golden hour

/lib/gcc/x86_64-redhat-linux/11/include

File/Folder	Size	Actions
acc_prof.h	7.28 KB
adxintrin.h	2.77 KB
ammintrin.h	3.14 KB
amxbf16intrin.h	1.75 KB
amxint8intrin.h	2.04 KB
amxtileintrin.h	3.02 KB
avx2intrin.h	57.37 KB
avx5124fmapsintrin.h	6.38 KB
avx5124vnniwintrin.h	4.16 KB
avx512bf16intrin.h	3.85 KB
avx512bf16vlintrin.h	6 KB
avx512bitalgintrin.h	8.64 KB
avx512bwintrin.h	100.03 KB
avx512cdintrin.h	5.69 KB
avx512dqintrin.h	90.67 KB
avx512erintrin.h	17.26 KB
avx512fintrin.h	512.62 KB
avx512ifmaintrin.h	3.35 KB
avx512ifmavlintrin.h	5.26 KB
avx512pfintrin.h	10.05 KB
avx512vbmi2intrin.h	19.35 KB
avx512vbmi2vlintrin.h	36.25 KB
avx512vbmiintrin.h	4.81 KB
avx512vbmivlintrin.h	8.17 KB
avx512vlbwintrin.h	142.35 KB
avx512vldqintrin.h	59.88 KB
avx512vlintrin.h	418.84 KB
avx512vnniintrin.h	4.85 KB
avx512vnnivlintrin.h	7.23 KB
avx512vp2intersectintrin.h	2.06 KB
avx512vp2intersectvlintrin.h	2.58 KB
avx512vpopcntdqintrin.h	3.04 KB
avx512vpopcntdqvlintrin.h	4.56 KB
avxintrin.h	51.83 KB
avxvnniintrin.h	3.52 KB
bmi2intrin.h	3.28 KB
bmiintrin.h	5.46 KB
bmmintrin.h	1.13 KB
cet.h	2.6 KB
cetintrin.h	3.26 KB
cldemoteintrin.h	1.58 KB
clflushoptintrin.h	1.63 KB
clwbintrin.h	1.55 KB
clzerointrin.h	1.46 KB
cpuid.h	9.62 KB
cross-stdarg.h	2.5 KB
emmintrin.h	50.93 KB
enqcmdintrin.h	1.77 KB
f16cintrin.h	3.33 KB
float.h	20.17 KB
fma4intrin.h	8.92 KB
fmaintrin.h	9.88 KB
fxsrintrin.h	2.01 KB
gcov.h	1.21 KB
gfniintrin.h	14.7 KB
hresetintrin.h	1.59 KB
ia32intrin.h	7.68 KB
immintrin.h	2.47 KB
iso646.h	1.24 KB
keylockerintrin.h	4.34 KB
limits.h	6.21 KB
lwpintrin.h	3.33 KB
lzcntintrin.h	2.31 KB
mm3dnow.h	6.91 KB
mm_malloc.h	1.74 KB
mmintrin.h	31.14 KB
movdirintrin.h	2.29 KB
mwaitintrin.h	1.67 KB
mwaitxintrin.h	1.71 KB
nmmintrin.h	1.26 KB
omp.h	9.97 KB
openacc.h	6.25 KB
pconfigintrin.h	2.3 KB
pkuintrin.h	1.7 KB
pmmintrin.h	3.92 KB
popcntintrin.h	1.71 KB
prfchwintrin.h	1.41 KB
rdseedintrin.h	1.97 KB
rtmintrin.h	2.67 KB
sanitizer	-
serializeintrin.h	1.59 KB
sgxintrin.h	6.92 KB
shaintrin.h	3.13 KB
smmintrin.h	27.77 KB
stdalign.h	1.18 KB
stdarg.h	3.98 KB
stdatomic.h	9.14 KB
stdbool.h	1.47 KB
stddef.h	12.66 KB
stdfix.h	5.86 KB
stdint-gcc.h	9.32 KB
stdint.h	328 B
stdnoreturn.h	1.11 KB
syslimits.h	330 B
tbmintrin.h	5.13 KB
tmmintrin.h	8.15 KB
tsxldtrkintrin.h	1.74 KB
uintrintrin.h	2.25 KB
unwind.h	10.65 KB
vaesintrin.h	3.39 KB
varargs.h	139 B
vpclmulqdqintrin.h	2.66 KB
waitpkgintrin.h	1.95 KB
wbnoinvdintrin.h	1.59 KB
wmmintrin.h	4.55 KB
x86gprintrin.h	5.94 KB
x86intrin.h	1.27 KB
xmmintrin.h	43.37 KB
xopintrin.h	28.11 KB
xsavecintrin.h	1.78 KB
xsaveintrin.h	2.42 KB
xsaveoptintrin.h	1.81 KB
xsavesintrin.h	2.11 KB
xtestintrin.h	1.65 KB

