nlslatt
commented
3 years ago | Descriptor | Information |
|---|---|
| Date | [07/13/2021] |
| Attendees | @PhilMiller @JacobDomagala @nmm0 @cz4rs @jstrzebonski @fnrizzi @ppebay @nlslatt |
| Description | Weekly Meeting |
Agenda:
@nlslatt:
- @lifflander is out on vacation today
- Mostly focused on Gemma and EMPIRE
- I’ve been referred from person to person at Sandia about getting Intel 18/19 licenses to use on Azure. Someone is now actively looking into it but I have no idea how long it make take to resolve this.
@jstrzebonski:
- DARMA-tasking/checkpoint#125 – it's done, and PR is waiting for a review (since reviewed and merged).
- DARMA-tasking/checkpoint#161 – I improved vector serializer's code a little bit, and also tweaked list and map serializer, but it's not finished yet.
- DARMA-tasking/checkpoint#218 – LSAN found a bug in serialization's error checking - memory is leaking when it throws. It's fixed already, PR is waiting for a review.
- Discovered post-meeting that none of checkpoint’s complication pipelines are required; doesn’t seem to be a way to make them required (see #vt discussion)
@cz4rs:
- vt #1202 - Intel 21 pipeline - work in progress
- Further restrictions in hours for DARMA, I will be focusing solely on Kokkos until September.
- Posted screenshot of Intel’s planned compiler support to #vt on slack
@nmm0:
- More debugging. We figured out a temporary solution to one problem but there are more issues with the reduce when LB is active. I'll discuss more at the meeting (at larger scale, reduction completes on first phase but not on other phases; this doesn’t show up in @jliffla’s reproducer)
- I will be on vacation starting this evening and will be back on the 28th
- Discussed that we should probably have a set of larger-scale tests that run weekly on Sandia machines so we know if problems are introduced that only manifest at larger scales than our CI testing.
@JacobDomagala:
- No vt related work last week. I'm mostly focused on Trilinos right now
@PhilMiller:
- I’m back online
@ppebay:
- Finished reading through all LB paper reviews
- Seems like @lifflander hasn’t assigned issues for addressing reviewer comments
- @ppebay will work on theoretical part; @nlslatt will send him latex source
lifflander
nmm0
This issue shall be used to log (weekly) meeting agendas and the corresponding resolution of the topics addressed (minutes). This will help us maintain a record of topics discussed and the resolution of these issues. Each comment shall contain a meeting agenda for a given week, edited later with the resolution for each point of order.
Other impromptu meetings that are relevant to the whole group can also be logged here for posterity and members of the team (or people following the project) who couldn't join.
Rendered template for each meeting:
Agenda:
Template: