openGPMP
Open Source Mathematics Package
_cuda_mtx.cuh
Go to the documentation of this file.
1 /*************************************************************************
2  *
3  * Project
4  * _____ _____ __ __ _____
5  * / ____| __ \| \/ | __ \
6  * ___ _ __ ___ _ __ | | __| |__) | \ / | |__) |
7  * / _ \| '_ \ / _ \ '_ \| | |_ | ___/| |\/| | ___/
8  *| (_) | |_) | __/ | | | |__| | | | | | | |
9  * \___/| .__/ \___|_| |_|\_____|_| |_| |_|_|
10  * | |
11  * |_|
12  *
13  * Copyright (C) Akiel Aries, <akiel@akiel.org>, et al.
14  *
15  * This software is licensed as described in the file LICENSE, which
16  * you should have received as part of this distribution. The terms
17  * among other details are referenced in the official documentation
18  * seen here : https://akielaries.github.io/openGPMP/ along with
19  * important files seen in this project.
20  *
21  * You may opt to use, copy, modify, merge, publish, distribute
22  * and/or sell copies of the Software, and permit persons to whom
23  * the Software is furnished to do so, under the terms of the
24  * LICENSE file. As this is an Open Source effort, all implementations
25  * must be of the same methodology.
26  *
27  *
28  *
29  * This software is distributed on an AS IS basis, WITHOUT
30  * WARRANTY OF ANY KIND, either express or implied.
31  *
32  ************************************************************************/
33 
40 #ifndef _CUDA_MTX_CUH
41 #define _CUDA_MTX_CUH
42 
43 namespace gpmp {
44 
45 namespace accl {
46 
51 class CUDAmtx {
52  public:
56  __global__ void mtx_add_(int n, float *x, float *y);
57 };
58 } // namespace accl
59 } // namespace gpmp
60 
61 #endif
Features CUDA GPU acceleration methods related to matrix operations.
Definition: _cuda_mtx.cuh:51
__global__ void mtx_add_(int n, float *x, float *y)
Multiply 2 N x M matrix.
The source C++ openGPMP namespace.