mirror of
https://github.com/Kitware/CMake.git
synced 2026-01-22 06:31:29 -06:00
f4fc0667ae
Previously the FindOpenACC module had issues where the contents of OpenACC_<lang>_FLAGS could not be used with target_compile_options when it contained multiple compiler flags.
45 lines
1013 B
C
45 lines
1013 B
C
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
|
|
void vecaddgpu(float* r, float* a, float* b, int n)
|
|
{
|
|
#pragma acc kernels loop present(r, a, b)
|
|
for (int i = 0; i < n; ++i)
|
|
r[i] = a[i] + b[i];
|
|
}
|
|
|
|
int main()
|
|
{
|
|
int n = 100000; /* vector length */
|
|
float* a; /* input vector 1 */
|
|
float* b; /* input vector 2 */
|
|
float* r; /* output vector */
|
|
float* e; /* expected output values */
|
|
int i, errs;
|
|
|
|
a = (float*)malloc(n * sizeof(float));
|
|
b = (float*)malloc(n * sizeof(float));
|
|
r = (float*)malloc(n * sizeof(float));
|
|
e = (float*)malloc(n * sizeof(float));
|
|
for (i = 0; i < n; ++i) {
|
|
a[i] = (float)(i + 1);
|
|
b[i] = (float)(1000 * i);
|
|
}
|
|
/* compute on the GPU */
|
|
#pragma acc data copyin(a [0:n], b [0:n]) copyout(r [0:n])
|
|
{
|
|
vecaddgpu(r, a, b, n);
|
|
}
|
|
/* compute on the host to compare */
|
|
for (i = 0; i < n; ++i)
|
|
e[i] = a[i] + b[i];
|
|
/* compare results */
|
|
errs = 0;
|
|
for (i = 0; i < n; ++i) {
|
|
if (r[i] != e[i]) {
|
|
++errs;
|
|
}
|
|
}
|
|
return errs;
|
|
}
|