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

r2.12 cherry-pick: 890a846bdc2 "[xla:gpu] Create a non-atomically upgradeable reader mutex lock that acquires and releases the lock via RAII" #59889

Merged
merged 1 commit into from Mar 3, 2023
Merged

r2.12 cherry-pick: 890a846bdc2 "[xla:gpu] Create a non-atomically upgradeable reader mutex lock that acquires and releases the lock via RAII" #59889

merged 1 commit into from Mar 3, 2023

Commits on Mar 3, 2023

  1. [xla:gpu] Create a non-atomically upgradeable reader mutex lock that … 

    …acquires and releases the lock via RAII

Runtime autotuning needs to be protected by a writer mutex lock. However GpuExecutable runs under a reader mutex lock, so it needs to be upgraded to a writer lock whenever autotuning happens.

PiperOrigin-RevId: 510509236
    @anlunx @tensorflow-jenkins
    anlunx authored and tensorflow-jenkins committed Mar 3, 2023
    Copy the full SHA
    70383ee View commit details
    Browse the repository at this point in the history