blob: 647d075bb0068753f31507c7a034b5627376225b (
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
73
74
75
76
77
78
|
#include <stdio.h>
#include <openacc.h>
#include <gomp-constants.h>
#define N (32*32*32+17)
#pragma acc routine worker
void __attribute__ ((noinline)) worker (int ary[N])
{
#pragma acc loop worker vector
for (unsigned ix = 0; ix < N; ix++)
{
if (acc_on_device (acc_device_not_host))
{
int g, w, v;
g = __builtin_goacc_parlevel_id (GOMP_DIM_GANG);
w = __builtin_goacc_parlevel_id (GOMP_DIM_WORKER);
v = __builtin_goacc_parlevel_id (GOMP_DIM_VECTOR);
ary[ix] = (g << 16) | (w << 8) | v;
}
else
ary[ix] = ix;
}
}
int main ()
{
int ary[N];
int ix;
int exit = 0;
int ondev = 0;
int workersize, vectorsize;
for (ix = 0; ix < N;ix++)
ary[ix] = -1;
#define NW 32
#define VL 32
#pragma acc parallel num_workers(NW) vector_length(VL) \
copy(ary) copy(ondev)
{
ondev = acc_on_device (acc_device_not_host);
worker (ary);
}
workersize = NW;
vectorsize = VL;
#ifdef ACC_DEVICE_TYPE_radeon
/* AMD GCN has an upper limit of 'num_workers(16)'. */
if (workersize > 16)
workersize = 16;
/* AMD GCN uses the autovectorizer for the vector dimension: the use
of a function call in vector-partitioned code in this test is not
currently supported. */
vectorsize = 1;
#endif
for (ix = 0; ix < N; ix++)
{
int expected = ix;
if(ondev)
{
int g = 0;
int w = (ix / vectorsize) % workersize;
int v = ix % vectorsize;
expected = (g << 16) | (w << 8) | v;
}
if (ary[ix] != expected)
{
exit = 1;
printf ("ary[%d]=%x expected %x\n", ix, ary[ix], expected);
}
}
return exit;
}
|
