Computer room walking tour, 1992
Recent searches
Search options
#hpc
8 posts7 participants0 posts today
#IBMPower systems support a number of different #Linux distributions including #RHEL, #SUSE, #Ubuntu, #AlmaLinux and #RockyLinux. This blog titled "Rocky Linux on IBM Power Really Rocks" from the team at #TachosHPC discusses their experience with #RockyLinux on #IBM #POWER10 from the #HPC context. https://tachoshpc.com/rocky-linux-on-ibm-power-really-rocks/
tachoshpc.comRocky Linux On IBM Power Really Rocks – TACHOS HPC
I run happen to run @AlmaLinux on my dual socket #POWER9 server at home. This blog by the folks at #TachosHPC discusses #RockyLinux on #IBMPower systems in the context of #HPC https://tachoshpc.com/rocky-linux-on-ibm-power-really-rocks/ #POWER10
tachoshpc.comRocky Linux On IBM Power Really Rocks – TACHOS HPC
I'm an HPC user of CPU Fortran compilers, and my primary/preferred compiler is__________"
Continued thread
#FireFlyer #AI #HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning https://arxiv.org/abs/2408.14158
arXiv.orgFire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep LearningThe rapid progress in Deep Learning (DL) and Large Language Models (LLMs) has exponentially increased demands of computational power and bandwidth. This, combined with the high costs of faster computing chips and interconnects, has significantly inflated High Performance Computing (HPC) construction costs. To address these challenges, we introduce the Fire-Flyer AI-HPC architecture, a synergistic hardware-software co-design framework and its best practices. For DL training, we deployed the Fire-Flyer 2 with 10,000 PCIe A100 GPUs, achieved performance approximating the DGX-A100 while reducing costs by half and energy consumption by 40%. We specifically engineered HFReduce to accelerate allreduce communication and implemented numerous measures to keep our Computation-Storage Integrated Network congestion-free. Through our software stack, including HaiScale, 3FS, and HAI-Platform, we achieved substantial scalability by overlapping computation and communication. Our system-oriented experience from DL training provides valuable insights to drive future advancements in AI-HPC.
#Europe Takes Another Whack At Homegrown Compute Engines
Digital Autonomy with #RISCV in Europe, Project "#DARE" is very much focused on #HPC even if it does have potential #AI use cases. Funded by #EuroHPC Joint Undertaking, the same pan-European organization that has funded pre-exascale and #exascale systems. A total of 38 different organizations, have joined up to work collaboratively on three different RISC-V compute engines.
https://www.nextplatform.com/2025/03/10/europe-takes-another-whack-at-homegrown-compute-engines/
The Next Platform · Europe Takes Another Whack At Homegrown Compute EnginesWith RISC-V International, the body controlling the RISC-V instruction set, located in Switzerland for the past five years, RISC-V now has just as much
DOE INCITE Program Seeks 2026 Proposals for Computing Innovation
The Innovative and Novel Computational Impact on Theory and Experiment, or INCITE, program has announced the 2026 Call for Proposals, inviting researchers to apply for access to some of the world’s most powerful high-performance computing systems.
The program allocates node-hours on Frontier at ORNL and Polaris and Aurora at ANL. Awards typically range from 250,000 to 1,000,000 node-hours.
TACC's upcoming leadership supercomputer, Horizon, is at risk due to steep cuts to NSF. Sounds like its fate is locked up in argument between Congress and the White House.
https://www.science.org/content/article/trump-throws-wrench-nsf-s-support-new-texas-supercomputer
I have a small set of linux machines (~5) that are mostly sitting idle. How can I turn it into a modest #CoW (cluster of workstations) so that people can easily submit long-running jobs to it?
Jobs will be mostly written in #rstats and #python .
What's a good entry-level setup for this? Easy to maintain, easy to use, nothing fancy.
I haven't done anything like that for at least 10 years, I'm sure things have moved on since then.
Thanks!
HPC woes:
5 * MONs with 2 * 100 Gb/s links each
16 OSDs with 2 * 100 Gb/s links each and 1 * 15 TB NVMe each rated at 5,5 GiB/s at 128 KiB IO write
fio says 
iperf3 says
Ceph:
Nouveau sponsor : Altair !
