vsoch commented on issue hpc-maths/samurai#322.
Thank you! I should be able to test again this week! I’m epically flailing with ebpf in containers at the moment.
vsoch opened a pull request to converged-computing/flux-apps-helm
vsoch pushed to compspec/compat-lib
do not require provided mount path
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch commented on issue DLR-AMR/t8code#1615.
Thanks @Davknapp ! I can definitely try again, although I don’t have many ideas, at least at the moment. We run these with the flux operator, which is deploying flux framework (an HPC workload manager and scheduler) within a closed space of pods in a Kubernetes cluster, so that means (depending on the cloud) we can use networks like Infiniband (Azure) and EFA (AWS), and the performance isn’t bad. For this set of tests we are in Google Cloud, which unfortunately is just optimized ethernet (they call it “Titanium” and the details aren’t revealed), but I’ve run over 25 applications and (at least for small sizes) they scale generally OK up until about 64 nodes. …
vsoch pushed to rseng/software
Merge pull request #422 from rseng/update/software-2025-05-11
Update from update/software-2025-05-11</small>
vsoch pushed to flux-framework/spack
Automated deployment to update flux-sched versions 2025-05-11 (#335)
Signed-off-by: github-actions github-actions@users.noreply.github.com Co-authored-by: github-actions github-actions@users.noreply.github.com</small>
vsoch pushed to converged-computing/google-performance-study
update lammps plots
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to sciworks/spack-updater
Package underscore (#50)
- ensure we install with an underscore
- do not use zlib
- remove openslide, takes too long
- use package name to install
Signed-off-by: vsoch vsoch@users.noreply.github.com Co-authored-by: vsoch vsoch@users.noreply.github.com</small>
vsoch commented on issue mpi4jax/mpi4jax#280.
Will be testing on multiple nodes later today - in the meantime I built the container and made the animation, it’s gorgeous!
vsoch pushed to flux-framework/spack
test branch that renames with underscore (#334)
- test branch that renames with underscore
- restore to main
- quick test
Signed-off-by: vsoch vsoch@users.noreply.github.com
Signed-off-by: vsoch vsoch@users.noreply.github.com Co-authored-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to converged-computing/google-performance-study
analysis: update lammps result analysis
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch opened a pull request to converged-computing/flux-apps-helm
vsoch commented on issue DLR-AMR/t8code#1615.
Hi @Davknapp ! I had a go at testing this today - first on a small, single container (it seemed to work OK there) but then when I moved to 4 nodes in Kubernetes, it hung here for 8 minutes:…
vsoch pushed to sciworks/spack-updater
Update spack package path
New path is: var/spack/repos/spack_repo/builtin/packages</small>
vsoch commented on issue mfem/mfem#4848.
Is there any reason the benchmark (Google Benchmark) isn’t exposed with spack?. I can try to derive a cmake command on my own, but there are so many options, I am almost guaranteed to get something wrong….
vsoch commented on issue hpc-maths/samurai#322.
I’m having a hard time building. I first tried installing dependencies directly with the system package manager, but hit that my gcc didn’t support c++17. The conan install didn’t work. So I tried setting up the development environment with mamba (and got farther there):…
vsoch pushed to flux-framework/flux-framework.github.io
Merge pull request #151 from flux-framework/release-docs-2025-05-09
Update from release-docs-2025-05-09</small>
vsoch commented on issue CEED/Remhos#52.
OK, working again with version updates! Sorry for the noise. Will again test soon….
vsoch pushed to singularityhub/shpc-registry
Merge pull request #322 from singularityhub/update/containers-2025-05-08
[bot] update/containers-2025-05-08</small>
vsoch pushed to sciworks/spack-updater
Update action.yaml
## What’s Changed
- metadata improvemens by @fmigneault in https://github.com/rseng/zenodo-release/pull/16
- Fix missing command arguments by @fmigneault in https://github.com/rseng/zenodo-release/pull/17
New Contributors
- @fmigneault made their first contribution in https://github.com/rseng/zenodo-release/pull/16
Full Changelog: https://github.com/rseng/zenodo-release/compare/0.0.20…0.0.21</small>View Comment
vsoch commented on issue pydicom/deid#278.
That’s generally how an or works, e.g. in Linux:…
vsoch commented on issue mpi4jax/mpi4jax#280.
OK! I will test it out. To set your expectation, I’m on travel and will be able to resume work this weekend (and report back)….
vsoch commented on issue hpc-maths/samurai#322.
> I’ve seen that other projects have been contacted. Could you tell us a little more about the purpose of this study?…
vsoch pushed to flux-framework/spack
binary_distribution: content addressable tarballs (#48713)
binary_distribution: content addressable url buildcache
Change how binary mirrors are laid out, adopting content addressing for every piece of data spack stores in a binary mirror. Items (e.g. tarballs, specfiles, public keys, indices, etc) are now discoverable via manifest files which give the size, checksum, compression type, etc of the the stored item. The information in the manifest, in turn, is used to find the actual data, which is stored by its content address in the blobs directory. Additionally, signing is now applied to the manifest files, rather than to the spec files themselves.</small>
vsoch pushed to flux-framework/flux-framework.github.io
Merge pull request #150 from flux-framework/release-docs-2025-05-07
Update from release-docs-2025-05-07</small>
vsoch commented on issue DLR-AMR/t8code#1615.
Sounds good! I will do some tests and report back. To set your expectation, I’m on travel and will be able to pick up work this weekend….
vsoch commented on issue CEED/Remhos#52.
@vladotomov it looks like there isn’t a spack variant for GPU:…
vsoch commented on issue CEED/Remhos#52.
This is great! We definitely need more GPU benchmarks. I’ll add this one to my list, and if you want to keep the issue open, am happy to report back here (likely close to the weekend, I’m currently on travel)….
vsoch pushed to flux-framework/spack
[skip-verify-checkums] (#50299)
vsoch pushed to converged-computing/google-performance-study
add new apps up to size 64
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to converged-computing/flux-apps-helm
Merge pull request #23 from converged-computing/add-docker-images
Add docker images</small>
vsoch merged a pull request to rse-ops/flux-hpc
vsoch open issue mpi4jax/mpi4jax#280.
Examples for multi-node scaling study?
Hi! Would your water example be suitable (or others you have) for a strong or weak scaling study? We are doing a study on 4 to 64 nodes and looking for apps / proxy apps / benchmarks / synthetic benchmarks that could be candidates. The only requirement is that I can build it into a container and run it across nodes, and there is some kind of figure of merit (FOM) at least running time. Thanks!…View Comment
vsoch commented on issue mfem/mfem#4848.
We definitely have laghos, and now that I think of it, there might be a few others with mfem:…
vsoch commented on issue hpc4cmb/toast#822.
Writing a result file at the end is OK! Many apps do that, and either I copy the file locally or cat to the terminal (so it appears in the log). The issue would be nodes (pods) requiring access to the same file. It sounds like that might be possible from your description?…
vsoch open issue hpc-maths/samurai#322.
[Question]: Examples with FOM or similar?
### What do you want?…View Comment
vsoch pushed to converged-computing/google-performance-study
likwid results and a few more analysis scripts
But I am tired, going to sleep
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to converged-computing/google-performance-study
gke cpu size 32 apps batch 2
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to converged-computing/flux-apps-helm
add lammps build
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch open issue LLNL/phloem#3.
crunch_mpigraph Hostlist module?
Hi! I’m trying to generate the html report for my mpiGraph result, but having trouble finding the Hostlist module….View Comment
vsoch commented on issue LLNL/RAJAPerf#511.
It’s in a larger set of helm apps (Kubernetes) that are mostly exemplifying the idea, so I’m relatively indifferent. I think the three that I chose should suffice - I appreciate your help, and am good to close the issue!…
vsoch commented on issue DLR-AMR/t8code#1615.
Okay figured out how to build occ, including what I already had in my container:…
vsoch open issue CEED/Remhos#52.
Figure of Merit?
Hi! I saw that your README says “Coming soon” for the FOM. Is there something to calculate or derive from the output? Thanks!…View Comment
vsoch commented on issue tudasc/cfdSCOPE#1.
I would built it into a container for our helm apps, and the container would need to be public. If you like I can do the build and remove the source code. Would either of those work?…
vsoch pushed to rseng/software
Merge pull request #421 from rseng/update/software-2025-05-04
Update from update/software-2025-05-04</small>
vsoch pushed to rse-ops/flux-hpc
new set of apps
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to converged-computing/flux-apps-helm
tweaks for size 4 run of gke cpu
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch commented on issue LLNL/benchpark#749.
Might be some good things here: https://github.com/genesis-release-r-ccs/genesis-nonbonded-kernels (and in that org)….
vsoch commented on issue LLNL/benchpark#748.
How can we use something from a private repository?…
vsoch open issue DLR-AMR/t8code#1615.
OCC Not Linked
# Bug report…View Comment
vsoch commented on issue tudasc/cfdSCOPE#1.
Will do! I ran a study this morning - I am using a helm chart that will install and run on on one node (Kubernetes), and then I “scale” via the OMP_NUM_THREADS
. I’m not sure more threads made it faster - I’ll share with you the plots when I make them (I have still about 20 other apps to test)!…
vsoch pushed to rseng/zenodo-release
Fix missing command arguments (#17)
- add title and description support + do not override related_identifiers if some exists
- fix invalid format args
- pass down title/description to command
- add quotes around action parameters
- undo quotes for zenodo json param
- undo quotes for doi param
- provide ‘–description-file’ alternative parameter for zenodo record description
- add missing ‘description_file’ forwarding
-
replace single quotes by escaped double quotes to avoid unresolved file path with literal quote in string parameter + use argparse.FileType to raise unresolved file immediately
- adjust commands to avoid weird literal single/double quotes parsing</small>
vsoch pushed to converged-computing/google-performance-study
results: fio, pytorch mnist, and multi gpu models
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to converged-computing/google-performance-study
gke gpu experiments sizes 4 and 8
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch commented on issue tudasc/cfdSCOPE#1.
Gotcha - I will do this as a single node run, and I agree multi-nodes would be a great feature to add. I’ll update the title of the issue to reflect that (and others can follow too). Thank you for the link to the paper!…
vsoch pushed to rse-ops/flux-hpc
aff more working builds
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch open issue pytorch/benchmark#2613.
Support for multiple nodes?
Hi! I know that torchrun can handle running across nodes - do you have an example for how to do that here? Thank you!…View Comment
vsoch commented on issue oras-project/oras-py#197.
@Sojamann it’s a developer library by default - I would argue that your use case is niche and should not refactor the entire structure of the library to support when it’s as easy as tweaking the session on the class….
vsoch pushed to converged-computing/flux-apps-helm
prototyping more apps (and gpu apps start)
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to conda-forge/oras-py-feedstock
updated v0.2.31 (#36)
vsoch open issue EnzymeAD/Enzyme#2298.
Examples, tests, or FOM?
Hi! I build enzyme with spack, and I’m looking for an example or test that we can run on multiple nodes at increasing sizes to assess performance or benchmark, ideally with time to completion or some other FOM. Can you make a suggestion? Thanks!…View Comment
vsoch pushed to rse-ops/flux-hpc
add havoqgt, smilei, e3sm-kernels, lulesh
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to researchapps/usernetes
flannel: add ethtool action to offload eth0
turn checksum off
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch created a new branch, update-imports at researchapps/havoqgt
vsoch commented on issue oras-project/oras-py#192.
Hi @Sojamann ! If you could please rebase, and then bump this to 0.2.31, we can run tests again and finish up the PR. Thank you!…
vsoch open issue converged-computing/aws-performance-study#4.
Add pytorch benchmarks
See https://github.com/pytorch/benchmark…View Comment
vsoch pushed to conda-forge/oras-py-feedstock
updated v0.2.30 (#35)
vsoch opened a pull request to LLNL/havoqgt
vsoch open issue ArjenTamerus/DFToy#10.
Reproducible build?
Hi! Do you have a container (or otherwise reproducible) build of this? I’ve been trying to tweak it for a more general environment (not with intel MPI) and I am epically failing. Thanks!…View Comment
vsoch pushed to flux-framework/spack
Automated deployment to update package flux-core 2025-04-30 (#330)
Co-authored-by: github-actions github-actions@users.noreply.github.com</small>
vsoch commented on issue rusq/slackdump#514.
Thanks - worked perfectly! I must have fat fingered it the first time - sorry for the noise….
vsoch opened a pull request to rse-ops/flux-hpc
vsoch commented on issue oras-project/oras-py#194.
We would definitely want to mirror what the Go oras client does. If you’d like to open a PR to work on the issue I’d be happy to review it….
vsoch pushed to singularityhub/shpc-registry
Merge pull request #320 from singularityhub/update/containers-2025-04-28
[bot] update/containers-2025-04-28</small>
vsoch open issue rusq/slackdump#514.
Export specific channel
Is your feature request related to a problem? Please describe.…View Comment
vsoch created a new branch, prototype-new-apps at converged-computing/google-performance-study
vsoch open issue ECP-copa/ExaMiniMD#40.
cmake instructions?
Hi! I’m following instructions in the README, and first it’s telling me that I need to add a flag to use deprecated Makefile to do the build in the README:…View Comment
vsoch pushed to rseng/software
Merge pull request #420 from rseng/update/software-2025-04-27
Update from update/software-2025-04-27</small>
vsoch commented on issue flux-framework/flux-core#6541.
I missed this (I’m reading features from the releases now)! Is this something that could be used to dynamically generate resources for a broker / worker set?…
vsoch pushed to converged-computing/flux-apps-helm
add multi gpu models / support for addcaps
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch pushed to oras-project/oras-py
Merge pull request #193 from oras-project/ensure-headers-defined
token.py ensure headers is defined</small>
vsoch pushed to conda-forge/oras-py-feedstock
oras-py v0.2.29 (#34)
-
updated v0.2.29
-
MNT: Re-rendered with conda-build 25.4.2, conda-smithy 3.47.2, and conda-forge-pinning 2025.04.23.13.34.55</small>
vsoch commented on issue bentoml/BentoML#3836.
What exactly about this issue is “not planned” - a person actually responding to me? In a timeframe of years later?
vsoch pushed to singularityhub/shpc-registry
Merge pull request #319 from singularityhub/update/containers-2025-04-24
[bot] update/containers-2025-04-24</small>
vsoch pushed to oras-project/oras-py
Update release.yaml
Signed-off-by: Vanessasaurus <814322+vsoch@users.noreply.github.com></small>
vsoch closed issue flux-framework/flux-core#6713.
flux job updated duration is not honored
I have a createsims job that I was testing the flux update duration
on, and it successfully changed the jobspec, but the job has happily continued running after 25 minutes (1500 seconds). I set it around 16 minutes so I don’t think it’s any kind of race condition. The job started with the default (0). Did I do something wrong?…View Comment
vsoch open issue abinit/abinit#86.
Undefined reference to dgemm
Hiya! I’m trying to build this, and using most dependencies from spack, and I hit this error with make -j 4
…View Comment
vsoch commented on issue spack/spack#50075.
Does anyone know why I keep getting notified for this issue? I’m going to try to comment so I can subscribe and unsubscribe (because I don’t see the option now)….
vsoch pushed to converged-computing/flux-apps-helm
app: multi-gpu-models
Signed-off-by: vsoch vsoch@users.noreply.github.com</small>
vsoch open issue charmplusplus/charm#3888.
Running with Flux Framework
Hi!
vsoch open issue ECP-copa/CabanaPIC#52.
Single-node or multi-node run examples
Hi! From what I can tell in the README, I need to compile a custom “deck” and then run the executable. Is that correct? Given that context, would this work just on a single node, or does it work with multiple nodes?…View Comment
vsoch pushed to vsoch/vsoch.github.io
All link to updated software
vsoch commented on issue vsoch/pull-request-action#106.
ok, no worries then - thanks!…
vsoch commented on issue oras-project/oras-py#188.
It says to use basic with a username and password. Did you export those both to the environment?…
vsoch commented on issue flux-framework/spack#329.
This looks to be typing changes we need to get from upstream (not the other way around)…..
vsoch pushed to converged-computing/google-performance-study
Merge pull request #3 from converged-computing/test-quicksilver
Quicksilver results</small>
vsoch pushed to flux-framework/spack
aocc: add missing attributes (#50082)
Co-authored-by: viveshar vivek.sharma2@amd.com</small>
vsoch commented on issue containers/containerimage-py#12.
It’s up to you! It never hurts to start a discussion….