Sync meeting 2024 06 11 - multixscale/meetings GitHub Wiki

MultiXscale WP1+WP5 sync meetings

Monthly, every 2nd Tuesday of the month at 10:00 CE(S)T
Notes of previous meetings at https://github.com/multixscale/meetings/wiki

Next meetings

Tue 11 June 2024 10:00 CEST
Tue 9 July 2024 10:00 CEST
- planning to attend: Caspar, Bob
- on summer break: Kenneth, Lara, Thomas
Tue 13 Aug 2024 10:00 CEST
- planning to attend: Kenneth, Lara, Caspar, Thomas
- on summer break: Bob

Agenda/notes 2024-06-11

attending:

Neja (NIC)
Alan (UB)
Kenneth, Lara (UGent)
Caspar, Casper, Maxim (SURF)
Thomas & Richard (UiB)
Bob, Pedro (RUG)
Jean-Noël (UStutt)
Julián (BSC)
Eli, Susana, Nadia (HPCNow!)

problems with shared drive
- cfr. incomplete progress reports 2024Q1 for WP1 (see drafts in drive upload by Satish) + WP5 (see Lara's email 6 May)
- works for Alan when logging in through incognito browser + logging in with personal Microsoft account
  - who else has this problem?
    - Kenneth, Susana, Jean-Noël, Rudolph, Pedro
- we can try to take a copy and create a new OneDrive
2024Q2 quarterly report
- try to get info in place end of June/early July
- Lara & Caspar will be mostly available in July
- if problems with OneDrive persist, send PMs info + bullet points with tasks to Caspar/Lara via email/Slack/HackMD
Milestone 3 (M18 - June 2024, lead: UStuttgart)
- Milestone name: "First portable test run on two systems with different architectures (e.g. with and without accelerators)"
- Means of validation: "Performance and scalability plots available for the application on the two architectures"
- working on this using ESPResSo, as extra test in EESSI test suite
  - see https://github.com/EESSI/test-suite/pull/144, using FFT test case
    - working with JSC to make FFT communication 8-16x faster
  - scalability for LJ test case should improve this year
    - should also be added to ESPResSo test
WP status updates
- [SURF] WP1 Developing a Central Platform for Scientific Software on Emerging Exascale Technologies
  - [UGent] T1.1 Stable (EESSI) - D1.3 due M24 (Dec'24)
    - more software, incl. Espresso 4.2.2
    - dev.eessi.io => see notes + support issue #61
      - would be very interesting service for developers in scientific WPs => cross-cutting across technical & scientific PRs
      - "looser" policy compared to software.eessi.io production repo
      - Devs can trigger their own builds
      - pre-release builds accepted (specific commits)
      - intially focused on Espresso & co
      - could also be used as "dev" environment for software.eessi.io features (e.g. GPU support)
      - if we're doing this on Azure, we should do it in a new subscription
        
        needs to be created by Martin @ SURF
        
        if done in AWS, Alan can do it
    - GPU software => see notes + support issue #59
      - Update bot to have GPU support [Thomas]
      - Update archdetect to support CUDA compute capability [???]
      - directory structure in software.eessi.io, for example software/x86_64/amd/zen2/accel/nvidia/cc80 [???]
      - blocked by dev.eessi.io?
        
