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.

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

Fix deadlock for CUDA #4044

Merged
merged 1 commit into from
Jul 22, 2024
Merged

Commits on Jul 22, 2024

  1. Fix deadlock for CUDA

    It has been noticed that Tests/GPU/CNS/Exec/RT hangs with
    `amrex.the_arena_init_size=0 amrex.the_arena_release_threshold=0`. The issue
    appears to be CUDA host callback functions do not work well with cudaFree in
    the main host thread. Note that we don't have any CUDA API calls in the host
    callback function. Also note that cudaMall seems work and using a single GPU
    stream also works.
    
    A workaround is implemented to avoid cudaFree when there are host callback
    functions inside an MFIter loop.
    WeiqunZhang committed Jul 22, 2024
    Configuration menu
    Copy the full SHA
    49463ad View commit details
    Browse the repository at this point in the history