#highPerformanceComputing

2025-06-12

Nun steht es fest: am 20.06. werde ich wieder eine, wenn auch kleine, aber feine Computer Ausstellung in #clausthalzellerfeld organisieren! Es geht dabei um das Thema #Zuse bis #highperformancecomputing - und natürlich auch um #homecomputer . Mehr kommt die Tage auf meiner Homepage Harzretro.de

#TUClausthal
#harz
#osterodeamharz
#goslar
#retrocomputing

2025-06-06

🚀 RoCE vs. InfiniBand: Asterfusion 800G Switch in AI Networking
In the realm of AI data centers, the debate between RoCE and InfiniBand is intensifying. Recent evaluations of Asterfusion's 800G RoCE switches reveal:

Lower P90 Inference Latency: Enhanced performance in AI inference tasks.

Higher Token Generation Rate: Improved throughput for large-scale AI models.

Cost Efficiency: Comparable performance to InfiniBand at a reduced cost.

These findings suggest that RoCE, especially when implemented on Asterfusion's 800G switches, offers a compelling alternative for AI networking infrastructure.

📖 Dive deeper into the analysis:
🔗 RoCE Beats InfiniBand? Asterfusion 800G Switch for AI Networking

#RoCE #InfiniBand #AIInfrastructure #800GSwitch #Asterfusion #DataCenterNetworking #HighPerformanceComputing #CloudSwith

DMI Universität Baseldmi_unibasel@wisskomm.social
2025-05-29

FANTASY Basel 2025 here we go!

📍Find us in the Sci-Fi & Space Area in Hall 1.2, booth nr. 307

#computerscience #ai #cybersecurity #highperformancecomputing

Center for Health Data Scienceheads@datasci.social
2025-05-09

Registration is FREE and covers:
- Transportation to and from Copenhagen
- A discount on overnight stay
- Food and drinks throughout the day

⚠️Deadline for registering is May 12th:
ddsa.dk/event/high-performance

#hpc #highperformancecomputing #ai #hackathon #copenhagen

John Carlsen 🇺🇸🇳🇱🇪🇺johnlogic@sfba.social
2025-05-08

About 24 years ago, I was introduced to AMD's HyperTransport (HT) while designing part of the first computer to implement it: the Newisys 2100.

UALink seems to have grown from HyperTransport, so I'm excited to see this.

(Recently, I saw something that suggests that NVIDIA is doing something similar but proprietary, and may have some catching up to do.)

"Open Compute Project Foundation and UALink™ Consortium Announce a New Collaboration"

Tuesday, April 29, 2025
Posted by Cliff Grossner, Ph.D. Chief Innovation Officer

opencompute.org/blog/open-comp

#HPC #HighPerformanceComputing

Research Computing ServicesCambridge_RCS@mast.hpc.social
2025-04-23

🎉 On March 27, something pretty special happened in Cambridge!

After months of prep, the @whpc Cambridge & East Anglia chapter teamed up with the RSE East of England group to host an incredible day of sharing, connecting, and showing off the amazing work of our community. About 25 brilliant folks – from Researchers and RSEs to HPC specialists – came together to do just that.

The theme? “Show up and show off!”

@whpc @ResearchSoftEng #WHPC #RSE #HighPerformanceComputing

Nine Internet Solutions AGninecloudnavigators
2025-04-23

🤖 The AI is omnipresent – with our GPU servers, you are perfectly equipped for the digital future. Why? Because they deliver the performance that AI tasks need and fulfil the requirements of modern high-performance computing (HPC). 💪 The great thing about it all? We also offer our GPU servers as a managed option – we take care of the server management for you. 👉 You can find all the information on our website at nine.ch/products/gpu-server/

2025-04-16

Job - Alert 💻

📚 W3-Professur „High-Performance Computing“

Deadline: 2025-05-22

Location: Germany, Hamburg

academiceurope.com/job/?id=743

#hiring #Professor #HighPerformanceComputing #mechanicalengineering #materialengineering #softwareengineering

2025-04-04
2025-04-04

Jülicher Supercomputer Jupiter startet Probebetrieb

Es kommt Leben in das Jülicher Containerdorf, in dem bald der Supercomputer Jupiter in Betrieb gehen soll – als Erster in Europa mit mehr als einem ExaFLOP/s.

heise.de/news/Juelicher-Superc

#HighPerformanceComputing #IT #KünstlicheIntelligenz #Server #Supercomputer #news

N-gated Hacker Newsngate
2025-04-01

🐢 Oh, joy! Yet another terminal dashboard that promises to save the planet by turning your PC into a snail when the electricity bill spikes. Because who doesn't love their high-performance computing being held hostage by a smart plug with delusions of grandeur? 🌍🔌
naveen.ing/cli-for-smartplugs/

2025-03-28

📢 🔥 Updated article on Blosc2: Compute with TB-sized datasets on your own hardware, within human timeframes!

Highlights:

🚀 Outperforms NumPy by 10x ~ 100x for large computations
💾 Maintains performance with datasets far exceeding physical memory
🐍 Integrates seamlessly with the Python data science ecosystem
💻 Works both in-memory and on-disk with minimal performance differences

Read more: ironarray.io/blog/compute-bigg

#DataScience #BigData #Compression #HighPerformanceComputing

Speedups of up to more than 75x for Blosc2 when doing computations with arbitrary NumPy functions.
2025-03-25

JobSet: New API for distributed ML and HPC applications on Kubernetes

The new open source JobSet API is designed to provide more flexible and diverse configuration options for large-scale distributed HPC and ML use cases.

heise.de/en/news/JobSet-New-AP

#Containerisierung #HighPerformanceComputing #IT #Kubernetes #MachineLearning #news

2025-03-25

JobSet: Neue API für verteilte ML- und HPC-Anwendungen auf Kubernetes

Die neue Open-Source-API JobSet soll flexiblere und vielfältigere Konfigurationsoptionen für groß angelegte verteilte HPC- und ML-Anwendungsfälle liefern.

heise.de/news/JobSet-Neue-API-

#Containerisierung #HighPerformanceComputing #IT #Kubernetes #MachineLearning #news

2025-03-25

SK Hynix and TSMC lead the HBM memory market, driven by AI and high-performance computing demands, reshaping the global semiconductor industry.The semiconductor industry is witnessing a seismic shift as High Bandwidth Memory (HBM) becomes the cornerstone of AI and high-performance computing. ❤️

redrobot.online/2025/03/asian-

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst