2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2012,2018, 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_CLH
37 #define VECTYPE_OPS_CLH
40 * AMD OpenCL compiler will fail with exotic message
41 * "Error: Undeclared function index 1024" if make_float4
42 * is inlined (nbnxnx_ocl_kernel_nvidia.clh call in line 375).
45 #define _VECTYPE_OPS_INLINE_
47 #if defined(_VECTYPE_OPS_INLINE_)
48 #define _INLINE_ inline
56 _INLINE_ float norm_f3(float3 a)
58 return sqrt(dot(a, a));
60 _INLINE_ float norm_ref_f3(float3 a)
62 return sqrt(a.x * a.x + a.y * a.y + a.z * a.z);
64 _INLINE_ float norm2(float3 a)
68 _INLINE_ float norm2_ref(float3 a)
70 return (a.x * a.x + a.y * a.y + a.z * a.z);
72 _INLINE_ float dist3_f3(float3 a, float3 b)
74 return distance(b, a);
76 _INLINE_ float dist3_ref_f3(float3 a, float3 b)
78 return norm_ref_f3(b - a);
81 _INLINE_ void atomicAdd_l_f(volatile __local float *addr, float val)
86 } next, expected, current;
90 expected.f32 = current.f32;
91 next.f32 = expected.f32 + val;
92 current.u32 = atomic_cmpxchg( (volatile __local unsigned int *)addr, expected.u32, next.u32);
94 while (current.u32 != expected.u32);
96 _INLINE_ void atomicAdd_l_f3(__local float3 *addr, float3 val)
98 atomicAdd_l_f( ((__local float*)(addr)), val.x);
99 atomicAdd_l_f( ((__local float*)(addr))+1, val.y);
100 atomicAdd_l_f( ((__local float*)(addr))+2, val.z);
102 _INLINE_ void atomicAdd_g_f(volatile __global float *addr, float val)
107 } next, expected, current;
111 expected.f32 = current.f32;
112 next.f32 = expected.f32 + val;
113 current.u32 = atomic_cmpxchg( (volatile __global unsigned int *)addr, expected.u32, next.u32);
115 while (current.u32 != expected.u32);
118 /* On the host float3, on the device float1 because f3 translates to f4 and messes up memory indexing */
119 _INLINE_ void atomicAdd_g_f3(__global float *addr, const float3 val)
121 atomicAdd_g_f(addr, val.x);
122 atomicAdd_g_f(addr + 1, val.y);
123 atomicAdd_g_f(addr + 2, val.z);
126 /****************************************************************/
131 _INLINE_ float norm_f4(float4 a)
133 return sqrt(dot(a, a));
136 _INLINE_ float norm_ref_f4(float4 a)
138 return sqrt(a.x * a.x + a.y * a.y + a.z * a.z + a.w * a.w);
141 _INLINE_ float dist3_f4(float4 a, float4 b)
143 return norm_f4(b - a);
146 _INLINE_ float dist3_ref_f4(float4 a, float4 b)
148 return norm_ref_f4(b - a);
150 #endif /* VECTYPE_OPS_CLH */