blob: b910e251fb1171987939cce041dda5153d4a98ff (
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
79
80
81
|
/* { dg-additional-options "-fopt-info-note-omp" }
{ dg-additional-options "--param=openacc-privatization=noisy" }
{ dg-additional-options "-foffload=-fopt-info-note-omp" }
{ dg-additional-options "-foffload=--param=openacc-privatization=noisy" }
for testing/documenting aspects of that functionality. */
/* { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
aspects of that functionality. */
#include <stdio.h>
#include <openacc.h>
#include <gomp-constants.h>
#define N (32*32*32+17)
int main ()
{
int ary[N];
int ix;
int exit = 0;
int ondev = 0;
int workersize;
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)
/* { dg-note {variable 'ix' declared in block isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-2 } */
/* { dg-warning "region is vector partitioned but does not contain vector partitioned code" "vector" { target *-*-* } .-3 } */
{
#pragma acc loop worker
/* { dg-note {variable 'ix' in 'private' clause isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-1 } */
/* { dg-note {variable 'g' declared in block isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-2 } */
/* { dg-note {variable 'w' declared in block isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-3 } */
/* { dg-note {variable 'v' declared in block isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-4 } */
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;
ondev = 1;
}
else
ary[ix] = ix;
}
}
workersize = NW;
#ifdef ACC_DEVICE_TYPE_radeon
/* AMD GCN has an upper limit of 'num_workers(16)'. */
if (workersize > 16)
workersize = 16;
#endif
for (ix = 0; ix < N; ix++)
{
int expected = ix;
if(ondev)
{
int g = 0;
int w = ix % workersize;
int v = 0;
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;
}
|
