Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[GPU] POC for new OCL kernels approach #26985

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

[GPU] POC for new OCL kernels approach #26985

wants to merge 3 commits into from
+2,681 −261

Conversation

vladimir-paramuzov
Copy link
Contributor

Details:

  • Currently we have separate kernel selector component with independent API and kernels list which leads to some data structures conversion overheads and it doesn't allow to have unified kernel selection logic. So the goals of this change are:
    • Make OCL jitters work with common primitive/layout descriptors
    • Have better multi-kernel impls design
    • Allow registration of OCL impls in the common impls list
    • Use ImplementationManager to check applicability of individual OCL impl
  • Several impls are reimplemented in scope of the POC:
    • CTCLoss for the simplest case (static shapes only, single impl)
    • GroupNormalization for the multi-kernel impl and multiple kernel versions
    • ROPE for dynamic-shape impl

@vladimir-paramuzov vladimir-paramuzov added WIP work in progress no_stale Do not mark as stale labels Oct 10, 2024
@github-actions github-actions bot added the category: GPU OpenVINO GPU plugin label Oct 10, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
category: GPU OpenVINO GPU plugin no_stale Do not mark as stale WIP work in progress
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@vladimir-paramuzov