Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Ralph Castain
Crud - sorry about that. There was no intent to exclude - we just sometimes forget that others who don't monitor the lists with our degree of obsession might also want to participate. There isn't a whole lot to report beyond what is in the thread, really. George provided a little more

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Vallee, Geoffroy R.
Too bad all this happened so fast otherwise ORNL would have at least participated to the call to understand what is going to happen (since we have a RTE module that we maintain). Any chance we could have a summary? Thanks, On May 1, 2014, at 2:40 PM, Ralph Castain wrote:

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Ralph Castain
Just to report back to the list: the three of us discussed this at some length, and decided we like George's proposed solution. Looks like a good clean approach that provides flexibility for the future. So we will introduce it when the BTLs move down to OPAL as (a) George already has it

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Jeff Squyres (jsquyres)
Done! On May 1, 2014, at 11:22 AM, George Bosilca wrote: > Apparently we are good today at 2PM EST. Fire-up the webex ;) > > George. > > On May 1, 2014, at 10:35 , Jeff Squyres (jsquyres) wrote: > >> http://doodle.com/hhm4yyr76ipcxgk2 >> >> >> On

Re: [OMPI devel] RFC: continue cleanup of build system abstractions

2014-05-01 Thread Ralph Castain
Next step: OMPI_INSTALL_BINARIES -> OPAL_INSTALL_BINARIES OMPI_ENSURE_CONTAINS_OPTFLAGS -> OPAL_ENSURE_CONTAINS_OPTFLAGS OMPI_CFLAGS_BEFORE_PICKY -> OPAL_CFLAGS_BEFORE_PICKY Most of the rest of the changes are in the config area and configure.ac - we'll start with the following:

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread George Bosilca
Apparently we are good today at 2PM EST. Fire-up the webex ;) George. On May 1, 2014, at 10:35 , Jeff Squyres (jsquyres) wrote: > http://doodle.com/hhm4yyr76ipcxgk2 > > > On May 1, 2014, at 10:25 AM, Ralph Castain > wrote: > >> sure - might be

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Jeff Squyres (jsquyres)
http://doodle.com/hhm4yyr76ipcxgk2 On May 1, 2014, at 10:25 AM, Ralph Castain wrote: > sure - might be faster that way :-) > > On May 1, 2014, at 6:59 AM, Jeff Squyres (jsquyres) > wrote: > >> Want to have a phone call/webex to discuss? >> >> >> On

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Ralph Castain
sure - might be faster that way :-) On May 1, 2014, at 6:59 AM, Jeff Squyres (jsquyres) wrote: > Want to have a phone call/webex to discuss? > > > On May 1, 2014, at 9:43 AM, Ralph Castain wrote: > >> The problem we'll have with BTLs in opal is going

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Jeff Squyres (jsquyres)
Want to have a phone call/webex to discuss? On May 1, 2014, at 9:43 AM, Ralph Castain wrote: > The problem we'll have with BTLs in opal is going to revolve around that > ompi_process_name_t and will occur in a number of places. I've been trying to > grok George's statement

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Ralph Castain
The problem we'll have with BTLs in opal is going to revolve around that ompi_process_name_t and will occur in a number of places. I've been trying to grok George's statement about accessors and can't figure out a clean way to make that work IF every RTE gets to define the process name a

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Jeff Squyres (jsquyres)
On Apr 30, 2014, at 10:01 PM, George Bosilca wrote: > Why do you need the ompi_process_name_t? Isn’t the opal_identifier_t enough > to dig for the info of the peer into the opal_db? At the moment, I use the ompi_process_name_t for RML sends/receives in the usnic BTL. I

Re: [OMPI devel] [OMPI svn] svn:open-mpi r31577 - trunk/ompi/mca/rte/base

2014-05-01 Thread Ralph Castain
A somewhat simpler solution (since we do use the jobid and vpid in various places) might be to just define an OMPI_PROCESS_NAME_T data type in the rte.h files for each rte, and then let opal_dstore simply store and retrieve that type. Problem solved - except you still need to have a jobid and