1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
|
/* Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of NVIDIA CORPORATION nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
// System includes
#include <stdio.h>
#include <assert.h>
// CUDA runtime
#include <cuda_runtime.h>
// helper functions and utilities to work with CUDA
#include <helper_functions.h>
#include <helper_cuda.h>
#ifndef MAX
#define MAX(a, b) (a > b ? a : b)
#endif
__global__ void testKernel(int val) {
printf("[%d, %d]:\t\tValue is:%d\n", blockIdx.y * gridDim.x + blockIdx.x,
threadIdx.z * blockDim.x * blockDim.y + threadIdx.y * blockDim.x +
threadIdx.x,
val);
}
int main(int argc, char **argv) {
int devID;
cudaDeviceProp props;
// This will pick the best possible CUDA capable device
devID = findCudaDevice(argc, (const char **)argv);
// Get GPU information
checkCudaErrors(cudaGetDevice(&devID));
checkCudaErrors(cudaGetDeviceProperties(&props, devID));
printf("Device %d: \"%s\" with Compute %d.%d capability\n", devID, props.name,
props.major, props.minor);
printf("printf() is called. Output:\n\n");
// Kernel configuration, where a two-dimensional grid and
// three-dimensional blocks are configured.
dim3 dimGrid(2, 2);
dim3 dimBlock(2, 2, 2);
testKernel<<<dimGrid, dimBlock>>>(10);
cudaDeviceSynchronize();
return EXIT_SUCCESS;
}
|
