More FI_MR related

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
+1
View File
@@ -58,6 +58,7 @@ source $root/sourceme-rocm7.2.sh
# hung, V2 with OMP_NUM_THREADS=1 completed, 2026-08-25). Each rank has a
# whole GCD; the parallelism is on the device for both.
export OMP_NUM_THREADS=1
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