, A, B, C, R) ((__m128d) __builtin_ia32_rangesd128_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_setzero_pd (), (__mmask8)(U), (R)))
|
||||
#define _mm_range_round_ss(A, B, C, R) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_setzero_ps (), (__mmask8) -1, (R)))
|
||||
#define _mm_mask_range_round_ss(W, U, A, B, C, R) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf)(__m128)(W), (__mmask8)(U), (R)))
|
||||
#define _mm_maskz_range_round_ss(U, A, B, C, R) ((__m128) __builtin_ia32_rangess128_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_setzero_ps (), (__mmask8)(U), (R)))
|
||||
#define _mm512_cvtt_roundpd_epi64(A, B) ((__m512i)__builtin_ia32_cvttpd2qq512_mask ((A), (__v8di) _mm512_setzero_si512 (), -1, (B)))
|
||||
#define _mm512_mask_cvtt_roundpd_epi64(W, U, A, B) ((__m512i)__builtin_ia32_cvttpd2qq512_mask ((A), (__v8di)(W), (U), (B)))
|
||||
#define _mm512_maskz_cvtt_roundpd_epi64(U, A, B) ((__m512i)__builtin_ia32_cvttpd2qq512_mask ((A), (__v8di)_mm512_setzero_si512 (), (U), (B)))
|
||||
|
|
@ -2243,29 +2271,13 @@ _mm512_fpclass_ps_mask (__m512 __A, const int __imm)
|
|||
#define _mm512_inserti32x8(X, Y, C) ((__m512i) __builtin_ia32_inserti32x8_mask ((__v16si)(__m512i) (X), (__v8si)(__m256i) (Y), (int) (C), (__v16si)(__m512i)_mm512_setzero_si512 (), (__mmask16)-1))
|
||||
#define _mm512_mask_inserti32x8(W, U, X, Y, C) ((__m512i) __builtin_ia32_inserti32x8_mask ((__v16si)(__m512i) (X), (__v8si)(__m256i) (Y), (int) (C), (__v16si)(__m512i)(W), (__mmask16)(U)))
|
||||
#define _mm512_maskz_inserti32x8(U, X, Y, C) ((__m512i) __builtin_ia32_inserti32x8_mask ((__v16si)(__m512i) (X), (__v8si)(__m256i) (Y), (int) (C), (__v16si)(__m512i)_mm512_setzero_si512 (), (__mmask16)(U)))
|
||||
#define _mm_fpclass_ss_mask(X, C) ((__mmask8) __builtin_ia32_fpclassss_mask ((__v4sf) (__m128) (X), (int) (C), (__mmask8) (-1)))
|
||||
#define _mm_fpclass_sd_mask(X, C) ((__mmask8) __builtin_ia32_fpclasssd_mask ((__v2df) (__m128d) (X), (int) (C), (__mmask8) (-1)))
|
||||
#define _mm_mask_fpclass_ss_mask(X, C, U) ((__mmask8) __builtin_ia32_fpclassss_mask ((__v4sf) (__m128) (X), (int) (C), (__mmask8) (U)))
|
||||
#define _mm_mask_fpclass_sd_mask(X, C, U) ((__mmask8) __builtin_ia32_fpclasssd_mask ((__v2df) (__m128d) (X), (int) (C), (__mmask8) (U)))
|
||||
#define _mm512_mask_fpclass_pd_mask(u, X, C) ((__mmask8) __builtin_ia32_fpclasspd512_mask ((__v8df) (__m512d) (X), (int) (C), (__mmask8)(u)))
|
||||
#define _mm512_mask_fpclass_ps_mask(u, x, c) ((__mmask16) __builtin_ia32_fpclassps512_mask ((__v16sf) (__m512) (x), (int) (c),(__mmask16)(u)))
|
||||
#define _mm512_fpclass_pd_mask(X, C) ((__mmask8) __builtin_ia32_fpclasspd512_mask ((__v8df) (__m512d) (X), (int) (C), (__mmask8)-1))
|
||||
#define _mm512_fpclass_ps_mask(x, c) ((__mmask16) __builtin_ia32_fpclassps512_mask ((__v16sf) (__m512) (x), (int) (c),(__mmask16)-1))
|
||||
#define _mm_reduce_sd(A, B, C) ((__m128d) __builtin_ia32_reducesd_mask ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_setzero_pd (), (__mmask8)-1))
|
||||
#define _mm_mask_reduce_sd(W, U, A, B, C) ((__m128d) __builtin_ia32_reducesd_mask ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df)(__m128d)(W), (__mmask8)(U)))
|
||||
#define _mm_maskz_reduce_sd(U, A, B, C) ((__m128d) __builtin_ia32_reducesd_mask ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_setzero_pd (), (__mmask8)(U)))
|
||||
#define _mm_reduce_round_sd(A, B, C, R) ((__m128d) __builtin_ia32_reducesd_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_mask_reduce_round_sd(W, U, A, B, C, R) ((__m128d) __builtin_ia32_reducesd_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df)(__m128d)(W), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_maskz_reduce_round_sd(U, A, B, C, R) ((__m128d) __builtin_ia32_reducesd_mask_round ((__v2df)(__m128d)(A), (__v2df)(__m128d)(B), (int)(C), (__v2df) _mm_setzero_pd (), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_reduce_ss(A, B, C) ((__m128) __builtin_ia32_reducess_mask ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_setzero_ps (), (__mmask8)-1))
|
||||
#define _mm_mask_reduce_ss(W, U, A, B, C) ((__m128) __builtin_ia32_reducess_mask ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf)(__m128)(W), (__mmask8)(U)))
|
||||
#define _mm_maskz_reduce_ss(U, A, B, C) ((__m128) __builtin_ia32_reducess_mask ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_setzero_ps (), (__mmask8)(U)))
|
||||
#define _mm_reduce_round_ss(A, B, C, R) ((__m128) __builtin_ia32_reducess_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_mask_reduce_round_ss(W, U, A, B, C, R) ((__m128) __builtin_ia32_reducess_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf)(__m128)(W), (__mmask8)(U), (int)(R)))
|
||||
#define _mm_maskz_reduce_round_ss(U, A, B, C, R) ((__m128) __builtin_ia32_reducesd_mask_round ((__v4sf)(__m128)(A), (__v4sf)(__m128)(B), (int)(C), (__v4sf) _mm_setzero_ps (), (__mmask8)(U), (int)(R)))
|
||||
#endif
|
||||
#ifdef __DISABLE_AVX512DQ__
|
||||
#undef __DISABLE_AVX512DQ__
|
||||
#ifdef __DISABLE_AVX512DQ_512__
|
||||
#undef __DISABLE_AVX512DQ_512__
|
||||
#pragma GCC pop_options
|
||||
#endif
|
||||
#endif
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue