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
|
// RUN: %libomptarget-compile-generic && env OMP_MAX_ACTIVE_LEVELS=2 %libomptarget-run-generic | %fcheck-generic -allow-empty
#include <assert.h>
#include <omp.h>
#include <stdio.h>
#include <stdlib.h>
const int magic_num = 7;
int main(int argc, char *argv[]) {
const int N = 128;
const int num_devices = omp_get_num_devices();
// No target device, just return
if (num_devices == 0) {
printf("PASS\n");
return 0;
}
const int src_device = 0;
int dst_device = num_devices - 1;
int length = N * sizeof(int);
int *src_ptr = omp_target_alloc(length, src_device);
int *dst_ptr = omp_target_alloc(length, dst_device);
assert(src_ptr && "src_ptr is NULL");
assert(dst_ptr && "dst_ptr is NULL");
#pragma omp target teams distribute parallel for device(src_device) \
is_device_ptr(src_ptr)
for (int i = 0; i < N; ++i) {
src_ptr[i] = magic_num;
}
int rc =
omp_target_memcpy(dst_ptr, src_ptr, length, 0, 0, dst_device, src_device);
assert(rc == 0 && "error in omp_target_memcpy");
int *buffer = malloc(length);
assert(buffer && "failed to allocate host buffer");
#pragma omp target teams distribute parallel for device(dst_device) \
map(from : buffer[0 : N]) is_device_ptr(dst_ptr)
for (int i = 0; i < N; ++i) {
buffer[i] = dst_ptr[i] + magic_num;
}
for (int i = 0; i < N; ++i)
assert(buffer[i] == 2 * magic_num);
printf("PASS\n");
// Free host and device memory
free(buffer);
omp_target_free(src_ptr, src_device);
omp_target_free(dst_ptr, dst_device);
return 0;
}
// CHECK: PASS
|
