Björne2
New Contributor
New ContributorScatter-updates to global memory and false sharing
I have an array of unique indexes. Let's call it I. So e.g I = {3, 9, 15, 22, 23, 24, ...}. I want to update all elements of a global float buffer G matching those indexes. Like this:
for (int i = 0; i < n; i++) {
G[I[i]] += 123.4;
}
If all indexes in I are unique, is it ok to use #pragma ivdep on the loop, or will that lead to false sharing problems? The reason I ask is because as the attached screenshot shows the loop has an II of 338 which is terrible. I suspect that #pragma ivdep is not ok here, but I'm unsure of why. If #pragma ivdep is not ok are there other ways to avoid the terrible high II?
