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
{lib}[GCC 11.2.0-13.2.0] UCX 1.16.0-rc4 #20237
Conversation
Test report by @zao |
|
@boegelbot please test @ generoso |
@boegel: Request for testing this PR well received on login1 PR test command '
Test results coming soon (I hope)... - notification for comment with ID 2026148011 processed Message to humans: this is just bookkeeping information for me, |
Test report by @boegelbot |
Test report by @zao |
Test report by @boegel |
Going in, thanks @hajgato! |
Recent intel MPI might need ucx >=1.16.0 if MLNX/NVIDIA OFED >= 23.10 is installed.
(We experienced infinite hangs with FDS/6.8.0-intel-2022b, and swapping to UCX-1.16.0-rc4 solved the problem. UCX < 1.16 did not solve the problem) Note that only AMD CPUs are affected, we did not get the same problem with Intel CPUs.
With our previous OFED 23.04 version, we did not have the problem.