Skip to content

Conversation

@jzc
Copy link
Contributor

@jzc jzc commented Oct 16, 2024

computeFunctionToKernelsMapping did not compute the mapping correctly for leaves of its call graph if the call graph for leaves 3 levels or more deep, which results in some kernels not having inferred calls-indirectly being attached. This fixes the logic and cleans up the duplication a bit in the function.

@jzc jzc requested a review from a team as a code owner October 16, 2024 23:51
@jzc jzc temporarily deployed to WindowsCILock October 16, 2024 23:52 — with GitHub Actions Inactive
@jzc jzc requested a review from AlexeySachkov October 16, 2024 23:54
@jzc jzc temporarily deployed to WindowsCILock October 17, 2024 00:36 — with GitHub Actions Inactive
if (It == CG.end())
return;

Mapping[F].insert(Kernel);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

So, when we entered a leaf, we wouldn't have anything in call graph for it and therefore wouldn't update the mapping - is my understanding of the problem correct?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yea, that's correct

@AlexeySachkov AlexeySachkov merged commit 8398698 into intel:sycl Oct 21, 2024
13 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants