Spack Working Group @ SDSC - Meeting - 2023/03/17

[mkandes]

Attendance

• Marty Kandes
• Mahidahr Tatineni
• Subhashini Sivagnanam
• Jerry Greenberg
• Nicole Wolter
• Yuwu Chen
• Trevor Cooper

Agenda

1. Regular meeting time

Weekly, Fridays @ 1PM PT until new production instances are deployed on Expanse and TSCC2. After deployment, we will revisit regular meeting time and move to either a biweekly and/or monthly meeting.

Note: Friday, March 31st is Cesar Chavez Day (Holiday)

2. Upcoming Planned Maintenance on Expanse

Expected date of maintenance: April 2023 - May 2023

Key changes expected to system software:

• Update operating system from Rocky 8.5 to Rocky 8.7
• Update Infiniband driver from Mellanox OFED 4.9-4.1.7 to Mellanox OFED 4.9-6.0.6 or Mellanox OFED 5.x
• Update Lustre client from lfs 2.12.8_6_g5457c37 to lfs 2.15.2
• Update NVIDIA GPU driver from NVIDIA 510.39.01 CUDA 11.6 to NVIDIA 515.65.01 CUDA 11.7

3. Update on pre-production testing of expanse/0.17.3/cpu/a and expanse/0.17.3/gpu/a

New applications deployed in expanse/0.17.3/cpu/a this past week:

• matlab/2022b/lefe4oq SDSC: PKG - expanse/0.17.3/cpu/b - Missing matlab (example application) #39
• orca/5.0.4/kunhxho; @nwolter - Do you plan to re-run with the orca testsuite? SDSC: PKG - expanse/0.17.3/cpu/a - Missing ORCA (example application) #40
• vasp6/6.2.1/3fjhwod SDSC: PKG - expanse/0.17.3/cpu/a - Missing VASP (example application) #45

Upcoming application deployments

• gaussian SDSC: PKG - expanse/0.17.3/cpu/b - Missing gaussian (example application) #37 - do we still need getcpusets with latest version of gaussian?
• gamess SDSC: PKG - expanse/0.17.3/cpu/b - Missing gamess (example application) #36
• wainner90 SDSC: PKG - expanse/0.17.3/cpu/b - Missing Wannier90 (example application) #46

Other issues

• trinity container testing SDSC: PKG - expanse/0.17.3/cpu/a - Missing Trinity (example application) #44

4. Planning and Preparation for Deployment of Spack on TSCC2

Expected date of deployment: April 2023
Expected operating system at deployment: Rocky 9.x; base gcc moves to 11.2.x

Check on Jerry's GitHub user account issues; which username will be used as part of SDSC's GitHub organization moving forward?

Manual integration of tscc2/cpu and tscc2/gpu instance specs and yamls configs into official sdsc/spack repo

• https://github.com/jerrygreenberg2/sdsc

5. Other things to do

• Investigate creating a build cache on Jetstream2; may allow us to deploy more quickly during system maintenance
• Complete initial draft of DEPLOYMENT.md, which will serve as general deployment documentation
• Complete initial draft of CONTRIBUTING.md, which will serve as documentation on how to contribute work to this repo
• Create a dev & test spack instance(s) based on a subset of the the expanse/0.17.3/cpu and expanse/0.17.3/gpu instances

References:

• https://forge.sdsc.edu/confluence/display/HO/Expanse+Acceptance+Testing
• https://forge.sdsc.edu/confluence/display/HO/Expanse+Spack+Application+Deployment