-
Notifications
You must be signed in to change notification settings - Fork 55
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[release/2.5][ROCm] Fix largeIndexBlockSize #1659
base: release/2.5
Are you sure you want to change the base?
Conversation
On ROCm, hipification converts std::min to ::min, but ::min is not returning the right result. In the meantime, use < operator to comapre. (cherry picked from commit c0266db)
Not yet decided on cherry-picks into 2.5, so want to wait on this PR merge. |
Jenkins build for db33c0f8917630a279e142c898a5011bdef163a1 commit finished as FAILURE |
Jenkins build for db33c0f8917630a279e142c898a5011bdef163a1 commit finished as FAILURE |
Jenkins build for db33c0f8917630a279e142c898a5011bdef163a1 commit finished as FAILURE |
Jenkins build for db33c0f8917630a279e142c898a5011bdef163a1 commit finished as FAILURE Detected error during Pytorch building:
|
Jenkins build for db33c0f8917630a279e142c898a5011bdef163a1 commit finished as FAILURE Detected error during Pytorch building:
|
Jenkins build for db33c0f8917630a279e142c898a5011bdef163a1 commit finished as FAILURE Detected error during Pytorch building:
|
Jenkins build for db33c0f8917630a279e142c898a5011bdef163a1 commit finished as FAILURE Detected error during Pytorch building:
|
On ROCm, hipification converts std::min to ::min, but ::min is not returning the right result. This impacts index_add_ operation on a large tensor, we end up picking the large values instead of max supported block size (128). This leads to GPU accessing memory out of bounds.
While we wait for ::min to be fixed, we can use < operator to compare instead of relying on ::min.
Example Code w/ failure:
(cherry picked from commit c0266db)