2 * This file is part of the GROMACS molecular simulation package.
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.
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_ARM_NEON_ASIMD_SIMD4_FLOAT_H
37 #define GMX_SIMD_IMPL_ARM_NEON_ASIMD_SIMD4_FLOAT_H
43 #include "gromacs/simd/impl_arm_neon/impl_arm_neon_simd4_float.h"
48 static inline Simd4Float gmx_simdcall
49 fma(Simd4Float a, Simd4Float b, Simd4Float c)
52 vfmaq_f32(c.simdInternal_, b.simdInternal_, a.simdInternal_)
56 static inline Simd4Float gmx_simdcall
57 fms(Simd4Float a, Simd4Float b, Simd4Float c)
60 vnegq_f32(vfmsq_f32(c.simdInternal_, b.simdInternal_, a.simdInternal_))
64 static inline Simd4Float gmx_simdcall
65 fnma(Simd4Float a, Simd4Float b, Simd4Float c)
68 vfmsq_f32(c.simdInternal_, b.simdInternal_, a.simdInternal_)
72 static inline Simd4Float gmx_simdcall
73 fnms(Simd4Float a, Simd4Float b, Simd4Float c)
76 vnegq_f32(vfmaq_f32(c.simdInternal_, b.simdInternal_, a.simdInternal_))
80 static inline Simd4Float gmx_simdcall
84 vrndnq_f32(x.simdInternal_)
88 static inline Simd4Float gmx_simdcall
92 vrndq_f32(x.simdInternal_)
96 static inline bool gmx_simdcall
99 return (vmaxvq_u32(a.simdInternal_) != 0);
102 static inline float gmx_simdcall
105 float32x4_t b = a.simdInternal_;
106 b = vpaddq_f32(b, b);
107 b = vpaddq_f32(b, b);
108 return vgetq_lane_f32(b, 0);
111 static inline float gmx_simdcall
112 dotProduct(Simd4Float a, Simd4Float b)
117 /* set 4th element to 0, then add all of them */
118 c.simdInternal_ = vsetq_lane_f32(0.0f, c.simdInternal_, 3);
124 #endif // GMX_SIMD_IMPL_ARM_NEON_ASIMD_SIMD4_FLOAT_H