src/gromacs/simd/impl_x86_sse2/impl_x86_sse2_simd4_float.h

   1 /*
   2  * This file is part of the GROMACS molecular simulation package.
   3  *
   4  * Copyright (c) 2014,2015, 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.
   8  *
   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.
  13  *
  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.
  18  *
  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.
  23  *
  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.
  31  *
  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.
  34  */
  35
  36 #ifndef GMX_SIMD_IMPL_X86_SSE2_SIMD4_FLOAT_H
  37 #define GMX_SIMD_IMPL_X86_SSE2_SIMD4_FLOAT_H
  38
  39 #include "config.h"
  40
  41 #include <emmintrin.h>
  42
  43 #include "impl_x86_sse2_common.h"
  44 #include "impl_x86_sse2_simd_float.h"
  45
  46 /* SSE2 is already 4-wide in single, so we just reuse float datatype for SIMD4. */
  47 #define gmx_simd4_float_t                gmx_simd_float_t
  48 #define gmx_simd4_load_f                 gmx_simd_load_f
  49 #define gmx_simd4_load1_f                gmx_simd_load1_f
  50 #define gmx_simd4_set1_f                 gmx_simd_set1_f
  51 #define gmx_simd4_store_f                gmx_simd_store_f
  52 #define gmx_simd4_loadu_f                gmx_simd_loadu_f
  53 #define gmx_simd4_storeu_f               gmx_simd_storeu_f
  54 #define gmx_simd4_setzero_f              gmx_simd_setzero_f
  55 #define gmx_simd4_add_f                  gmx_simd_add_f
  56 #define gmx_simd4_sub_f                  gmx_simd_sub_f
  57 #define gmx_simd4_mul_f                  gmx_simd_mul_f
  58 #define gmx_simd4_fmadd_f                gmx_simd_fmadd_f
  59 #define gmx_simd4_fmsub_f                gmx_simd_fmsub_f
  60 #define gmx_simd4_fnmadd_f               gmx_simd_fnmadd_f
  61 #define gmx_simd4_fnmsub_f               gmx_simd_fnmsub_f
  62 #define gmx_simd4_and_f                  gmx_simd_and_f
  63 #define gmx_simd4_andnot_f               gmx_simd_andnot_f
  64 #define gmx_simd4_or_f                   gmx_simd_or_f
  65 #define gmx_simd4_xor_f                  gmx_simd_xor_f
  66 #define gmx_simd4_rsqrt_f                gmx_simd_rsqrt_f
  67 #define gmx_simd4_fabs_f                 gmx_simd_fabs_f
  68 #define gmx_simd4_fneg_f                 gmx_simd_fneg_f
  69 #define gmx_simd4_max_f                  gmx_simd_max_f
  70 #define gmx_simd4_min_f                  gmx_simd_min_f
  71 #define gmx_simd4_round_f                gmx_simd_round_f
  72 #define gmx_simd4_trunc_f                gmx_simd_trunc_f
  73 #define gmx_simd4_dotproduct3_f          gmx_simd4_dotproduct3_f_sse2
  74 #define gmx_simd4_fbool_t                gmx_simd_fbool_t
  75 #define gmx_simd4_cmpeq_f                gmx_simd_cmpeq_f
  76 #define gmx_simd4_cmplt_f                gmx_simd_cmplt_f
  77 #define gmx_simd4_cmple_f                gmx_simd_cmple_f
  78 #define gmx_simd4_and_fb                 gmx_simd_and_fb
  79 #define gmx_simd4_or_fb                  gmx_simd_or_fb
  80 #define gmx_simd4_anytrue_fb             gmx_simd_anytrue_fb
  81 #define gmx_simd4_blendzero_f            gmx_simd_blendzero_f
  82 #define gmx_simd4_blendnotzero_f         gmx_simd_blendnotzero_f
  83 #define gmx_simd4_blendv_f               gmx_simd_blendv_f
  84 #define gmx_simd4_reduce_f               gmx_simd_reduce_f
  85
  86 /* SIMD4 Dotproduct helper function */
  87 static gmx_inline float gmx_simdcall
  88 gmx_simd4_dotproduct3_f_sse2(__m128 a, __m128 b)
  89 {
  90     float  f;
  91     __m128 c;
  92     a = _mm_mul_ps(a, b);
  93     c = _mm_add_ps(a, _mm_shuffle_ps(a, a, _MM_SHUFFLE(2, 1, 2, 1)));
  94     c = _mm_add_ps(c, _mm_shuffle_ps(a, a, _MM_SHUFFLE(3, 2, 3, 2)));
  95     _mm_store_ss(&f, c);
  96     return f;
  97 }
  98
  99 #endif /* GMX_SIMD_IMPL_X86_SSE2_SIMD4_FLOAT_H */