Skip to content

WeeklyTelcon_20210511

Jeff Squyres edited this page May 11, 2021 · 1 revision

Open MPI Weekly Telecon ---

Attendees (on Web-ex)

  • Jeff Squyres (Cisco)
  • Joseph Schuchart (HLRS)
  • Brendan Cunningham (Cornelis Networks)
  • Hessam Mirsadeghi (NVIDIA))
  • Sam Gutierrez (LANL)
  • Todd Kordenbrock (Sandia)
  • William Zhang (AWS)
  • Harumi Kuno (HPE)
  • Tomislav Janjusic (NVIDIA)
  • David Bernholdt (ORNL)
  • Raghu Raja (secret startup)
  • Edgar Gabriel (UH)

not there today (I keep this for easy cut-n-paste for future notes)

  • Akshay Venkatesh (NVIDIA)
  • Artem Polyakov (NVIDIA)
  • Aurelien Bouteiller (UTK)
  • Austen Lauria (IBM)
  • Brandon Yates (Intel)
  • Brian Barrett (AWS)
  • Charles Shereda (LLNL)
  • Christoph Niethammer (HLRS)
  • Erik Zeiske (HPE)
  • Geoffrey Paulsen (IBM)
  • Geoffroy Vallee (ARM)
  • George Bosilca (UTK)
  • Howard Pritchard (LANL)
  • Josh Hursey (IBM)
  • Joshua Ladd (NVIDIA)
  • Marisa Roman (Cornelius)
  • Mark Allen (IBM)
  • Matias Cabral (Intel)
  • Matthew Dosanjh (Sandia)
  • Michael Heinz (Cornelis Networks)
  • Nathan Hjelm (Google)
  • Naughton III, Thomas (ORNL)
  • Noah Evans (Sandia)
  • Ralph Castain (Intel)
  • Scott Breyer (Sandia?)
  • Shintaro iwasaki
  • Xin Zhao (NVIDIA)

New Items

  • Jeff Sq. outlined the fix to the git commit checker CI: https://github.com/open-mpi/ompi/pull/8947.
    • ATM, there's only a somewhat-obscure way to re-trigger this CI test: edit the PR title or PR description (to include even just adding a space). This will re-trigger the PR.
    • Jeff Sq. will be looking at this this weekend to see if there's a better way to re-trigger the CI test.

4.0.x

  • We're still waiting on Datatype issues now reported in v4.1.1
    • Potentially getting access to a machine to replicate after today.

v4.1.x

  • In holding pattern waiting for Datatype issue (see above).
  • We did merge a bunch of pending 4.1.x PRs.
  • If we need to go back and make a 4.1.2 with a datatype fix, we'll do the Right Git Stuff to make a minimum-distance 4.1.2.

v5.0.0

  • Geoff and Austen were not here; no real update.

Master

  • No discussion.

Reformatting master

  • RMs had discussion about this yesterday.
    • A new point was realized in the last week: clang-tidy makes us have heavy-handed style guide. I.e., we have to make decisions about all style issues -- we can't tell clang-tidy to ignore specific rules.
    • This is a deal-breaker.
    • Our style guide is intentionally very light touch -- very few rules.
    • It sounds like clang-tidy is simply not the tool for us.
  • The RMs therefore propose the following:
    • Accept what has already been done / merged in OPAL and tests.
    • Make sure that those changes are properly PR'ed over to v5.0.x.
    • Drop the pending reformatting OMPI/OSHMEM PRs. I.e., do no further reformatting.
  • If someone cares, see if there is another tool out there that would allow us to do "light touch" rules.
    • Linux kernel community checkpatch was discussed, but offhand, we think that their style rules will not be compatible with ours.

PMIx

  • No discussion.

PRRTE v2.0

  • No update

MTT

  • No discussion.

Longer Term discussions

  • No discussion.
Clone this wiki locally