Re: [OMPI devel] ORTE local rank
Thanks Ralph! (Adding de...@open-mpi.org to this thread; I think others may be interested, such as Myricom and QLogic) How do we get access to these values; are they in global variables somewhere, or do we make a function call to get them? On May 21, 2007, at 7:58 AM, Ralph H Castain wrote: Well, it took awhile longer than I had thought to get around to dealing with this. However, I have finally put this functionality in the OMPI trunk as of r14707. The local rank and number of local procs now get passed as part of the ORTE name passing system. So, once you get through orte_init (specifically, stage1 as this is broken out in mpi_init), you have both those pieces of information available to you. Let me know if you encounter any difficulties. Ralph -- Jeff Squyres Cisco Systems
Re: [OMPI devel] ORTE local rank
They are sitting in the orte_process_info global variable: orte_process_info.local_rank orte_process_info.num_local_procs Ralph On 5/21/07 9:10 AM, "Jeff Squyres" wrote: > Thanks Ralph! (Adding de...@open-mpi.org to this thread; I think > others may be interested, such as Myricom and QLogic) > > How do we get access to these values; are they in global variables > somewhere, or do we make a function call to get them? > > > On May 21, 2007, at 7:58 AM, Ralph H Castain wrote: > >> Well, it took awhile longer than I had thought to get around to >> dealing with >> this. However, I have finally put this functionality in the OMPI >> trunk as of >> r14707. >> >> The local rank and number of local procs now get passed as part of >> the ORTE >> name passing system. So, once you get through orte_init (specifically, >> stage1 as this is broken out in mpi_init), you have both those >> pieces of >> information available to you. >> >> Let me know if you encounter any difficulties. >> Ralph
[OMPI devel] Outdated PMB_2.2 test suite
All, Would anyone be opposed to me removing the PMB_2.2 test suite from the ompi-tests repository? IMB_2.3 (also in the ompi-tests repository) is more up-to-date. If I don't hear any objections by COB Wednesday, I'll delete PMB_2.2. -Ethan
