path: root/lib/Headers/avxintrin.h

/*===---- avxintrin.h - AVX intrinsics -------------------------------------===
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 *
 *===-----------------------------------------------------------------------===
 */

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

typedef double __v4df __attribute__ ((__vector_size__ (32)));
typedef float __v8sf __attribute__ ((__vector_size__ (32)));
typedef long long __v4di __attribute__ ((__vector_size__ (32)));
typedef int __v8si __attribute__ ((__vector_size__ (32)));
typedef short __v16hi __attribute__ ((__vector_size__ (32)));
typedef char __v32qi __attribute__ ((__vector_size__ (32)));

typedef float __m256 __attribute__ ((__vector_size__ (32)));
typedef double __m256d __attribute__((__vector_size__(32)));
typedef long long __m256i __attribute__((__vector_size__(32)));

/* Arithmetic */
static __inline __m256d __attribute__((__always_inline__, __nodebug__))
_mm256_add_pd(__m256d __a, __m256d __b)
{
  return __a+__b;
}

static __inline __m256 __attribute__((__always_inline__, __nodebug__))
_mm256_add_ps(__m256 __a, __m256 __b)
{
  return __a+__b;
}

static __inline __m256d __attribute__((__always_inline__, __nodebug__))
_mm256_sub_pd(__m256d __a, __m256d __b)
{
  return __a-__b;
}

static __inline __m256 __attribute__((__always_inline__, __nodebug__))
_mm256_sub_ps(__m256 __a, __m256 __b)
{
  return __a-__b;
}

static __inline __m256d __attribute__((__always_inline__, __nodebug__))
_mm256_addsub_pd(__m256d __a, __m256d __b)
{
  return (__m256d)__builtin_ia32_addsubpd256((__v4df)__a, (__v4df)__b);
}

static __inline __m256 __attribute__((__always_inline__, __nodebug__))
_mm256_addsub_ps(__m256 __a, __m256 __b)
{
  return (__m256)__builtin_ia32_addsubps256((__v8sf)__a, (__v8sf)__b);
}

static __inline __m256d __attribute__((__always_inline__, __nodebug__))
_mm256_div_pd(__m256d __a, __m256d __b)
{
  return __a / __b;
}

static __inline __m256 __attribute__((__always_inline__, __nodebug__))
_mm256_div_ps(__m256 __a, __m256 __b)
{
  return __a / __b;
}

static __inline __m256d __attribute__((__always_inline__, __nodebug__))
_mm256_max_pd(__m256d __a, __m256d __b)
{
  return (__m256d)__builtin_ia32_maxpd256((__v4df)__a, (__v4df)__b);
}

static __inline __m256 __attribute__((__always_inline__, __nodebug__))
_mm256_max_ps(__m256 __a, __m256 __b)
{
  return (__m256)__bu