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
|
// Comes from:
// https://docs.nvidia.com/cuda/curand/host-api-overview.html#host-api-example
#ifdef _WIN32
# define EXPORT __declspec(dllexport)
#else
# define EXPORT
#endif
/*
* This program uses the host CURAND API to generate 100
* pseudorandom floats.
*/
#include <cuda.h>
#include <curand.h>
#include <stdio.h>
#include <stdlib.h>
#define CUDA_CALL(x) \
do { \
if ((x) != cudaSuccess) { \
printf("Error at %s:%d\n", __FILE__, __LINE__); \
return EXIT_FAILURE; \
} \
} while (0)
#define CURAND_CALL(x) \
do { \
if ((x) != CURAND_STATUS_SUCCESS) { \
printf("Error at %s:%d\n", __FILE__, __LINE__); \
return EXIT_FAILURE; \
} \
} while (0)
EXPORT int curand_main()
{
size_t n = 100;
size_t i;
curandGenerator_t gen;
float *devData, *hostData;
/* Allocate n floats on host */
hostData = (float*)calloc(n, sizeof(float));
/* Allocate n floats on device */
CUDA_CALL(cudaMalloc((void**)&devData, n * sizeof(float)));
/* Create pseudo-random number generator */
CURAND_CALL(curandCreateGenerator(&gen, CURAND_RNG_PSEUDO_DEFAULT));
/* Set seed */
CURAND_CALL(curandSetPseudoRandomGeneratorSeed(gen, 1234ULL));
/* Generate n floats on device */
CURAND_CALL(curandGenerateUniform(gen, devData, n));
/* Copy device memory to host */
CUDA_CALL(
cudaMemcpy(hostData, devData, n * sizeof(float), cudaMemcpyDeviceToHost));
/* Cleanup */
CURAND_CALL(curandDestroyGenerator(gen));
CUDA_CALL(cudaFree(devData));
free(hostData);
return EXIT_SUCCESS;
}
|
