Just stumbled upon this report from the #reproducibility in #HPC workshop that took place before #SC25 ๐Ÿ‘‡
https://zenodo.org/records/15306610

It is disappointing in some ways, but itโ€™s great to see this topic being discussedโ€”putting โ€œreproducibilityโ€ and โ€œHPCโ€ together was unthinkable just a few years ago!

๐Ÿงต

Report on Challenges of Practical Reproducibility for Systems and HPC Computer Science

This report from the NSF-sponsored REPETO project synthesizes findings from the November 2024 Community Workshop on Practical Reproducibility in HPC, which convened researchers, artifact authors, reviewers, and chairs of reproducibility initiatives to address the critical challenge of making computational experiments reproducible in a cost-effective manner. The workshop deliberately focused on systems and HPC computer science research due to its unique requirements, including specialized hardware access and deep system reconfigurability. Through structured discussions, lightning talks, and panel sessions, participants identified key barriers to practical reproducibility and formulated actionable recommendations for the community. The report presents a dual framework of challenges and recommendations organized by target audience (authors, reviewers, organizations, and community). It characterizes technical obstacles in experiment packaging and review, including completeness of artifact descriptions, acquisition of specialized hardware, and establishing reproducibility conditions. The recommendations range from immediate practical tools (comprehensive checklists for artifact packaging) to ecosystem-level improvements (refining badge systems, creating artifact digital libraries, and developing AI-assisted environment creation). Rather than advocating for reproducibility regardless of cost, the report emphasizes striking an appropriate balance between reproducibility rigor and practical feasibility, positioning reproducibility as an integral component of scientific exploration rather than a burdensome afterthought. Appendices provide detailed, immediately actionable checklists for authors and reviewers to improve reproducibility practices across the HPC community. The workshop and report were supported by the NSF-sponsored REPETO project (award 2226406) and indirectly by the Chameleon project (NSF award 2027170). Citing this report: Keahey, K., Richardson, M., Tolosana Calasanz, R., Hunold, S., Lofstead, J., Malik, T., & Perez, C. (2025). Report on Challenges of Practical Reproducibility for Systems and HPC Computer Science. Community Workshop on Practical Reproducibility in HPC, Atlanta, Georgia. Zenodo. 10.5281/zenodo.15306610 PLEASE SEND YOUR COMMENTS ON THE REPORT TO MTRICHARDSON@UCHICAGO.EDU. TO DOWNLOAD OR CONTRIBUTE TO THE PACKAGING CHECKLISTS, PLEASE SEE OUR WORKSHOP WEBSITE.

Zenodo

How Missouriโ€™s Hellbender System Creates Community

"When the hellbender is thriving, it signals that the natural world around it is in harmony."

I am a big fan of this headline.

https://sc25.supercomputing.org/2025/08/hpc-ignites-collaboration-how-missouris-hellbender-system-creates-community/

#HPC #Missouri #SC25

๐ŸŒ๐ŸŒ ๐——๐—ฒ๐˜€๐˜๐—ถ๐—ป๐—ฎ๐˜๐—ถ๐—ผ๐—ป ๐—˜๐—ฎ๐—ฟ๐˜๐—ตโ€™๐˜€ ๐—–๐—น๐—ถ๐—บ๐—ฎ๐˜๐—ฒ ๐—–๐—ต๐—ฎ๐—ป๐—ด๐—ฒ ๐—”๐—ฑ๐—ฎ๐—ฝ๐˜๐—ฎ๐˜๐—ถ๐—ผ๐—ป ๐——๐—ถ๐—ด๐—ถ๐˜๐—ฎ๐—น ๐—ง๐˜„๐—ถ๐—ป ๐—ถ๐˜€ ๐—ป๐—ผ๐—บ๐—ถ๐—ป๐—ฎ๐˜๐—ฒ๐—ฑ ๐—ณ๐—ผ๐—ฟ ๐˜๐—ต๐—ฒ ๐—”๐—–๐—  ๐—š๐—ผ๐—ฟ๐—ฑ๐—ผ๐—ป ๐—•๐—ฒ๐—น๐—น ๐—ฃ๐—ฟ๐—ถ๐˜‡๐—ฒ ๐—ณ๐—ผ๐—ฟ ๐—–๐—น๐—ถ๐—บ๐—ฎ๐˜๐—ฒ ๐— ๐—ผ๐—ฑ๐—ฒ๐—น๐—น๐—ถ๐—ป๐—ด. ๐ŸŽ‰

https://destine.ecmwf.int/news/destines-climate-change-adaptation-digital-twin-shortlisted-for-the-acm-gordon-bell-prize-for-climate/

#HPC #GordonBell #SC #SC25 #ECMWF #DestinE #DestinationEarth

Procrastinating thought about #supercomputing โ€ฆ

When does the world of #HPC lose the most productivity temporarily - during November when everyone is focusing on #SC25 - or during July/August when large numbers of people are taking holidays?

Ok #hpc peeps! Seeing as the โ€˜sky doesnโ€™t have polls, and I know a load of yโ€™all are on here, can we try an informal pseudo poll? Who allโ€™s planning on being *physically* present at #sc25 in St. Louis this fall? Bash the โค๏ธ if you are, or drop a comment. Iโ€™ll report back! #supercomputing

Our #SC25 tutorial is up! ๐ŸŽ‰

https://sc25.conference-program.com/presentation/?id=tut158&sess=sess271

I'm already excited! We will be co-presenting with #AWS and teaching you how to run #HPC workloads using #Kubernetes with the Flux Operator. And a taste of MuMMI, a workload with AI/ML components. Hope to see you there! ๐Ÿฅณ

Weโ€™ve extended the deadline for HPCTESTS until 7 Aug! #SC25
How about writing up something cool about testing #HPC systems? Or some exciting accelerator analysis?
Weโ€™ve just extended the deadline for submission to the #WACCPD workshop at #SC25. And #HPCTESTS is also still open. Both close on Friday, EOD!
Links:
- WACCPD CfP: https://waccpd.org/call-for-papers/
- HPCTESTS CfP: https://olcf.github.io/hpc-system-test-wg/hpctests/hpctests2025.html
#GPU #Benchmarking
Call for Papers โ€“ WACCPD 2025

#SC25 registration asks "What are your ethnic origins or ancestry? Please select ALL geographic areas from which your family's ancestors first originated." and I don't see how anyone can't take "first" literally and answer Africa.
#Jupiter, Europeโ€™s most powerful #supercomputer, takes maiden flight - but misses exascale orbit
Full system expected to break the exaFLOP barrier - perhaps in time for #SC25 this fall?
In its first appearance on the biannual ranking, the Jรผlich Supercomputing Center's (JSC) flagship system managed 793 petaFLOPS of double precision (FP64) grunt in the time-honored High-Performance Linpack (#HPL) benchmark.
https://www.theregister.com/2025/06/10/jupiter_europes_top_super/
#Nvidia #Eviden #EuroHPC
Jupiter, Europeโ€™s most powerful super, takes maiden flight - but misses exascale orbit

ISC: Full system expected to break the exaFLOP barrier - perhaps in time for SC25 this fall?

The Register