blob: fbd462b36831e511d8d056893a0fe92e49707a9f (
plain)
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
|
/* PR middle-end/111017 */
#include <omp.h>
#define DIM 32
#define N (DIM*DIM)
int
main ()
{
int a[N], b[N], c[N];
int dim = DIM;
for (int i = 0; i < N; i++)
{
a[i] = 3*i;
b[i] = 7*i;
c[i] = 42;
}
#pragma omp parallel for collapse(2)
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
c[j] = a[j] + b[j];
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
if (c[j] != a[j] + b[j] || c[j] != 3*j +7*j)
__builtin_abort ();
for (int i = 0; i < N; i++)
c[i] = 42;
#pragma omp parallel for collapse(2)
for (int i = 0; i < dim; i++)
for (int j = (i*dim); j < (i*dim + dim); j++)
c[j] = a[j] + b[j];
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
if (c[j] != a[j] + b[j] || c[j] != 3*j +7*j)
__builtin_abort ();
for (int i = 0; i < N; i++)
c[i] = 42;
for (int dev = 0; dev <= omp_get_num_devices(); dev++)
{
#pragma omp target teams loop device(dev) map(to:a,b) map(from:c)
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
c[j] = a[j] + b[j];
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
if (c[j] != a[j] + b[j] || c[j] != 3*j +7*j)
__builtin_abort ();
for (int i = 0; i < N; i++)
c[i] = 42;
#pragma omp target teams loop device(dev) map(to:a,b) map(from:c)
for (int i = 0; i < dim; i++)
for (int j = (i*dim); j < (i*dim + dim); j++)
c[j] = a[j] + b[j];
for (int i = 0; i < DIM; i++)
for (int j = (i*DIM); j < (i*DIM + DIM); j++)
if (c[j] != a[j] + b[j] || c[j] != 3*j +7*j)
__builtin_abort ();
for (int i = 0; i < N; i++)
c[i] = 42;
}
return 0;
}
|
