2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2014,2015,2019, by the GROMACS development team, led by
5 * Mark Abraham, David van der Spoel, Berk Hess, and Erik Lindahl,
6 * and including many others, as listed in the AUTHORS file in the
7 * top-level source 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.
36 #ifndef GMX_SIMD_IMPL_X86_AVX_128_FMA_UTIL_DOUBLE_H
37 #define GMX_SIMD_IMPL_X86_AVX_128_FMA_UTIL_DOUBLE_H
44 #include <immintrin.h>
45 #include <x86intrin.h>
47 #include "gromacs/simd/impl_x86_sse4_1/impl_x86_sse4_1_util_double.h"
52 static inline void gmx_simdcall expandScalarsToTriplets(SimdDouble scalar,
53 SimdDouble* triplets0,
54 SimdDouble* triplets1,
55 SimdDouble* triplets2)
57 triplets0->simdInternal_ = _mm_permute_pd(scalar.simdInternal_, _MM_SHUFFLE2(0, 0));
58 triplets1->simdInternal_ = _mm_permute_pd(scalar.simdInternal_, _MM_SHUFFLE2(1, 0));
59 triplets2->simdInternal_ = _mm_permute_pd(scalar.simdInternal_, _MM_SHUFFLE2(1, 1));
62 static inline double reduceIncr4ReturnSum(double* m, SimdDouble v0, SimdDouble v1, SimdDouble v2, SimdDouble v3)
64 __m128d t1, t2, t3, t4;
66 t1 = _mm_unpacklo_pd(v0.simdInternal_, v1.simdInternal_);
67 t2 = _mm_unpackhi_pd(v0.simdInternal_, v1.simdInternal_);
68 t3 = _mm_unpacklo_pd(v2.simdInternal_, v3.simdInternal_);
69 t4 = _mm_unpackhi_pd(v2.simdInternal_, v3.simdInternal_);
71 t1 = _mm_add_pd(t1, t2);
72 t3 = _mm_add_pd(t3, t4);
74 assert(std::size_t(m) % 16 == 0);
76 t2 = _mm_add_pd(t1, _mm_load_pd(m));
77 t4 = _mm_add_pd(t3, _mm_load_pd(m + 2));
79 _mm_store_pd(m + 2, t4);
81 t1 = _mm_add_pd(t1, t3);
83 t2 = _mm_add_sd(t1, _mm_permute_pd(t1, _MM_SHUFFLE2(1, 1)));
84 return *reinterpret_cast<double*>(&t2);
89 #endif // GMX_SIMD_IMPL_X86_AVX_128_FMA_UTIL_DOUBLE_H