FM / include

/usr/lib/gcc/x86_64-linux-gnu/9/include/

/usr/lib/gcc/x86_64-linux-gnu/9/include

Name	Size	Mode	Actions
sanitizer/	-	0755	rm
adxintrin.h	2831	0644	edit dl rm
ammintrin.h	3216	0644	edit dl rm
avx2intrin.h	58632	0644	edit dl rm
avx512bitalgintrin.h	8850	0644	edit dl rm
avx512bwintrin.h	101510	0644	edit dl rm
avx512cdintrin.h	5822	0644	edit dl rm
avx512dqintrin.h	85374	0644	edit dl rm
avx512erintrin.h	12965	0644	edit dl rm
avx512fintrin.h	512201	0644	edit dl rm
avx512ifmaintrin.h	3430	0644	edit dl rm
avx512ifmavlintrin.h	5385	0644	edit dl rm
avx512pfintrin.h	10288	0644	edit dl rm
avx512vbmi2intrin.h	19810	0644	edit dl rm
avx512vbmi2vlintrin.h	37120	0644	edit dl rm
avx512vbmiintrin.h	4921	0644	edit dl rm
avx512vbmivlintrin.h	8364	0644	edit dl rm
avx512vlbwintrin.h	143849	0644	edit dl rm
avx512vldqintrin.h	61317	0644	edit dl rm
avx512vlintrin.h	425487	0644	edit dl rm
avx512vnniintrin.h	4969	0644	edit dl rm
avx512vnnivlintrin.h	8244	0644	edit dl rm
avx512vpopcntdqintrin.h	3110	0644	edit dl rm
avx512vpopcntdqvlintrin.h	4667	0644	edit dl rm
avx5124fmapsintrin.h	6535	0644	edit dl rm
avx5124vnniwintrin.h	4256	0644	edit dl rm
avxintrin.h	50613	0644	edit dl rm
backtrace-supported.h	2982	0644	edit dl rm
backtrace.h	9080	0644	edit dl rm
bmi2intrin.h	3388	0644	edit dl rm
bmiintrin.h	5628	0644	edit dl rm
bmmintrin.h	1154	0644	edit dl rm
cet.h	2665	0644	edit dl rm
cetintrin.h	3333	0644	edit dl rm
cldemoteintrin.h	1614	0644	edit dl rm
clflushoptintrin.h	1663	0644	edit dl rm
clwbintrin.h	1585	0644	edit dl rm
clzerointrin.h	1491	0644	edit dl rm
cpuid.h	9069	0644	edit dl rm
cross-stdarg.h	2558	0644	edit dl rm
emmintrin.h	51412	0644	edit dl rm
f16cintrin.h	3410	0644	edit dl rm
float.h	16979	0644	edit dl rm
fma4intrin.h	9132	0644	edit dl rm
fmaintrin.h	10116	0644	edit dl rm
fxsrintrin.h	2056	0644	edit dl rm
gcov.h	1394	0644	edit dl rm
gfniintrin.h	15050	0644	edit dl rm
ia32intrin.h	7873	0644	edit dl rm
immintrin.h	6463	0644	edit dl rm
iso646.h	1272	0644	edit dl rm
ISO_Fortran_binding.h	8471	0644	edit dl rm
limits.h	6089	0644	edit dl rm
lwpintrin.h	3400	0644	edit dl rm
lzcntintrin.h	2398	0644	edit dl rm
mm3dnow.h	7076	0644	edit dl rm
mmintrin.h	31354	0644	edit dl rm
mm_malloc.h	1783	0644	edit dl rm
movdirintrin.h	2347	0644	edit dl rm
mwaitxintrin.h	1747	0644	edit dl rm
nmmintrin.h	1288	0644	edit dl rm
omp.h	7435	0644	edit dl rm
openacc.h	5570	0644	edit dl rm
pconfigintrin.h	2348	0644	edit dl rm
pkuintrin.h	1741	0644	edit dl rm
pmmintrin.h	4368	0644	edit dl rm
popcntintrin.h	1750	0644	edit dl rm
prfchwintrin.h	1447	0644	edit dl rm
quadmath.h	9358	0644	edit dl rm
quadmath_weak.h	3208	0644	edit dl rm
rdseedintrin.h	2017	0644	edit dl rm
rtmintrin.h	2733	0644	edit dl rm
sgxintrin.h	7091	0644	edit dl rm
shaintrin.h	3204	0644	edit dl rm
smmintrin.h	28405	0644	edit dl rm
stdalign.h	1210	0644	edit dl rm
stdarg.h	4072	0644	edit dl rm
stdatomic.h	9321	0644	edit dl rm
stdbool.h	1524	0644	edit dl rm
stddef.h	12959	0644	edit dl rm
stdfix.h	6000	0644	edit dl rm
stdint-gcc.h	9457	0644	edit dl rm
stdint.h	328	0644	edit dl rm
stdnoreturn.h	1136	0644	edit dl rm
syslimits.h	330	0644	edit dl rm
tbmintrin.h	5242	0644	edit dl rm
tmmintrin.h	8343	0644	edit dl rm
unwind.h	10905	0644	edit dl rm
vaesintrin.h	3473	0644	edit dl rm
varargs.h	139	0644	edit dl rm
vpclmulqdqintrin.h	2727	0644	edit dl rm
waitpkgintrin.h	1999	0644	edit dl rm
wbnoinvdintrin.h	1620	0644	edit dl rm
wmmintrin.h	4656	0644	edit dl rm
x86intrin.h	1429	0644	edit dl rm
xmmintrin.h	42387	0644	edit dl rm
xopintrin.h	28568	0644	edit dl rm
xsavecintrin.h	1821	0644	edit dl rm
xsaveintrin.h	2472	0644	edit dl rm
xsaveoptintrin.h	1851	0644	edit dl rm
xsavesintrin.h	2157	0644	edit dl rm
xtestintrin.h	1687	0644	edit dl rm

