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
|
// incrementArrays.cu
#include <stdio.h>
#include <assert.h>
#include <cuda.h>
void incrementArrayOnHost(float *a, int N)
{
int i;
for (i=0; i<N; i++) {
a[i] = a[i] + 1.f;
}
}
__global__ void incrementArrayOnDevice(float *a, int N)
{
int idx = blockIdx.x * blockDim.x + threadIdx.x;
if (idx<N) {
a[idx] = a[idx] + 1.f;
}
}
int main(void)
{
float *a_h, *b_h; // pointers to host memory
float *a_d; // pointer to device memory
int i, N = 10;
size_t size = N*sizeof(float);
// allocate arrays on host
a_h = (float *)malloc(size);
b_h = (float *)malloc(size);
// allocate array on device
cudaMalloc((void **) &a_d, size);
// initialization of host data
for (i=0; i<N; i++) {
printf("%i\n", i);
a_h[i] = (float) i;
}
printf("\n");
// copy data from host to device
cudaMemcpy(a_d, a_h, sizeof(float)*N, cudaMemcpyHostToDevice);
// do calculation on host
incrementArrayOnHost(a_h, N);
// do calculation on device
// 01 - compute execution configuration
int blockSize = 4;
int nBlocks = N/blockSize + (N%blockSize == 0?0:1);
// 02 - call incrementArrayOnDevice kernel
incrementArrayOnDevice <<< nBlocks, blockSize >>> (a_d, N);
// Retrieve result from device and store in b_h
// (dst, src, count, kind)
cudaMemcpy(b_h, a_d, sizeof(float)*N, cudaMemcpyDeviceToHost);
// check result
for (i=0; i<N; i++) {
printf("%.2f\n", b_h[i]);
assert(a_h[i] == b_h[i]);
}
// cleanup
free(a_h); free(b_h); cudaFree(a_d);
}
|
