portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2026-08-31 06:49:36 +01:00
Code Releases Activity

More FI_MR related

Browse Source
This commit is contained in:
Peter Boyle
2026-08-28 22:01:36 -04:00
parent 43c6573ca4
commit e03797e882
15 changed files with 95 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
systems/Frontier/nrhs_fault.job
+1
View File
@@ -60,6 +60,7 @@ export OMP_NUM_THREADS=7
# .nfs quota disaster of 2026-08-25) obeys ulimit -c like the kernel's (ROCgdb docs, "AMD GPU
# core dumps"); Slurm propagates the batch shell's limits to srun tasks by default.
ulimit -c 0
export FI_MR_CACHE_MONITOR=kdreg2 # REQUIRED for device-buffer MPI on Slingshot: libfabric memhooks monitor (default) is defective, see systems/WorkArounds.txt (libfabric #11451)
export MPICH_GPU_SUPPORT_ENABLED=1
export MPICH_SMP_SINGLE_COPY_MODE=CMA
export MPICH_OFI_NIC_POLICY=GPU