[mpiwg-rma] MPI RMA WG call

Joseph Schuchart schuchart at icl.utk.edu
Thu Sep 2 14:16:36 CDT 2021


Thanks for filling in the poll everyone. The poll was meant for generic 
dates but I didn't see a way to make that happen in doodle. I wasn't 
clear on that, sorry. If that changes the entries in the poll please 
just add another entry, I will filter them out (I don't think doodle 
allows you to change your entry).

I don't have a strong opinion on whether we should meet weekly or 
biweekly. We probably have enough topics to discuss for a weekly meeting 
but people have other things to do so maybe we should start biweekly and 
see how far that gets us. Let me know if you think otherwise :)

Cheers
Joseph


On 9/2/21 10:30 AM, Thakur, Rajeev via mpiwg-rma wrote:
>
> And should it be weekly or biweekly. A week goes by pretty quickly.
>
> *From: *mpiwg-rma <mpiwg-rma-bounces at lists.mpi-forum.org> on behalf of 
> Jim Dinan via mpiwg-rma <mpiwg-rma at lists.mpi-forum.org>
> *Reply-To: *MPI WG Remote Memory Access working group 
> <mpiwg-rma at lists.mpi-forum.org>
> *Date: *Thursday, September 2, 2021 at 9:07 AM
> *To: *MPI WG Remote Memory Access working group 
> <mpiwg-rma at lists.mpi-forum.org>
> *Cc: *Jim Dinan <james.dinan at gmail.com>
> *Subject: *Re: [mpiwg-rma] MPI RMA WG call
>
> Thanks for creating the poll. I will be unavailable Sept 14-16 because 
> of the OpenSHMEM workshop, but otherwise have time available on these 
> days. Would you like a response for these specific dates, or for a 
> recurring weekly meeting on that day of the week?
>
> On Mon, Aug 30, 2021 at 6:02 PM Joseph Schuchart via mpiwg-rma 
> <mpiwg-rma at lists.mpi-forum.org <mailto:mpiwg-rma at lists.mpi-forum.org>> 
> wrote:
>
>     Judging from the mails so far, there are multiple slots that might
>     work
>     for people. Not everyone has responded yet though. To simplify the
>     process I have set up a doodle poll:
>
>     https://doodle.com/poll/7yzsvqv4re8xnc59
>     <https://doodle.com/poll/7yzsvqv4re8xnc59>
>
>     It contains all the slots within the timezone constraints
>     mentioned by
>     Bill plus one hour later, minus the MPI Forum meeting slot on
>     Wednesdays. Please put in your availability so we can find a slot
>     starting the week after the EuroMPI/MPI Forum next week. If some
>     slots
>     only work bi-weekly, please mention that in a comment on the poll. In
>     the meantime, we can have a first (informal) meeting Tuesday at 11-12
>     CET (seems to suit at least some) at
>
>     https://tennessee.zoom.us/j/5524140679
>     <https://tennessee.zoom.us/j/5524140679>
>
>     to start a discussion on the items most important for 4.1. It's on
>     short
>     notice so whoever wants to join is welcome, I will start working
>     on the
>     rank terminology in the chapter otherwise ^^
>
>     Thanks,
>     Joseph
>
>     On 8/28/21 3:08 PM, William Gropp wrote:
>     > I have no objections to someone else taking the lead.  We did
>     try to
>     > find a good time for a meeting, but I don’t think that we
>     succeeded,
>     > and I didn’t restart the search in August, and agreeing on a time
>     > remains the first thing to resolve.
>     >
>     > Just to get this restarted, would 10-11 US Central time on Tuesday
>     > work? Keep in mind these constraints - for the US West coast, we
>     try
>     > to start no earlier than 8PT/10CT. For Europe, we try to end by
>     6 CET,
>     > which is noon US CT.
>     >
>     > Let me know if that time works. If it doesn’t suggest something
>     in the
>     > range above.
>     >
>     > Bill
>     >
>     > William Gropp
>     > Director, NCSA
>     > Thomas M. Siebel Chair in Computer Science
>     > University of Illinois Urbana-Champaign
>     > IEEE-CS President-Elect
>     >
>     >
>     >
>     >
>     >> On Aug 28, 2021, at 10:28 AM, Jim Dinan <james.dinan at gmail.com
>     <mailto:james.dinan at gmail.com>
>     >> <mailto:james.dinan at gmail.com <mailto:james.dinan at gmail.com>>>
>     wrote:
>     >>
>     >> I have not seen such an announcement. I think this WG is in
>     need of
>     >> someone to take the lead on organizing meetings and topics. If you
>     >> have the bandwidth to get us moving, I think the help would be
>     very
>     >> much appreciated. @William Gropp <mailto:wgropp at illinois.edu
>     <mailto:wgropp at illinois.edu>> What do
>     >> you think?
>     >>
>     >> Cheers,
>     >>  ~Jim.
>     >>
>     >> On Wed, Aug 25, 2021 at 12:01 PM Joseph Schuchart via mpiwg-rma
>     >> <mpiwg-rma at lists.mpi-forum.org
>     <mailto:mpiwg-rma at lists.mpi-forum.org>
>     >> <mailto:mpiwg-rma at lists.mpi-forum.org
>     <mailto:mpiwg-rma at lists.mpi-forum.org>>> wrote:
>     >>
>     >>     Hi Bill, all,
>     >>
>     >>     Has there been a decision on when to reconvene the RMA working
>     >>     group? I
>     >>     recently changed institutes and might have missed emails
>     sent to
>     >>     my old
>     >>     address...
>     >>
>     >>     Thanks,
>     >>     Joseph
