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
|
/* PR middle-end/66199 */
/* { dg-do run } */
/* { dg-options "-O2 -fopenmp" } */
#pragma omp declare target
int u[1024], v[1024], w[1024];
#pragma omp end declare target
__attribute__((noinline, noclone)) void
f1 (long a, long b)
{
long d;
#pragma omp target teams distribute parallel for simd default(none) firstprivate (a, b) shared(u, v, w)
for (d = a; d < b; d++)
u[d] = v[d] + w[d];
}
__attribute__((noinline, noclone)) void
f2 (long a, long b, long c)
{
long d, e;
#pragma omp target teams distribute parallel for simd default(none) firstprivate (a, b) shared(u, v, w) linear(d) linear(c:5) lastprivate(e)
for (d = a; d < b; d++)
{
u[d] = v[d] + w[d];
c += 5;
e = c;
}
}
__attribute__((noinline, noclone)) void
f3 (long a1, long b1, long a2, long b2)
{
long d1, d2;
#pragma omp target teams distribute parallel for simd default(none) firstprivate (a1, b1, a2, b2) shared(u, v, w) lastprivate(d1, d2) collapse(2)
for (d1 = a1; d1 < b1; d1++)
for (d2 = a2; d2 < b2; d2++)
u[d1 * 32 + d2] = v[d1 * 32 + d2] + w[d1 * 32 + d2];
}
__attribute__((noinline, noclone)) void
f4 (long a1, long b1, long a2, long b2)
{
long d1, d2;
#pragma omp target teams distribute parallel for simd default(none) firstprivate (a1, b1, a2, b2) shared(u, v, w) collapse(2)
for (d1 = a1; d1 < b1; d1++)
for (d2 = a2; d2 < b2; d2++)
u[d1 * 32 + d2] = v[d1 * 32 + d2] + w[d1 * 32 + d2];
}
int
main ()
{
f1 (0, 1024);
f2 (0, 1024, 17);
f3 (0, 32, 0, 32);
f4 (0, 32, 0, 32);
return 0;
}
|
