Maximizing Performance on HPC Falcon #16768
-
Hello, I am trying to understand how One thing is clear to me: However, I'm not sure how shared memory works on Falcon. Particularly, what the One other thing I'm concerned about is the I guess my question is the following: How should I set the |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 3 replies
-
For full MPI and no shared memory parallelism (1 thread), I would do OMP_NUM_THREADS=1 (does not matter though, --n-threads should have the final say on the number of threads, and 1 is the default anyway) and MV2_ENABLE_AFFINITY=1, which is recommended for single threaded applications. Guillaume |
Beta Was this translation helpful? Give feedback.
For full MPI and no shared memory parallelism (1 thread), I would do OMP_NUM_THREADS=1 (does not matter though, --n-threads should have the final say on the number of threads, and 1 is the default anyway) and MV2_ENABLE_AFFINITY=1, which is recommended for single threaded applications.
Guillaume