        we want to use this as a playground for GPU builds
        
        => can look into this during hackathon on Tue 18 June
      - needs to be planned
    - need to review description of Task 1.1, make sure all subtasks are covered
      - => need to update project planning (Caspar, Kenneth)
    - "we will benchmark software from the shared software stack and compare the performance against on-premise software stacks to identify potential performance limitations, ..."
      - Espresso + LAMMPS + OpenFOAM + ALL(?) (MultiXscale), GROMACS (BioExcel)
    - "increase stability of the shared software stack ... pro-actively by developing monitoring tools"
      - proper monitoring for CVMFS network (S0 + S1s)
      - for RUG?
  - [RUG] T1.2 Extending support - D1.4 due M30 (June'25)
    - Arm support fits here
    - zen4 + sapphirerapids
    - AMD ROCm
      - lower impact, should we should limit our efforts here?
      - select apps, like PyTorch/TensorFlow
    - should also look into Grace Hopper (JUPITER)
  - [SURF] T1.3 Test suite - D1.5 due M30 (June'25)
    - Milestone 3 for Espresso test
  - [BSC] T1.4 RISC-V (starts M13)
    - cfr. efforts by Bob & Julian, incl. riscv.eessi.io
    - actively looking into adding more software, incl. Extrae
    - lot of interest from EUPILOT project @ BSC
  - [SURF] T1.5 Consolidation (starts M25 - Jan'25)
    - (not started yet)
- [UGent] WP5 Building, Supporting and Maintaining a Central Shared Stack of Optimized Scientific Software Installations
  - (FINISHED M12 [UGent] T5.1 Support portal)
  - [SURF] T5.2 Monitoring/testing, D5.3 due M30 (June'25)
    - discussions with SURF + initial work done on dashboard
    - working on two dashboards: one detailed, one with overview
  - (FINISHED M12 [UiB] T5.3 community contributions (bot))
  - [UGent] T5.4 support/maintenance - D5.4 due M48 (Dec'26)
    - support portal + rotation working well
    - support issues in April+May
      - Opened: 12 issues
      - Closed: 10 issues
      - total: 69 issues (26 open, 43 closed)
    - bot release
- [UB] WP6 Community outreach, education, and training
  - [Kenneth, Lara, Pedro] EasyBuild User Meeting (EUM'24), 23-25 April 2024 @ Umeå, Sweden
  - [Kenneth, Lara, Eli] activity at ISC'24, see https://eessi.io/docs/blog/2024/05/17/isc24
  - [Eli] Teratec (29-30 May'24)
    - poster
    - demo for Sanofi, were quite interested
  - [Thomas] presentation @ Norwegian Bioinformatic Days on making bionformatics workflows easy (using Nextflow)
    - they use a lot of containers, but can also use different backends
      - backend for EESSI could be interesting
    - similar work was done in BioHackaton Europe (https://biohackathon-europe.org)
  - [Lara] EESSI promotion @ DH Benelux in Leuven (Belgium), 4-7 June'24
    - some people were interested, like getting students easy access to software installations
  - [Matej] presenting poster at ASHPC this week
  - [Alan] invited speaker for Nordic Industry Days (early Sept'24)
  - submit BoF proposal on EESSI for SC24 (Atlanta, US)
    - HPCNow! will be attending
    - tutorial submission done
  - CernVM-FS workshop (Sept'24, Geneva)
    - submission due this month
    - EESSI is in default CernVM-FS configuration
    - could cover work on dev.eessi.io
  - deliverable due: D6.2 (M24 - Dec'24), D6.3 (M30 - June'25)
- [HPCNow] WP7 Dissemination, Exploitation & Communication
  - T7.1 Scientific applications provisioned on demand (lead: HPCNow)
    - ...
  - Task 7.2 - Dissemination and communication activities (lead: NIC)
    - more EESSI stickers
      - via HPCNow?
      - Neja will ask at NIC
    - new section in MultiXscale website: https://www.multixscale.eu/dissemination
      - interview with Matej being worked on by Susana
      - will try to include it in newsletter of July
  - Task 7.3 - Sustainability (lead: NIC, started M18)
    - Legal entity for EESSI needs to be looked into?
    - subcontracting money available for this
    - we should explore options ourselves a bit first
  - Task 7.4 - Industry-oriented training activities (lead: HPCNow)
    - ...
- [NIC] WP8 (Management and Coordination)
  - reply to review report (see Word doc in shared drive, 1st periodic report | Results of the Review)
  - amendment in the works?
    - Neja will start looking into that after holiday in July
  - next General Assembly meeting
    - 23-24 Jan'25 in Barcelona/Sitges
      - coupled to HiPEAC'25 (20-22 Jan 2025)
      - https://www.hipeac.net/2025/barcelona
    - call for workshops/tutorials at HiPEAC'25
      - https://www.hipeac.net/2025/barcelona/#/call/
      - deadline: 1 July
      - Eli working on workshop submission for Women in HPC/CoE's
  - two deliverables due 5th of July (in response to project review)
    - one on co-design (by Alan)
      - focus on collaborating with projects like EUPILOT, EPI, EUPEX (rather than contacting vendors directly)
    - one for scientific WPs

Notes

CI/CD call for EuroHPC
- is 100% funded (not 50/50 EU/countries)
- not published yet
request for success story by CASTIEL2
- ideally end of June, by latest at end of August
- involvement of SKA in EESSI
  - Neja is talking to Caspar on this
- deployment of EESSI on Vega/Karolina
- maybe something on Deucalion
  - at best by mid Aug'24
- collaboration with AWS/Azure
  - getting EESSI in AWS ParallelCluster
next general MultiXscale meeting
- Tue 25 June 2024, 10:00-11:00 CEST
- hosted by Alan
- agenda point: update on pairing of technical + scientific WPs
(Susana) suggestions for blog are welcome
- something on leveraging EESSI on GitHub Actions to run CI
  - using GROMACS?
  - we should also have something on CD aspect
  - Alan has something that may be useful
- something on progress in RISC-V

Notes of previous meetings

Template for sync meeting notes

TO COPY-PASTE

overview of MultiXscale planning
- https://github.com/orgs/multixscale/projects/1/views/1
WP status updates
- [SURF] WP1 Developing a Central Platform for Scientific Software on Emerging Exascale Technologies
  - [UGent] T1.1 Stable (EESSI) - due M12+M24
    - ...
  - [RUG] T1.2 Extending support (starts M9, due M30)
  - [SURF] T1.3 Test suite - due M12+M24
    - ...
  - [BSC] T1.4 RISC-V (starts M13)
  - [SURF] T1.5 Consolidation (starts M25)
- [UGent] WP5 Building, Supporting and Maintaining a Central Shared Stack of Optimized Scientific Software Installations
  - [UGent] T5.1 Support portal - due M12
    - ...
  - [SURF] T5.2 Monitoring/testing (starts M9)
  - [UiB] T5.3 community contributions (bot) - due M12
    - ...
  - [UGent] T5.4 support/maintenance (starts M13)
- [UB] WP6 Community outreach, education, and training
  - ...
- [HPCNow] WP7 Dissemination, Exploitation & Communication
  - ...