Edit: /usr/lib/gcc/x86_64-linux-gnu/9/include/mmintrin.h (31354B)

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/>.  */

/* Implemented from the specification included in the Intel C++ Compiler
   User Guide and Reference, version 9.0.  */

#ifndef _MMINTRIN_H_INCLUDED
#define _MMINTRIN_H_INCLUDED

#if defined __x86_64__ && !defined __SSE__ || !defined __MMX__
#pragma GCC push_options
#ifdef __x86_64__
#pragma GCC target("sse,mmx")
#else
#pragma GCC target("mmx")
#endif
#define __DISABLE_MMX__
#endif /* __MMX__ */

/* The Intel API is flexible enough that we must allow aliasing with other
   vector types, and their scalar components.  */
typedef int __m64 __attribute__ ((__vector_size__ (8), __may_alias__));

/* Unaligned version of the same type  */
typedef int __m64_u __attribute__ ((__vector_size__ (8), __may_alias__, __aligned__ (1)));

/* Internal data types for implementing the intrinsics.  */
typedef int __v2si __attribute__ ((__vector_size__ (8)));
typedef short __v4hi __attribute__ ((__vector_size__ (8)));
typedef char __v8qi __attribute__ ((__vector_size__ (8)));
typedef long long __v1di __attribute__ ((__vector_size__ (8)));
typedef float __v2sf __attribute__ ((__vector_size__ (8)));

/* Empty the multimedia state.  */
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_empty (void)
{
  __builtin_ia32_emms ();
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_empty (void)
{
  _mm_empty ();
}

/* Convert I to a __m64 object.  The integer is zero-extended to 64-bits.  */
extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi32_si64 (int __i)
{
  return (__m64) __builtin_ia32_vec_init_v2si (__i, 0);
}

extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_from_int (int __i)
{
  return _mm_cvtsi32_si64 (__i);
}

#ifdef __x86_64__
/* Convert I to a __m64 object.  */

/* Intel intrinsic.  */
extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_from_int64 (long long __i)
{
  return (__m64) __i;
}

extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64_m64 (long long __i)
{
  return (__m64) __i;
}

/* Microsoft intrinsic.  */
extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64x_si64 (long long __i)
{
  return (__m64) __i;
}

extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pi64x (long long __i)
{
  return (__m64) __i;
}
#endif

/* Convert the lower 32 bits of the __m64 object into an integer.  */
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64_si32 (__m64 __i)
{
  return __builtin_ia32_vec_ext_v2si ((__v2si)__i, 0);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_to_int (__m64 __i)
{
  return _mm_cvtsi64_si32 (__i);
}

#ifdef __x86_64__
/* Convert the __m64 object to a 64bit integer.  */

/* Intel intrinsic.  */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_to_int64 (__m64 __i)
{
  return (long long)__i;
}

extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtm64_si64 (__m64 __i)
{
  return (long long)__i;
}