Edit: avx512erintrin.h

This file is part of GCC.

GCC is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 3, or (at your option)
   any later version.

GCC is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

Under Section 7 of GPL version 3, you are granted additional
   permissions described in the GCC Runtime Library Exception, version
   3.1, as published by the Free Software Foundation.

You should have received a copy of the GNU General Public License and
   a copy of the GCC Runtime Library Exception along with this program;
   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
   <http://www.gnu.org/licenses/>.  */

#ifndef _IMMINTRIN_H_INCLUDED
#error "Never use <avx512erintrin.h> directly; include <immintrin.h> instead."
#endif

#ifndef _AVX512ERINTRIN_H_INCLUDED
#define _AVX512ERINTRIN_H_INCLUDED

#ifndef __AVX512ER__
#pragma GCC push_options
#pragma GCC target("avx512er")
#define __DISABLE_AVX512ER__
#endif /* __AVX512ER__ */

/* Internal data types for implementing the intrinsics.  */
typedef double __v8df __attribute__ ((__vector_size__ (64)));
typedef float __v16sf __attribute__ ((__vector_size__ (64)));

/* The Intel API is flexible enough that we must allow aliasing with other
   vector types, and their scalar components.  */
typedef float __m512 __attribute__ ((__vector_size__ (64), __may_alias__));
typedef double __m512d __attribute__ ((__vector_size__ (64), __may_alias__));

typedef unsigned char  __mmask8;
typedef unsigned short __mmask16;

#ifdef __OPTIMIZE__
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_exp2a23_round_pd (__m512d __A, int __R)
{
  __m512d __W;
  return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
					       (__v8df) __W,
					       (__mmask8) -1, __R);
}

extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_exp2a23_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
{
  return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
					       (__v8df) __W,
					       (__mmask8) __U, __R);
}

extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_exp2a23_round_pd (__mmask8 __U, __m512d __A, int __R)
{
  return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
					       (__v8df) _mm512_setzero_pd (),
					       (__mmask8) __U, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_exp2a23_round_ps (__m512 __A, int __R)
{
  __m512 __W;
  return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
					      (__v16sf) __W,
					      (__mmask16) -1, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_exp2a23_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
{
  return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
					      (__v16sf) __W,
					      (__mmask16) __U, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_exp2a23_round_ps (__mmask16 __U, __m512 __A, int __R)
{
  return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
					      (__v16sf) _mm512_setzero_ps (),
					      (__mmask16) __U, __R);
}

extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rcp28_round_pd (__m512d __A, int __R)
{
  __m512d __W;
  return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
						(__v8df) __W,
						(__mmask8) -1, __R);
}

extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rcp28_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
{
  return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
						(__v8df) __W,
						(__mmask8) __U, __R);
}

extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rcp28_round_pd (__mmask8 __U, __m512d __A, int __R)
{
  return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
						(__v8df) _mm512_setzero_pd (),
						(__mmask8) __U, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rcp28_round_ps (__m512 __A, int __R)
{
  __m512 __W;
  return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
					       (__v16sf) __W,
					       (__mmask16) -1, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rcp28_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
{
  return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
					       (__v16sf) __W,
					       (__mmask16) __U, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rcp28_round_ps (__mmask16 __U, __m512 __A, int __R)
{
  return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
					       (__v16sf) _mm512_setzero_ps (),
					       (__mmask16) __U, __R);
}

extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp28_round_sd (__m128d __A, __m128d __B, int __R)
{
  return (__m128d) __builtin_ia32_rcp28sd_round ((__v2df) __B,
						 (__v2df) __A,
						 __R);
}

extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_rcp28_round_sd (__m128d __W, __mmask8 __U, __m128d __A,
			 __m128d __B, int __R)
{
  return (__m128d) __builtin_ia32_rcp28sd_mask_round ((__v2df) __B,
						      (__v2df) __A,
						      (__v2df) __W,
						      __U,
						      __R);
}

extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_rcp28_round_sd (__mmask8 __U, __m128d __A, __m128d __B, int __R)
{
  return (__m128d) __builtin_ia32_rcp28sd_mask_round ((__v2df) __B,
						      (__v2df) __A,
						      (__v2df)
						      _mm_setzero_pd (),
						      __U,
						      __R);
}

extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp28_round_ss (__m128 __A, __m128 __B, int __R)
{
  return (__m128) __builtin_ia32_rcp28ss_round ((__v4sf) __B,
						(__v4sf) __A,
						__R);
}

extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_rcp28_round_ss (__m128 __W, __mmask8 __U, __m128 __A,
			 __m128 __B, int __R)
{
  return (__m128) __builtin_ia32_rcp28ss_mask_round ((__v4sf) __B,
						     (__v4sf) __A,
						     (__v4sf) __W,
						     __U,
						     __R);
}

extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_rcp28_round_ss (__mmask8 __U, __m128 __A, __m128 __B, int __R)
{
  return (__m128) __builtin_ia32_rcp28ss_mask_round ((__v4sf) __B,
						     (__v4sf) __A,
						     (__v4sf)
						     _mm_setzero_ps (),
						     __U,
						     __R);
}

extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rsqrt28_round_pd (__m512d __A, int __R)
{
  __m512d __W;
  return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
						  (__v8df) __W,
						  (__mmask8) -1, __R);
}

extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rsqrt28_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
{
  return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
						  (__v8df) __W,
						  (__mmask8) __U, __R);
}

extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rsqrt28_round_pd (__mmask8 __U, __m512d __A, int __R)
{
  return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
						  (__v8df) _mm512_setzero_pd (),
						  (__mmask8) __U, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rsqrt28_round_ps (__m512 __A, int __R)
{
  __m512 __W;
  return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
						 (__v16sf) __W,
						 (__mmask16) -1, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rsqrt28_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
{
  return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
						 (__v16sf) __W,
						 (__mmask16) __U, __R);
}

extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rsqrt28_round_ps (__mmask16 __U, __m512 __A, int __R)
{
  return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
						 (__v16sf) _mm512_setzero_ps (),
						 (__mmask16) __U, __R);
}

extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt28_round_sd (__m128d __A, __m128d __B, int __R)
{
  return (__m128d) __builtin_ia32_rsqrt28sd_round ((__v2df) __B,
						   (__v2df) __A,
						   __R);
}

extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_rsqrt28_round_sd (__m128d __W, __mmask8 __U, __m128d __A,
			   __m128d __B, int __R)
{
  return (__m128d) __builtin_ia32_rsqrt28sd_mask_round ((__v2df) __B,
							(__v2df) __A,
							(__v2df) __W,
							__U,
							__R);
}

extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_rsqrt28_round_sd (__mmask8 __U, __m128d __A, __m128d __B, int __R)
{
  return (__m128d) __builtin_ia32_rsqrt28sd_mask_round ((__v2df) __B,
							(__v2df) __A,
							(__v2df)
							_mm_setzero_pd (),
							__U,
							__R);
}

extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt28_round_ss (__m128 __A, __m128 __B, int __R)
{
  return (__m128) __builtin_ia32_rsqrt28ss_round ((__v4sf) __B,
						  (__v4sf) __A,
						  __R);
}

extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_rsqrt28_round_ss (__m128 __W, __mmask8 __U, __m128 __A,
			   __m128 __B, int __R)
{
  return (__m128) __builtin_ia32_rsqrt28ss_mask_round ((__v4sf) __B,
						       (__v4sf) __A,
						       (__v4sf) __W,
						       __U,
						       __R);
}

extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_rsqrt28_round_ss (__mmask8 __U, __m128 __A, __m128 __B, int __R)
{
  return (__m128) __builtin_ia32_rsqrt28ss_mask_round ((__v4sf) __B,
						       (__v4sf) __A,
						       (__v4sf)
						       _mm_setzero_ps (),
						       __U,
						       __R);
}

