target_depend_nowait.cpp
1.77 KB
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
// RUN: %libomptarget-compilexx-run-and-check-aarch64-unknown-linux-gnu
// RUN: %libomptarget-compilexx-run-and-check-powerpc64-ibm-linux-gnu
// RUN: %libomptarget-compilexx-run-and-check-powerpc64le-ibm-linux-gnu
// RUN: %libomptarget-compilexx-run-and-check-x86_64-pc-linux-gnu
// RUN: %libomptarget-compilexx-run-and-check-nvptx64-nvidia-cuda
#include <omp.h>
#include <stdio.h>
#define N 1024
int A[N];
int B[N];
int C[N];
int main() {
for (int i = 0; i < N; i++)
A[i] = B[i] = i;
#pragma omp parallel num_threads(2)
{
if (omp_get_thread_num() == 1) {
// map data A & B and move to
#pragma omp target enter data map(to : A, B) depend(out : A[0]) nowait
// no data move since already mapped
#pragma omp target map(A, B) depend(out : A[0]) nowait
{
for (int i = 0; i < N; i++)
++A[i];
for (int i = 0; i < N; i++)
++B[i];
}
// no data move since already mapped
#pragma omp target teams num_teams(1) map(A, B) depend(out : A[0]) nowait
{
for (int i = 0; i < N; i++)
++A[i];
for (int i = 0; i < N; i++)
++B[i];
}
// A updated via update
#pragma omp target update from(A) depend(out : A[0]) nowait
// B updated via exit, A just released
#pragma omp target exit data map(release \
: A) map(from \
: B) depend(out \
: A[0]) nowait
} // if
} // parallel
int Sum = 0;
for (int i = 0; i < N; i++)
Sum += A[i] + B[i];
// Sum is 2 * N * (2 + N - 1 + 2) / 2
// CHECK: Sum = 1051648.
printf("Sum = %d.\n", Sum);
return Sum != 2 * N * (2 + N - 1 + 2) / 2;
}