mamot.fr is one of the many independent Mastodon servers you can use to participate in the fediverse.
Mamot.fr est un serveur Mastodon francophone, géré par La Quadrature du Net.

Server stats:

2.9K
active users

#hpc

22 posts17 participants2 posts today

We're expanding our gallery space in August to set up a Thinking Machines: Connection Machine with an event to celebrate the 40th anniversary. Join as a BOOTSTRAP member to attend the preview and get a behind the scene peek at the CM2's HOST, a Symbolics 3670 LISP machine, as we restore and recover its *LISP (StarLISP) programming system.

icm.museum

toobnix.org/w/57vV3XjbcdEjNVqY

icm.museumThe Interim Computer Museum

#HPC #Linux Don't ever let someone tell you classic pipelines aren't effective or useful. Non permettere mai che qualcun* dirti i tool classici dell'UNIX fanno schifo a causa che non sono "moderni"...

This is a quick way to find potentially slow links on an Infiniband fabric using clusterkit and a mixture of find, cat, and AWK.

Beep, Beep - I am your friendly #Snakemake release announcement bot.

There is a new release of the Snakemake executor for #SLURM on #HPC systems. Its version now is 1.6.0!

Give us some time, and you will automatically find the plugin on #Bioconda and #Pypi.

If you want to discuss the release, you will find the maintainers here on Mastodon!
@rupdecat and @johanneskoester

If you discover any issues, please report them on github.com/snakemake/snakemake.

See github.com/snakemake/snakemake for details. Here is the header of the changelog:

𝑅𝑒𝑙𝑒𝑎𝑠𝑒 𝑁𝑜𝑡𝑒𝑠 (𝑝𝑜𝑠𝑠𝑖𝑏𝑙𝑦 𝑎𝑏𝑏𝑟𝑖𝑔𝑒𝑑):
𝐅𝐞𝐚𝐭𝐮𝐫𝐞𝐬

* added github action to label long pending issues as 'stale' (github.com/snakemake/snakemake) ([6d7c50a](github.com/snakemake/snakemake))
* treat sbatch errors as job errors instead of workflow errors (github.com/snakemake/snakemake) ([5e38507](github.com/snakemake/snakemake))
* using the current version of the announcement bot for Mastodon (github.com/snakemake/snakemake) ([03e0e24](github.com/snakemake/snakemake))

𝐁𝐮𝐠 𝐅𝐢𝐱𝐞𝐬

* allow unse...

A Snakemake executor plugin for submitting jobs to a SLURM cluster - snakemake/snakemake-executor-plugin-slurm
GitHubsnakemake/snakemake-executor-plugin-slurmA Snakemake executor plugin for submitting jobs to a SLURM cluster - snakemake/snakemake-executor-plugin-slurm

Heute kamen Gäste aus Politik, Wissenschaft und Industrie zur feierlichen Inbetriebnahme des Native Processing Server (NPS) von Q.ANT am LRZ zusammen.

Während der Veranstaltung demonstrierte Dr. Michael Förtsch, Gründer und CEO von Q.ANT, wie das System Muster erkennt, indem es Fotos von verschiedenen Obstarten kategorisierte. Dabei braucht das Q.ANT-System deutlich weniger Strom als andere.

Mehr: lrz.de/news/detail/leibniz-rec

#KI #FutureComputing #Innovation #HPC #Supercomputing @bmftr_bund

In a surprise move, NVIDIA is bringing CUDA to RISC-V CPUs 💥
Announced at RISC-V Summit China , this allows RISC-V processors to run CUDA drivers + logic, with NVIDIA GPUs handling compute tasks ⚙️
Enables open CPU + proprietary GPU AI systems—big for edge, HPC & China’s chipmakers 🇨🇳

A potential shift in global AI infrastructure 🌐

@itsfoss

news.itsfoss.com/nvidia-cuda-r

It's FOSS News · In a Surprise Move, NVIDIA Brings CUDA to RISC-V ProcessorsA surprise collaboration, I must say.

Attention Fortran lawyers!

A colleague posed an interesting one to me (assuming b is a 2D real array containing values):
OK:
real, dimension(:), allocatable :: a
a = b(1, :)

Error:
real, dimension(:), allocatable :: a
a = sum(b(2:,:), dim=1)
! (can fixed by allocating a)

Is there a rule about automatic allocation requiring no temporaries? Or compiler bug (in either case?)