/* Microsoft intrinsic.  */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64_si64x (__m64 __i)
{
  return (long long)__i;
}
#endif

/* Pack the four 16-bit values from M1 into the lower four 8-bit values of
   the result, and the four 16-bit values from M2 into the upper four 8-bit
   values of the result, all with signed saturation.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packs_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_packsswb ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_packsswb (__m64 __m1, __m64 __m2)
{
  return _mm_packs_pi16 (__m1, __m2);
}

/* Pack the two 32-bit values from M1 in to the lower two 16-bit values of
   the result, and the two 32-bit values from M2 into the upper two 16-bit
   values of the result, all with signed saturation.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packs_pi32 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_packssdw ((__v2si)__m1, (__v2si)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_packssdw (__m64 __m1, __m64 __m2)
{
  return _mm_packs_pi32 (__m1, __m2);
}

/* Pack the four 16-bit values from M1 into the lower four 8-bit values of
   the result, and the four 16-bit values from M2 into the upper four 8-bit
   values of the result, all with unsigned saturation.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packs_pu16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_packuswb ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_packuswb (__m64 __m1, __m64 __m2)
{
  return _mm_packs_pu16 (__m1, __m2);
}

/* Interleave the four 8-bit values from the high half of M1 with the four
   8-bit values from the high half of M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_pi8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_punpckhbw ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpckhbw (__m64 __m1, __m64 __m2)
{
  return _mm_unpackhi_pi8 (__m1, __m2);
}

/* Interleave the two 16-bit values from the high half of M1 with the two
   16-bit values from the high half of M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_punpckhwd ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpckhwd (__m64 __m1, __m64 __m2)
{
  return _mm_unpackhi_pi16 (__m1, __m2);
}

/* Interleave the 32-bit value from the high half of M1 with the 32-bit
   value from the high half of M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_pi32 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_punpckhdq ((__v2si)__m1, (__v2si)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpckhdq (__m64 __m1, __m64 __m2)
{
  return _mm_unpackhi_pi32 (__m1, __m2);
}

/* Interleave the four 8-bit values from the low half of M1 with the four
   8-bit values from the low half of M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_pi8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_punpcklbw ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpcklbw (__m64 __m1, __m64 __m2)
{
  return _mm_unpacklo_pi8 (__m1, __m2);
}

/* Interleave the two 16-bit values from the low half of M1 with the two
   16-bit values from the low half of M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_punpcklwd ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpcklwd (__m64 __m1, __m64 __m2)
{
  return _mm_unpacklo_pi16 (__m1, __m2);
}

/* Interleave the 32-bit value from the low half of M1 with the 32-bit
   value from the low half of M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_pi32 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_punpckldq ((__v2si)__m1, (__v2si)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpckldq (__m64 __m1, __m64 __m2)
{
  return _mm_unpacklo_pi32 (__m1, __m2);
}

/* Add the 8-bit values in M1 to the 8-bit values in M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_pi8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_paddb ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddb (__m64 __m1, __m64 __m2)
{
  return _mm_add_pi8 (__m1, __m2);
}

/* Add the 16-bit values in M1 to the 16-bit values in M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_paddw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddw (__m64 __m1, __m64 __m2)
{
  return _mm_add_pi16 (__m1, __m2);
}

/* Add the 32-bit values in M1 to the 32-bit values in M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_pi32 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_paddd ((__v2si)__m1, (__v2si)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddd (__m64 __m1, __m64 __m2)
{
  return _mm_add_pi32 (__m1, __m2);
}

/* Add the 64-bit values in M1 to the 64-bit values in M2.  */
#ifndef __SSE2__
#pragma GCC push_options
#pragma GCC target("sse2,mmx")
#define __DISABLE_SSE2__
#endif /* __SSE2__ */

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_si64 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_paddq ((__v1di)__m1, (__v1di)__m2);
}
#ifdef __DISABLE_SSE2__
#undef __DISABLE_SSE2__
#pragma GCC pop_options
#endif /* __DISABLE_SSE2__ */

/* Add the 8-bit values in M1 to the 8-bit values in M2 using signed
   saturated arithmetic.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_pi8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_paddsb ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddsb (__m64 __m1, __m64 __m2)
{
  return _mm_adds_pi8 (__m1, __m2);
}

