mastodon.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
The original server operated by the Mastodon gGmbH non-profit

Administered by:

Server stats:

341K
active users

#hpc

32 posts31 participants1 post today

In #Jülich startet der #Supercomputer Jupiter, Europas erster #Exascale-Rechner mit über einem #ExaFLOP/s, in den Testbetrieb.

Das modular aufgebaute #Rechenzentrum in Containern nutzt rund 24.000 #Nvidia GH200-Chips für Simulationen und #KI-Training.

Ziel ist nicht nur Leistung, sondern auch #Energieeffizienz mit #Wärmerückgewinnung. Ab 2027 ergänzt das KI-Modul #Jarvis das System.

heise.de/news/Juelicher-Superc

heise online · Jülicher Supercomputer Jupiter startet ProbebetriebBy Bernd Schöne

My brain is absolutely fried.
Today is the last day of coursework submissions for this semester. What a hectic month.
DNN with PyTorch, Brain model parallelisation with MPI, SYCL and OpenMP offloading of percolation models,hand optimizing serial codes for performance.
Two submissions due today. Submitted one and finalising my report for the second one.
Definitely having a pint after this

#sycl#hpc#msc

Die Open Edge and HPC Initiative (OEHI) und die @gwdg haben ein gemeinsames Proof of Concept (PoC)-Projekt gestartet, um die Datenverwaltung in Compute Continuum-Infrastrukturen zu untersuchen, die HPC-Knoten, Cloud- und Edge-Umgebungen nahtlos integrieren. Traditionell greifen HPC-Knoten über ein POSIX-Dateisystem auf Daten zu, während Cloud- und Edge-Knoten über eine Objektspeicherschnittstelle interagieren.

⏩ s.gwdg.de/yXemQv
⏩ s.gwdg.de/V0A0nd

🚀 Intel Developer Tools v2025.1 is here with new OpenMP 6.0 features!

The Intel® Fortran Compiler enhances #OpenMP 6.0 support with two powerful additions: WORKDISTRIBUTE for efficient thread-level work distribution, and INTERCHANGE to reorder loop nests for improved parallelism and optimization.

A big win for HPC and embedded devs!

intel.com/content/www/us/en/de

IntelIntel® Software News UpdatesStay up to date on the latest software happenings, including software releases, new capabilities, ecosystem adoption, success stories, and more.

Started SYCL this semester in my MSc, and I have a coursework on it.
I have never been more frustrated in my life.
I am not saying SYCL is bad. I might just be too dumb to master it in a sem in order to port an existing CPU code to use MPI & SYCL together.
CUDA was much easier for me for the same task.

We were thinking to take the entire #HPC section to #SC in St Louis this year (it's time for us to build a new cluster). But for obvious reasons none of us are going, not this year nor coming years.

Fortunately, HPC Asia *and* Supercomputing Asia will have a joint 4-day conference in Osaka, Japan in January! It's perfect - not just because it's 15 minutes by bicycle from our family home; Glitch #coffee has a shop at walking distance. Just saying.

sca-hpcasia2026.jp/

www.sca-hpcasia2026.jpSCA/HPCAsia 2026 - Convention Linkage, Inc.Website of SCA/HPCAsia 2026 to be held at Osaka International Convention Center, Japan, January 26-29, 2026.