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

PR #19116: [XLA:CPU] [oneDNN] Refactoring oneDNN Memory Util for Custom Call oneDNN Thunk Runtime Support #19121

Merged
merged 1 commit into from
Nov 15, 2024
Merged

PR #19116: [XLA:CPU] [oneDNN] Refactoring oneDNN Memory Util for Custom Call oneDNN Thunk Runtime Support #19121

merged 1 commit into from
Nov 15, 2024
+11 −7

Commits on Nov 15, 2024

  1. PR #19116: [XLA:CPU] [oneDNN] Refactoring oneDNN Memory Util for Cust… 

    …om Call oneDNN Thunk Runtime Support

Imported from GitHub PR #19116

At thunk execution, the memory buffer info for oneDNN is created based on the shapes of the input arguments and the output results. This PR refactors the `onednn_memory_util` to create memory references from shape, which will be used in a separate PR to add custom call oneDNN thunk support.
Copybara import of the project:

--
8664ea2 by Om Thakkar <[email protected]>:

onednn_memory_util refactoring for thunk support

Merging this change closes #19116

COPYBARA_INTEGRATE_REVIEW=#19116 from Intel-tensorflow:othakkar/memref_onednn_mem_util 3389b1a
PiperOrigin-RevId: 697001291
    @othakkar @Google-ML-Automation
    othakkar authored and Google-ML-Automation committed Nov 15, 2024
    Configuration menu
    Copy the full SHA
    4d5f691 View commit details
    Browse the repository at this point in the history