/* Add the 16-bit values in M1 to the 16-bit values in M2 using signed
   saturated arithmetic.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_paddsw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddsw (__m64 __m1, __m64 __m2)
{
  return _mm_adds_pi16 (__m1, __m2);
}

/* Add the 8-bit values in M1 to the 8-bit values in M2 using unsigned
   saturated arithmetic.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_pu8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_paddusb ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddusb (__m64 __m1, __m64 __m2)
{
  return _mm_adds_pu8 (__m1, __m2);
}

/* Add the 16-bit values in M1 to the 16-bit values in M2 using unsigned
   saturated arithmetic.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_pu16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_paddusw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddusw (__m64 __m1, __m64 __m2)
{
  return _mm_adds_pu16 (__m1, __m2);
}

/* Subtract the 8-bit values in M2 from the 8-bit values in M1.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_pi8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_psubb ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubb (__m64 __m1, __m64 __m2)
{
  return _mm_sub_pi8 (__m1, __m2);
}

/* Subtract the 16-bit values in M2 from the 16-bit values in M1.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_psubw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubw (__m64 __m1, __m64 __m2)
{
  return _mm_sub_pi16 (__m1, __m2);
}

/* Subtract the 32-bit values in M2 from the 32-bit values in M1.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_pi32 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_psubd ((__v2si)__m1, (__v2si)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubd (__m64 __m1, __m64 __m2)
{
  return _mm_sub_pi32 (__m1, __m2);
}

/* Add the 64-bit values in M1 to the 64-bit values in M2.  */
#ifndef __SSE2__
#pragma GCC push_options
#pragma GCC target("sse2,mmx")
#define __DISABLE_SSE2__
#endif /* __SSE2__ */

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_si64 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_psubq ((__v1di)__m1, (__v1di)__m2);
}
#ifdef __DISABLE_SSE2__
#undef __DISABLE_SSE2__
#pragma GCC pop_options
#endif /* __DISABLE_SSE2__ */

/* Subtract the 8-bit values in M2 from the 8-bit values in M1 using signed
   saturating arithmetic.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_pi8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_psubsb ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubsb (__m64 __m1, __m64 __m2)
{
  return _mm_subs_pi8 (__m1, __m2);
}

/* Subtract the 16-bit values in M2 from the 16-bit values in M1 using
   signed saturating arithmetic.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_psubsw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubsw (__m64 __m1, __m64 __m2)
{
  return _mm_subs_pi16 (__m1, __m2);
}

/* Subtract the 8-bit values in M2 from the 8-bit values in M1 using
   unsigned saturating arithmetic.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_pu8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_psubusb ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubusb (__m64 __m1, __m64 __m2)
{
  return _mm_subs_pu8 (__m1, __m2);
}

/* Subtract the 16-bit values in M2 from the 16-bit values in M1 using
   unsigned saturating arithmetic.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_pu16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_psubusw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubusw (__m64 __m1, __m64 __m2)
{
  return _mm_subs_pu16 (__m1, __m2);
}

/* Multiply four 16-bit values in M1 by four 16-bit values in M2 producing
   four 32-bit intermediate results, which are then summed by pairs to
   produce two 32-bit results.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_madd_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pmaddwd ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pmaddwd (__m64 __m1, __m64 __m2)
{
  return _mm_madd_pi16 (__m1, __m2);
}

/* Multiply four signed 16-bit values in M1 by four signed 16-bit values in
   M2 and produce the high 16 bits of the 32-bit results.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mulhi_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pmulhw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pmulhw (__m64 __m1, __m64 __m2)
{
  return _mm_mulhi_pi16 (__m1, __m2);
}

/* Multiply four 16-bit values in M1 by four 16-bit values in M2 and produce
   the low 16 bits of the results.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mullo_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pmullw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pmullw (__m64 __m1, __m64 __m2)
{
  return _mm_mullo_pi16 (__m1, __m2);
}

/* Shift four 16-bit values in M left by COUNT.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_pi16 (__m64 __m, __m64 __count)
{
  return (__m64) __builtin_ia32_psllw ((__v4hi)__m, (__v4hi)__count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psllw (__m64 __m, __m64 __count)
{
  return _mm_sll_pi16 (__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_pi16 (__m64 __m, int __count)
{
  return (__m64) __builtin_ia32_psllwi ((__v4hi)__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psllwi (__m64 __m, int __count)
{
  return _mm_slli_pi16 (__m, __count);
}

