Re: [OMPI users] Setting coll_sm_priority = 35 didn't improve communication performance

Thank you, Gilles for the pointer. I see what operations supported in SM now. On Wed, Dec 9, 2015 at 8:05 PM, Gilles Gouaillardet wrote: > Saliya, > > from ompi/mca/coll/sm/coll_sm_module.c in mca_coll_sm_comm_query() > sm_module->super.coll_allgatherv = NULL; > > that means the coll sm module d

Re: [OMPI users] Setting coll_sm_priority = 35 didn't improve communication performance

Saliya, from ompi/mca/coll/sm/coll_sm_module.c in mca_coll_sm_comm_query() sm_module->super.coll_allgatherv = NULL; that means the coll sm module does *not* implement allgatherv, so openmpi will use the next module (which is very likely the default module, that is why there is no performance i

Re: [OMPI users] Setting coll_sm_priority = 35 didn't improve communication performance

I did this, but output is a bit unclear to me. For example it has lines like [j-053:221827] mca: base: components_register: found loaded component sm and in the same node, same process reports, [j-053:221827] coll:find_available: coll component sm is not available Does this mean SM is not avail

Re: [OMPI users] Setting coll_sm_priority = 35 didn't improve communication performance

Try to run with coll_base_verbose 1000, just to see what collective module got effectively loaded. Aurélien -- Aurélien Bouteiller, Ph.D. ~~ https://icl.cs.utk.edu/~bouteill/ > Le 9 déc. 2015 à 09:53, Saliya Ekanayake a écrit : > > Hi, > > In a previous ema

[OMPI users] Setting coll_sm_priority = 35 didn't improve communication performance

Hi, In a previous email, I wanted to know how to enable shared memory collectives and I was told setting the coll_sm_priority to anything over 30 should do it. I tested this for a microbenchmark on allgatherv, but it didn't improve performance over the default setting. See below, where I tested f