Meeting 2015 01

January 2015 OMPI Developer's Meeting

This is a standalone meeting; it is not being held in conjunction with an MPI Forum meeting.

Logistics

Doodle for choosing the date: https://doodle.com/zzaupgxge9y6medu

• Date: 9am Tuesday, January 27 through 3pm Thursday, January 29, 2015
• Location: Cisco facility (outside Dallas):

2200 East President George Bush Highway
Richardson, Texas 75082-3550

Google maps link: https://goo.gl/maps/SNrbu

Attendees

• Jeff Squyres - Cisco
• Howard Pritchard - Los Alamos
• Ralph Castain - Intel
• George Bosilca - U. Tennessee, Knoxville
• Dave Goodell - Cisco
• Edgar Gabriel (not Monday probably) - U. Houston
• Vish Venkatesan (not Tuesday) - Intel
• Geoff Paulsen - IBM
• Joshua Ladd - Mellanox Technologies
• Rayaz Jagani - IBM
• Dave Solt - IBM
• Perry Schmidt - IBM
• Nathan Hjelm (remote) - Los Alamos
• Naoyuki Shida - Fujitsu
• Shinji Sumimoto - Fujitsu
• ...please add your name if you plan to attend...

Topics

• Jeff/Howard: Branch for v1.9
• Jeff/Howard: Jenkins integration with Github:
  • how do we do multiple Jenkins servers? (e.g., running at different organizations)
• Ralph: Review: v1.8 series / RM experience with Github and Jenkins and the release process
  • Ralph's feedback: lots more PRs than we used to have CMRs
  • Ralph's feedback: people seem to be relying on Jenkins for correctness, when Jenkins is really just a smoke test
• Nathan: Performance of freelists and other common OPAL classes with OPAL_ENABLE_MULTI_THREADS==1 (as discussed in [GitHub]). Part of this is done already -- LIFO is a bit faster now (with threads), etc.
• Ralph: Scalable startup, including:
  • Async modex, static endpoint support
  • Re-define the role of PML/BTL add_procs: need to move to a more lazy-based setup of peers
  • Memory footprint reduction
• Ralph: RTE-MPI sharing of BTLs
• Ralph: Data passing down to OPAL
  • Revising process naming scheme
  • MPI_Info
• Howard: Progress on async progress
  • What happened to this proposal: http://www.open-mpi.org/community/lists/devel/2014/02/14170.php
• Jeff: Progress on thread-multiple support
• Ralph/Nathan: MTL overhead reduction
• Intel/LANL: MTL selection issue (PSM vs. OFI)
• Nathan: Enhance MTL interface to include one-sided and atomics
• Ralph: Error response planning (e.g., BTL error propagation up from OPAL into ORTE and OMPI, particularly in the presence of async progress).
• Ralph: Collective switching points & MPI tuning params - what is required to change them. Had a discussion brought up by Mellanox, and we never finished this.
• Vish: Memkind integration: see http://www.open-mpi.org/community/lists/devel/2014/11/16320.php
• Jeff: MPI extensions: MPIX_ prefix, or OMPI_ prefix?
• Ralph: PMIx and ORCM updates
• Nathan: --disable-smp-locks: remove this option?
  • See RFC email http://www.open-mpi.org/community/lists/devel/2015/01/16736.php
  • See, in particular, George's replies
• Fujitsu: future plans for Open MPI development

Resolved

• TBD

Since this will be a full meeting in itself, we'll have a good amount of time for discussion, design, and for hacking!