/* Shift two 32-bit values in M left by COUNT.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_pi32 (__m64 __m, __m64 __count)
{
  return (__m64) __builtin_ia32_pslld ((__v2si)__m, (__v2si)__count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pslld (__m64 __m, __m64 __count)
{
  return _mm_sll_pi32 (__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_pi32 (__m64 __m, int __count)
{
  return (__m64) __builtin_ia32_pslldi ((__v2si)__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pslldi (__m64 __m, int __count)
{
  return _mm_slli_pi32 (__m, __count);
}

/* Shift the 64-bit value in M left by COUNT.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_si64 (__m64 __m, __m64 __count)
{
  return (__m64) __builtin_ia32_psllq ((__v1di)__m, (__v1di)__count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psllq (__m64 __m, __m64 __count)
{
  return _mm_sll_si64 (__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_si64 (__m64 __m, int __count)
{
  return (__m64) __builtin_ia32_psllqi ((__v1di)__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psllqi (__m64 __m, int __count)
{
  return _mm_slli_si64 (__m, __count);
}

/* Shift four 16-bit values in M right by COUNT; shift in the sign bit.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sra_pi16 (__m64 __m, __m64 __count)
{
  return (__m64) __builtin_ia32_psraw ((__v4hi)__m, (__v4hi)__count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psraw (__m64 __m, __m64 __count)
{
  return _mm_sra_pi16 (__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srai_pi16 (__m64 __m, int __count)
{
  return (__m64) __builtin_ia32_psrawi ((__v4hi)__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrawi (__m64 __m, int __count)
{
  return _mm_srai_pi16 (__m, __count);
}

/* Shift two 32-bit values in M right by COUNT; shift in the sign bit.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sra_pi32 (__m64 __m, __m64 __count)
{
  return (__m64) __builtin_ia32_psrad ((__v2si)__m, (__v2si)__count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrad (__m64 __m, __m64 __count)
{
  return _mm_sra_pi32 (__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srai_pi32 (__m64 __m, int __count)
{
  return (__m64) __builtin_ia32_psradi ((__v2si)__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psradi (__m64 __m, int __count)
{
  return _mm_srai_pi32 (__m, __count);
}

/* Shift four 16-bit values in M right by COUNT; shift in zeros.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_pi16 (__m64 __m, __m64 __count)
{
  return (__m64) __builtin_ia32_psrlw ((__v4hi)__m, (__v4hi)__count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrlw (__m64 __m, __m64 __count)
{
  return _mm_srl_pi16 (__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_pi16 (__m64 __m, int __count)
{
  return (__m64) __builtin_ia32_psrlwi ((__v4hi)__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrlwi (__m64 __m, int __count)
{
  return _mm_srli_pi16 (__m, __count);
}

/* Shift two 32-bit values in M right by COUNT; shift in zeros.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_pi32 (__m64 __m, __m64 __count)
{
  return (__m64) __builtin_ia32_psrld ((__v2si)__m, (__v2si)__count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrld (__m64 __m, __m64 __count)
{
  return _mm_srl_pi32 (__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_pi32 (__m64 __m, int __count)
{
  return (__m64) __builtin_ia32_psrldi ((__v2si)__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrldi (__m64 __m, int __count)
{
  return _mm_srli_pi32 (__m, __count);
}

/* Shift the 64-bit value in M left by COUNT; shift in zeros.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_si64 (__m64 __m, __m64 __count)
{
  return (__m64) __builtin_ia32_psrlq ((__v1di)__m, (__v1di)__count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrlq (__m64 __m, __m64 __count)
{
  return _mm_srl_si64 (__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_si64 (__m64 __m, int __count)
{
  return (__m64) __builtin_ia32_psrlqi ((__v1di)__m, __count);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrlqi (__m64 __m, int __count)
{
  return _mm_srli_si64 (__m, __count);
}

/* Bit-wise AND the 64-bit values in M1 and M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_and_si64 (__m64 __m1, __m64 __m2)
{
  return __builtin_ia32_pand (__m1, __m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pand (__m64 __m1, __m64 __m2)
{
  return _mm_and_si64 (__m1, __m2);
}

/* Bit-wise complement the 64-bit value in M1 and bit-wise AND it with the
   64-bit value in M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_andnot_si64 (__m64 __m1, __m64 __m2)
{
  return __builtin_ia32_pandn (__m1, __m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pandn (__m64 __m1, __m64 __m2)
{
  return _mm_andnot_si64 (__m1, __m2);
}

/* Bit-wise inclusive OR the 64-bit values in M1 and M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_or_si64 (__m64 __m1, __m64 __m2)
{
  return __builtin_ia32_por (__m1, __m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_por (__m64 __m1, __m64 __m2)
{
  return _mm_or_si64 (__m1, __m2);
}

/* Bit-wise exclusive OR the 64-bit values in M1 and M2.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_xor_si64 (__m64 __m1, __m64 __m2)
{
  return __builtin_ia32_pxor (__m1, __m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pxor (__m64 __m1, __m64 __m2)
{
  return _mm_xor_si64 (__m1, __m2);
}

/* Compare eight 8-bit values.  The result of the comparison is 0xFF if the
   test is true and zero if false.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_pi8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pcmpeqb ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpeqb (__m64 __m1, __m64 __m2)
{
  return _mm_cmpeq_pi8 (__m1, __m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_pi8 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pcmpgtb ((__v8qi)__m1, (__v8qi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpgtb (__m64 __m1, __m64 __m2)
{
  return _mm_cmpgt_pi8 (__m1, __m2);
}

/* Compare four 16-bit values.  The result of the comparison is 0xFFFF if
   the test is true and zero if false.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pcmpeqw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpeqw (__m64 __m1, __m64 __m2)
{
  return _mm_cmpeq_pi16 (__m1, __m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_pi16 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pcmpgtw ((__v4hi)__m1, (__v4hi)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpgtw (__m64 __m1, __m64 __m2)
{
  return _mm_cmpgt_pi16 (__m1, __m2);
}

/* Compare two 32-bit values.  The result of the comparison is 0xFFFFFFFF if
   the test is true and zero if false.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_pi32 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pcmpeqd ((__v2si)__m1, (__v2si)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpeqd (__m64 __m1, __m64 __m2)
{
  return _mm_cmpeq_pi32 (__m1, __m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_pi32 (__m64 __m1, __m64 __m2)
{
  return (__m64) __builtin_ia32_pcmpgtd ((__v2si)__m1, (__v2si)__m2);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpgtd (__m64 __m1, __m64 __m2)
{
  return _mm_cmpgt_pi32 (__m1, __m2);
}

/* Creates a 64-bit zero.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setzero_si64 (void)
{
  return (__m64)0LL;
}

/* Creates a vector of two 32-bit values; I0 is least significant.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pi32 (int __i1, int __i0)
{
  return (__m64) __builtin_ia32_vec_init_v2si (__i0, __i1);
}

/* Creates a vector of four 16-bit values; W0 is least significant.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pi16 (short __w3, short __w2, short __w1, short __w0)
{
  return (__m64) __builtin_ia32_vec_init_v4hi (__w0, __w1, __w2, __w3);
}

/* Creates a vector of eight 8-bit values; B0 is least significant.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pi8 (char __b7, char __b6, char __b5, char __b4,
	     char __b3, char __b2, char __b1, char __b0)
{
  return (__m64) __builtin_ia32_vec_init_v8qi (__b0, __b1, __b2, __b3,
					       __b4, __b5, __b6, __b7);
}

/* Similar, but with the arguments in reverse order.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_pi32 (int __i0, int __i1)
{
  return _mm_set_pi32 (__i1, __i0);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_pi16 (short __w0, short __w1, short __w2, short __w3)
{
  return _mm_set_pi16 (__w3, __w2, __w1, __w0);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_pi8 (char __b0, char __b1, char __b2, char __b3,
	      char __b4, char __b5, char __b6, char __b7)
{
  return _mm_set_pi8 (__b7, __b6, __b5, __b4, __b3, __b2, __b1, __b0);
}

/* Creates a vector of two 32-bit values, both elements containing I.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_pi32 (int __i)
{
  return _mm_set_pi32 (__i, __i);
}

/* Creates a vector of four 16-bit values, all elements containing W.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_pi16 (short __w)
{
  return _mm_set_pi16 (__w, __w, __w, __w);
}

/* Creates a vector of eight 8-bit values, all elements containing B.  */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_pi8 (char __b)
{
  return _mm_set_pi8 (__b, __b, __b, __b, __b, __b, __b, __b);
}
#ifdef __DISABLE_MMX__
#undef __DISABLE_MMX__
#pragma GCC pop_options
#endif /* __DISABLE_MMX__ */

#endif /* _MMINTRIN_H_INCLUDED */

cmd: