36
edits
Changes
m
→OpenMP GPU Basic Implementation
err=0.0f;
#pragma omp target
#pragma omp parallel
{
#pragma omp parallel for shared(nx, Anew, A) reduction(max:err)
for(int i = 1; i < nx-1; i++) {
Anew[i] = 0.5f * (A[i+1] + A[i-1]);
err = fmax(err, fabs(Anew[i] - A[i]));
}
#pragma omp parallel for shared(nx, Anew, A)
for( int i = 1; i < nx-1; i++ ) {
A[i] = Anew[i];
}
</source>
=== OpenMP GPU Proper Implementation ===
