blob: 8e640b7fff3aa4d1d6a34f3aafb1d875e6e8d647 (
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
|
// Unonptimized, we need 24000000 bytes heap
// RUN: %libomptarget-compilexx-generic
// RUN: env LIBOMPTARGET_HEAP_SIZE=24000000 \
// RUN: %libomptarget-run-generic 2>&1 | %fcheck-generic
// RUN: %libomptarget-compileoptxx-run-and-check-generic
// REQUIRES: libc
#include <iostream>
template <typename LOOP_BODY>
inline void forall(int Begin, int End, LOOP_BODY LoopBody) {
#pragma omp target parallel for schedule(static)
for (int I = Begin; I < End; ++I) {
LoopBody(I);
}
}
#define N (1000)
//
// Demonstration of the RAJA abstraction using lambdas
// Requires data mapping onto the target section
//
int main() {
double A[N], B[N], C[N];
for (int I = 0; I < N; I++) {
A[I] = I + 1;
B[I] = -I;
C[I] = -9;
}
#pragma omp target data map(tofrom : C[0 : N]) map(to : A[0 : N], B[0 : N])
{
forall(0, N, [&](int I) { C[I] += A[I] + B[I]; });
}
int Fail = 0;
for (int I = 0; I < N; I++) {
if (C[I] != -8) {
std::cout << "Failed at " << I << " with val " << C[I] << std::endl;
Fail = 1;
}
}
// CHECK: Succeeded
if (Fail) {
std::cout << "Failed" << std::endl;
} else {
std::cout << "Succeeded" << std::endl;
}
return 0;
}
|
