Skip to content

Conversation

@uwedolinsky
Copy link
Contributor

@uwedolinsky uwedolinsky commented Jul 21, 2025

Makes most operations including memory copies asynchronous except enqueueBufferMap

Worker threads wait for dependent events instead of the main thread.

The state struct is now constructed by the threads instead of being constructed by the main thread and copied which

  1. reduces the capturing overhead in the enqueue lambda
  2. enabled removing mutable from enqueue lambda

Also removing #ifdef NATIVECPU_USE_OCK

@uwedolinsky uwedolinsky requested a review from a team as a code owner July 21, 2025 18:31
@uwedolinsky uwedolinsky marked this pull request as draft July 21, 2025 18:33
@uwedolinsky uwedolinsky changed the title [SYCL][NATIVECPU] faster enqueues and async ops [SYCL][NATIVECPU] async ops, wait for dependencies in threads Jul 28, 2025
@uwedolinsky
Copy link
Contributor Author

@intel/llvm-gatekeepers This looks ready to merge. Thank you.

@sommerlukas sommerlukas merged commit 1dee8fc into intel:sycl Aug 18, 2025
49 of 50 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.

3 participants