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

[XLA] Make our LLVM usage more googley #24706

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[XLA] Make our LLVM usage more googley #24706

wants to merge 1 commit into from

Commits on Nov 7, 2024

  1. [XLA] Make our LLVM usage more googley 

    With the advent of heterogenuous compute, XLA compilation now encompasses sub-compilation for multiple devices. These all can use LLVM, but with different settings. Today this means it is possible for one XLA client to reinitialize LLVM's global state while another client is in the middle of compilation.

Add a global lock around our LLVM usage. Concurrent compilation is still allowed, as long as both invocations have the same set of options. This means from within the same client multiple compilation invocations should still be non-blocking.

PiperOrigin-RevId: 688333737
    @vsytch @Google-ML-Automation
    vsytch authored and Google-ML-Automation committed Nov 7, 2024
    Configuration menu
    Copy the full SHA
    da07e1e View commit details
    Browse the repository at this point in the history