#else
#define _mm512_exp2a23_round_pd(A, C)            \
    __builtin_ia32_exp2pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)

#define _mm512_mask_exp2a23_round_pd(W, U, A, C) \
    __builtin_ia32_exp2pd_mask(A, W, U, C)

#define _mm512_maskz_exp2a23_round_pd(U, A, C)   \
    __builtin_ia32_exp2pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)

#define _mm512_exp2a23_round_ps(A, C)            \
    __builtin_ia32_exp2ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)

#define _mm512_mask_exp2a23_round_ps(W, U, A, C) \
    __builtin_ia32_exp2ps_mask(A, W, U, C)

#define _mm512_maskz_exp2a23_round_ps(U, A, C)   \
    __builtin_ia32_exp2ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)

#define _mm512_rcp28_round_pd(A, C)            \
    __builtin_ia32_rcp28pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)

#define _mm512_mask_rcp28_round_pd(W, U, A, C) \
    __builtin_ia32_rcp28pd_mask(A, W, U, C)

#define _mm512_maskz_rcp28_round_pd(U, A, C)   \
    __builtin_ia32_rcp28pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)

#define _mm512_rcp28_round_ps(A, C)            \
    __builtin_ia32_rcp28ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)

#define _mm512_mask_rcp28_round_ps(W, U, A, C) \
    __builtin_ia32_rcp28ps_mask(A, W, U, C)

#define _mm512_maskz_rcp28_round_ps(U, A, C)   \
    __builtin_ia32_rcp28ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)

#define _mm512_rsqrt28_round_pd(A, C)            \
    __builtin_ia32_rsqrt28pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)

#define _mm512_mask_rsqrt28_round_pd(W, U, A, C) \
    __builtin_ia32_rsqrt28pd_mask(A, W, U, C)

#define _mm512_maskz_rsqrt28_round_pd(U, A, C)   \
    __builtin_ia32_rsqrt28pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)

#define _mm512_rsqrt28_round_ps(A, C)            \
    __builtin_ia32_rsqrt28ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)

#define _mm512_mask_rsqrt28_round_ps(W, U, A, C) \
    __builtin_ia32_rsqrt28ps_mask(A, W, U, C)

#define _mm512_maskz_rsqrt28_round_ps(U, A, C)   \
    __builtin_ia32_rsqrt28ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)

#define _mm_rcp28_round_sd(A, B, R)	\
    __builtin_ia32_rcp28sd_round(A, B, R)

#define _mm_mask_rcp28_round_sd(W, U, A, B, R)	\
    __builtin_ia32_rcp28sd_mask_round ((A), (B), (W), (U), (R))

#define _mm_maskz_rcp28_round_sd(U, A, B, R)	\
    __builtin_ia32_rcp28sd_mask_round ((A), (B), (__v2df) _mm_setzero_pd (), \
				       (U), (R))

#define _mm_rcp28_round_ss(A, B, R)	\
    __builtin_ia32_rcp28ss_round(A, B, R)

#define _mm_mask_rcp28_round_ss(W, U, A, B, R)	\
    __builtin_ia32_rcp28ss_mask_round ((A), (B), (W), (U), (R))

#define _mm_maskz_rcp28_round_ss(U, A, B, R)	\
    __builtin_ia32_rcp28ss_mask_round ((A), (B), (__v4sf) _mm_setzero_ps (), \
				       (U), (R))

#define _mm_rsqrt28_round_sd(A, B, R)	\
    __builtin_ia32_rsqrt28sd_round(A, B, R)

#define _mm_mask_rsqrt28_round_sd(W, U, A, B, R)	\
    __builtin_ia32_rsqrt28sd_mask_round ((A), (B), (W), (U), (R))

#define _mm_maskz_rsqrt28_round_sd(U, A, B, R)	\
    __builtin_ia32_rsqrt28sd_mask_round ((A), (B), (__v2df) _mm_setzero_pd (),\
					 (U), (R))

#define _mm_rsqrt28_round_ss(A, B, R)	\
    __builtin_ia32_rsqrt28ss_round(A, B, R)

#define _mm_mask_rsqrt28_round_ss(W, U, A, B, R)	\
    __builtin_ia32_rsqrt28ss_mask_round ((A), (B), (W), (U), (R))

#define _mm_maskz_rsqrt28_round_ss(U, A, B, R)	\
    __builtin_ia32_rsqrt28ss_mask_round ((A), (B), (__v4sf) _mm_setzero_ps (),\
					 (U), (R))

#endif

#define _mm_mask_rcp28_sd(W, U, A, B)\
    _mm_mask_rcp28_round_sd ((W), (U), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_maskz_rcp28_sd(U, A, B)\
    _mm_maskz_rcp28_round_sd ((U), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_mask_rcp28_ss(W, U, A, B)\
    _mm_mask_rcp28_round_ss ((W), (U), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_maskz_rcp28_ss(U, A, B)\
    _mm_maskz_rcp28_round_ss ((U), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_mask_rsqrt28_sd(W, U, A, B)\
    _mm_mask_rsqrt28_round_sd ((W), (U), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_maskz_rsqrt28_sd(U, A, B)\
    _mm_maskz_rsqrt28_round_sd ((U), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_mask_rsqrt28_ss(W, U, A, B)\
    _mm_mask_rsqrt28_round_ss ((W), (U), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm_maskz_rsqrt28_ss(U, A, B)\
    _mm_maskz_rsqrt28_round_ss ((U), (A), (B), _MM_FROUND_CUR_DIRECTION)

#define _mm512_exp2a23_pd(A)                    \
    _mm512_exp2a23_round_pd(A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_exp2a23_pd(W, U, A)   \
    _mm512_mask_exp2a23_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_exp2a23_pd(U, A)     \
    _mm512_maskz_exp2a23_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_exp2a23_ps(A)                    \
    _mm512_exp2a23_round_ps(A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_exp2a23_ps(W, U, A)   \
    _mm512_mask_exp2a23_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_exp2a23_ps(U, A)     \
    _mm512_maskz_exp2a23_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_rcp28_pd(A)                    \
    _mm512_rcp28_round_pd(A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_rcp28_pd(W, U, A)   \
    _mm512_mask_rcp28_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_rcp28_pd(U, A)     \
    _mm512_maskz_rcp28_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_rcp28_ps(A)                    \
    _mm512_rcp28_round_ps(A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_rcp28_ps(W, U, A)   \
    _mm512_mask_rcp28_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_rcp28_ps(U, A)     \
    _mm512_maskz_rcp28_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_rsqrt28_pd(A)                    \
    _mm512_rsqrt28_round_pd(A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_rsqrt28_pd(W, U, A)   \
    _mm512_mask_rsqrt28_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_rsqrt28_pd(U, A)     \
    _mm512_maskz_rsqrt28_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_rsqrt28_ps(A)                    \
    _mm512_rsqrt28_round_ps(A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_mask_rsqrt28_ps(W, U, A)   \
    _mm512_mask_rsqrt28_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm512_maskz_rsqrt28_ps(U, A)     \
    _mm512_maskz_rsqrt28_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)

#define _mm_rcp28_sd(A, B)	\
    __builtin_ia32_rcp28sd_round(B, A, _MM_FROUND_CUR_DIRECTION)

#define _mm_rcp28_ss(A, B)	\
    __builtin_ia32_rcp28ss_round(B, A, _MM_FROUND_CUR_DIRECTION)

#define _mm_rsqrt28_sd(A, B)	\
    __builtin_ia32_rsqrt28sd_round(B, A, _MM_FROUND_CUR_DIRECTION)

#define _mm_rsqrt28_ss(A, B)	\
    __builtin_ia32_rsqrt28ss_round(B, A, _MM_FROUND_CUR_DIRECTION)

#ifdef __DISABLE_AVX512ER__
#undef __DISABLE_AVX512ER__
#pragma GCC pop_options
#endif /* __DISABLE_AVX512ER__ */

#endif /* _AVX512ERINTRIN_H_INCLUDED */