>     >>
>     >>     On 6/15/21 11:10 AM, William Gropp via mpiwg-rma wrote:
>     >>     > Hi everyone,
>     >>     >
>     >>     > It's been a long time since we’ve had an RMA call, and there
>     >>     are many
>     >>     > open topics that we need to discuss. Specifically, Min Si has
>     >>     raised
>     >>     > the issue of generalized RMA atomics, in this ticket and PR:
>     >>     >
>     >>     > Ticket:https://github.com/mpi-forum/mpi-issues/issues/114
>     <https://github.com/mpi-forum/mpi-issues/issues/114>
>     >>   
>      <https://urldefense.com/v3/__https://github.com/mpi-forum/mpi-issues/issues/114__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XUDVVgWNQ$
>     <https://urldefense.com/v3/__https:/github.com/mpi-forum/mpi-issues/issues/114__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XUDVVgWNQ$>>
>     >>     > <https://github.com/mpi-forum/mpi-issues/issues/114
>     <https://github.com/mpi-forum/mpi-issues/issues/114>
>     >>   
>      <https://urldefense.com/v3/__https://github.com/mpi-forum/mpi-issues/issues/114__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XUDVVgWNQ$
>     <https://urldefense.com/v3/__https:/github.com/mpi-forum/mpi-issues/issues/114__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XUDVVgWNQ$>>>
>     >>     > PR:https://github.com/mpi-forum/mpi-standard/pull/93
>     <https://github.com/mpi-forum/mpi-standard/pull/93>
>     >>   
>      <https://urldefense.com/v3/__https://github.com/mpi-forum/mpi-standard/pull/93__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XWx8VJHCw$
>     <https://urldefense.com/v3/__https:/github.com/mpi-forum/mpi-standard/pull/93__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XWx8VJHCw$>>
>     >>     > <https://github.com/mpi-forum/mpi-standard/pull/93
>     <https://github.com/mpi-forum/mpi-standard/pull/93>
>     >>   
>      <https://urldefense.com/v3/__https://github.com/mpi-forum/mpi-standard/pull/93__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XWx8VJHCw$
>     <https://urldefense.com/v3/__https:/github.com/mpi-forum/mpi-standard/pull/93__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XWx8VJHCw$>>>
>     >>     >
>     >>     > I’d like to schedule at least one RMA call, and allow for a
>     >>     regular set
>     >>     > of calls until we’ve handled the open RMA issues. So my first
>     >>     questions
>     >>     > are (a) are you interested in participating and if so (b)
>     would
>     >>     sometime
>     >>     > mid-morning US (9-11 CDT) work? If so, the next step will
>     be a
>     >>     doodle
>     >>     > poll to find a specific regular time. Please let my
>     assistant,
>     >>     Stacy
>     >>     > Walker cc’ed above, know if you want to participate.
>     >>     >
>     >>     > Bill
>     >>     >
>     >>     > William Gropp
>     >>     > Director, NCSA
>     >>     > Thomas M. Siebel Chair in Computer Science
>     >>     > University of Illinois Urbana-Champaign
>     >>     > IEEE-CS President-Elect
>     >>     >
>     >>     >
>     >>     >
>     >>     >
>     >>     >
>     >>     > _______________________________________________
>     >>     > mpiwg-rma mailing list
>     >>     >mpiwg-rma at lists.mpi-forum.org
>     <mailto:mpiwg-rma at lists.mpi-forum.org>
>     <mailto:mpiwg-rma at lists.mpi-forum.org
>     <mailto:mpiwg-rma at lists.mpi-forum.org>>
>     >>     >https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma
>     <https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma>
>     >>   
>      <https://urldefense.com/v3/__https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XVd-PD3Gw$
>     <https://urldefense.com/v3/__https:/lists.mpi-forum.org/mailman/listinfo/mpiwg-rma__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XVd-PD3Gw$>>
>     >>     >
>     >>  _______________________________________________
>     >>     mpiwg-rma mailing list
>     >> mpiwg-rma at lists.mpi-forum.org
>     <mailto:mpiwg-rma at lists.mpi-forum.org>
>     <mailto:mpiwg-rma at lists.mpi-forum.org
>     <mailto:mpiwg-rma at lists.mpi-forum.org>>
>     >> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma
>     <https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma>
>     >>   
>      <https://urldefense.com/v3/__https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XVd-PD3Gw$
>     <https://urldefense.com/v3/__https:/lists.mpi-forum.org/mailman/listinfo/mpiwg-rma__;!!DZ3fjg!pWTz8X2p0GgYcSiF5U5n-QNwN0udoi4fbnJdP6LdGxj_skJIY6kR46---XVd-PD3Gw$>>
>     >>
>     >
>
>     _______________________________________________
>     mpiwg-rma mailing list
>     mpiwg-rma at lists.mpi-forum.org <mailto:mpiwg-rma at lists.mpi-forum.org>
>     https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma
>     <https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma>
>
>
> _______________________________________________
> mpiwg-rma mailing list
> mpiwg-rma at lists.mpi-forum.org
> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-rma



More information about the mpiwg-rma mailing list