2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2012,2015,2016,2019, 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 VECTYPE_OPS_CUH
37 #define VECTYPE_OPS_CUH
40 __forceinline__ __host__ __device__ float3 make_float3(float s)
42 return make_float3(s, s, s);
44 __forceinline__ __host__ __device__ float3 make_float3(float4 a)
46 return make_float3(a.x, a.y, a.z);
48 __forceinline__ __host__ __device__ float3 operator-(float3& a)
50 return make_float3(-a.x, -a.y, -a.z);
52 __forceinline__ __host__ __device__ float3 operator+(float3 a, float3 b)
54 return make_float3(a.x + b.x, a.y + b.y, a.z + b.z);
56 __forceinline__ __host__ __device__ float3 operator-(float3 a, float3 b)
58 return make_float3(a.x - b.x, a.y - b.y, a.z - b.z);
60 __forceinline__ __host__ __device__ float3 operator*(float3 a, float k)
62 return make_float3(k * a.x, k * a.y, k * a.z);
64 __forceinline__ __host__ __device__ float3 operator*(float k, float3 a)
66 return make_float3(k * a.x, k * a.y, k * a.z);
68 __forceinline__ __host__ __device__ void operator+=(float3& a, float3 b)
74 __forceinline__ __host__ __device__ void operator+=(float3& a, float4 b)
80 __forceinline__ __host__ __device__ void operator-=(float3& a, float3 b)
86 __forceinline__ __host__ __device__ float norm(float3 a)
88 return sqrt(a.x * a.x + a.y * a.y + a.z * a.z);
90 __forceinline__ __host__ __device__ float norm2(float3 a)
92 return (a.x * a.x + a.y * a.y + a.z * a.z);
94 __forceinline__ __host__ __device__ float dist3(float3 a, float3 b)
98 __forceinline__ __host__ __device__ float3 operator*(float3 a, float3 b)
100 return make_float3(a.x * b.x, a.y * b.y, a.z * b.z);
102 __forceinline__ __host__ __device__ void operator*=(float3& a, float3 b)
108 __forceinline__ __host__ __device__ void operator*=(float3& a, float b)
114 __forceinline__ __device__ void atomicAdd(float3* addr, float3 val)
116 atomicAdd(&addr->x, val.x);
117 atomicAdd(&addr->y, val.y);
118 atomicAdd(&addr->z, val.z);
120 /****************************************************************/
123 __forceinline__ __host__ __device__ float4 make_float4(float s)
125 return make_float4(s, s, s, s);
127 __forceinline__ __host__ __device__ float4 make_float4(float3 a)
129 return make_float4(a.x, a.y, a.z, 0.0f);
131 __forceinline__ __host__ __device__ float4 operator+(float4 a, float4 b)
133 return make_float4(a.x + b.x, a.y + b.y, a.z + b.z, a.w + b.w);
135 __forceinline__ __host__ __device__ float4 operator+(float4 a, float3 b)
137 return make_float4(a.x + b.x, a.y + b.y, a.z + b.z, a.w);
139 __forceinline__ __host__ __device__ float4 operator-(float4 a, float4 b)
141 return make_float4(a.x - b.x, a.y - b.y, a.z - b.z, a.w - b.w);
143 __forceinline__ __host__ __device__ float4 operator*(float4 a, float k)
145 return make_float4(k * a.x, k * a.y, k * a.z, k * a.w);
147 __forceinline__ __host__ __device__ void operator+=(float4& a, float4 b)
154 __forceinline__ __host__ __device__ void operator+=(float4& a, float3 b)
160 __forceinline__ __host__ __device__ void operator-=(float4& a, float3 b)
167 __forceinline__ __host__ __device__ float norm(float4 a)
169 return sqrt(a.x * a.x + a.y * a.y + a.z * a.z + a.w * a.w);
172 __forceinline__ __host__ __device__ float dist3(float4 a, float4 b)
177 #endif /* VECTYPE_OPS_CUH */