Altair est un leader mondial de l’intelligence numérique. Leur mission ? Aider les organisations à innover plus vite, décider plus intelligemment et agir plus durablement.
Leur expertise couvre la simulation, le calcul haute performance (HPC), la data science et l’intelligence artificielle.
Le tout, avec une vision claire : construire un futur plus efficace, plus intelligent et plus respectueux de l’environnement 
Merci à Altair de soutenir MiXiT 2025 !
Découvrez notre plaquette sponsoring : https://mixitconf.org/sponsors
hgpu.org · Scalability Evaluation of HPC Multi-GPU Training for ECG-based LLMsTraining large language models requires extensive processing, made possible by many high-performance computing resources. This study compares multi-node and multi-GPU environments for training larg…
Magnetic field of a cow.
(Simulated magnetic field of a kitchen magnet sized and magnetized cow model)
Available now in Ionsolver: https://github.com/VioletSpace/IonSolver
#physics #gpu #hpc
Last year at the Open Science Retreat (#OSR24NL) I have been introduced to nanopubs by @egonw and created my first nanopub declaring citations for a paper using CiTOs (citation ontologies).
Now, travelling to #OSR25CH, due to issues with the train network foreseen with plenty of time, I used the opportunity and created a new one ( https://w3id.org/np/RAicq7k9QHX8EG8ho7Baib9GxHsU18O0tyFCZ4tbbGGPA ) for my latest publication on teaching #Snakemake on #HPC systems.
The teaching material is — again — in desperate need of additions and overhaul, but that is for another day.
w3id.orgRAicq7k9QH (explore) | nanodash
@AMD Releases #ROCm 6.4: More Powerful, More Modular, but Still No RDNA4 Support https://medium.com/p/amd-releases-rocm-6-4-more-powerful-more-modular-but-still-no-rdna4-support-ff3030d3da3a?source=social.tw #opensource #llm #ai #hpc
Medium · AMD Releases ROCm 6.4: More Powerful, More Modular, but Still No RDNA4 Support
Explore the latest OpenMP 6.0 webinar by POP!
Learn about the strategic roadmap, enhanced base language support (C23, C++23, FORTRAN), innovative tasking (free-agent threads, taskgraphs, iteration concepts), advanced loop transformations (user-defined inductions), threadsets, transparent tasks, and new device offloading features.
Watch here: https://youtu.be/YTbPPhOjO58
Slides: https://bit.ly/3OpnMP6
youtu.be- YouTubeEnjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.
The Hydration Pharmaceuticals Company ( #HPC ) has released " Q1 CY25 Sales Update " on Fri 11 Apr at 09:36 AEST #today #Australia #media #Strategy #live
https://grafa.com/asset/hydration-pharmaceuticals-company-ltd-7590-hpc.asx?utm_source=asxmktsensitive&utm_medium=mastodon&utm_campaign=hpc.asx
GrafaThe Hydration Pharmaceuticals Company share priceThe Hydration Pharmaceuticals Company (ASX:HPC) is an asset listed on the ASX, and part of the Consumer Staples sector. Grafa’s asset page shows The Hydration P
chapel-lang.orgMemory Safety in ChapelA description of how Chapel’s features for memory safety strike a balance between productivity and performance, with comparisons to other languages
https://www.europesays.com/uk/8995/ EuroHPC JU Issues Call for AI Factories Antennas – High-Performance Computing News Analysis #AI #AIFactories #AIFactoryAntennas #Computing #EuroHPC #EuroHPCJU #HPC' #Technology #UK #UnitedKingdom
Check out Michael Ferguson's new article in the Chapel Blog to learn about how Chapel's design gives it good memory safety properties. The article shows how C, C++, Rust, Python, OpenSHMEM, MPI, and Chapel respond to common programming errors.
chapel-lang.orgMemory Safety in ChapelA description of how Chapel’s features for memory safety strike a balance between productivity and performance, with comparisons to other languages