2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2012, by the GROMACS development team, led by
5 * David van der Spoel, Berk Hess, Erik Lindahl, and including many
6 * others, as listed in the AUTHORS file in the top-level source
7 * directory and at http://www.gromacs.org.
9 * GROMACS is free software; you can redistribute it and/or
10 * modify it under the terms of the GNU Lesser General Public License
11 * as published by the Free Software Foundation; either version 2.1
12 * of the License, or (at your option) any later version.
14 * GROMACS is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 * Lesser General Public License for more details.
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with GROMACS; if not, see
21 * http://www.gnu.org/licenses, or write to the Free Software Foundation,
22 * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
24 * If you want to redistribute modifications to GROMACS, please
25 * consider that scientific software is very special. Version
26 * control is crucial - bugs must be traceable. We will be happy to
27 * consider code for inclusion in the official distribution, but
28 * derived work must not be called official GROMACS. Details are found
29 * in the README & COPYING files - if they are missing, get the
30 * official version at http://www.gromacs.org.
32 * To help us fund GROMACS development, we humbly ask that you cite
33 * the research papers on the package. Check out http://www.gromacs.org.
35 #ifndef _gmx_avx_single_h_
36 #define _gmx_avx_single_h_
38 /* We require AVX now! */
40 #include <immintrin.h> /* AVX */
43 gmx_mm256_invsqrt_ps(__m256 x)
45 const __m256 half = _mm256_set_ps(0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5);
46 const __m256 three = _mm256_set_ps(3.0,3.0,3.0,3.0,3.0,3.0,3.0,3.0);
48 __m256 lu = _mm256_rsqrt_ps(x);
50 return _mm256_mul_ps(half,_mm256_mul_ps(_mm256_sub_ps(three,_mm256_mul_ps(_mm256_mul_ps(lu,lu),x)),lu));
54 gmx_mm256_calc_rsq_ps(__m256 dx, __m256 dy, __m256 dz)
56 return _mm256_add_ps( _mm256_add_ps( _mm256_mul_ps(dx,dx), _mm256_mul_ps(dy,dy) ), _mm256_mul_ps(dz,dz) );
59 /* Normal sum of four xmm registers */
60 #define gmx_mm256_sum4_ps(t0,t1,t2,t3) _mm256_add_ps(_mm256_add_ps(t0,t1),_mm256_add_ps(t2,t3))
62 #endif /* gmx_avx_single_h_ */