Skip to content
Snippets Groups Projects
Commit 70383eec authored by Anlun Xu's avatar Anlun Xu Committed by TensorFlow Release Automation
Browse files

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

[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
parent 5b7330c8
No related merge requests found
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment