AI on Supercomputers
|
| >> News: AI Competition <<Gauss Centre AI Competition: As part of the Gauss AI Compute Competition, researchers will, for a specified period, gain special access to JUPITER (roughly 15 million GPU-hours) will be available from the beginning of JUPITER’s operation: More Information |
|
| Joint Initiative of NHR and GCSThe Gauss Centre for Supercomputing (GCS) and the NHR Alliance (NHR) offer support for using high-performance computing for AI applications. A web seminar has been jointly developed and was offered for the first time in October 2023 and has been held weekly ever since. |
|
AI - From Laptop to Supercomputer
Do you need compute time for AI projects? Is your workstation or university cluster too small? Are you considering a project even on the largest scale? The National High Performance Computing Alliance (NHR) and Gauss Centre for Supercomputing (GCS) can help. We provide computing resources well suited for AI in twelve High Performance Computing (HPC) Centres. The best: this is for free for scientists who belong to a German research institution.
>> AI Web Seminar
In our web seminar, we will give an overview over the HPC landscape in Germany, provide an introduction of supercomputer/HPC architecture, and where and how to apply for compute time. We provide a starting point for you to bootstrap your compute time application to a German Tier 1 or 2 HPC Centre.
Next session | 20.03.25, 14:00 - 16:00
AI - From Laptop to Supercomputer
Eventlink: go-nhr.de/ai_on_hpc_vconf | Language: English
Contact: aionsupercomputer@nhr-verein.de
>> Q&A Café | Questions & Answers
If you have any questions, please join our open "Questions & Answers"-session which takes place every Thursday between 14:00 and 15:00. Our experts from NHR and GCS will answer all your questions on how to get access to computing time and using it in the most efficient way. Join us and let us chat about AI and supercomputers!
Every Thursday, 14:00 - 15:00
AI - From Laptop to Supercomputer
Info: on 20.03.2025 there will be an AI Web Seminar
Eventlink: http://go-nhr.de/ai_on_hpc_vconf | Language: English
Contact: aionsupercomputer@nhr-verein.de
Q&A with a special focus | 13.03.25, 14:00 - 15:00
Topic: "Leveraging Deep Learning for Inverse Design in Material and System Development"
Targeted design of materials and systems with certain desired properties is an important and general task across many scientific and engineering domains, but is incredibly difficult due to its ill-defined, functionally inverse nature. Traditionally, brute-force approaches have instead been employed together with niche expertise to generate and analyse massive datasets for candidate materials or systems of interest, often incurring great time and computational expenses. Recently, deep learning methods have found a way to avoid such expensive forward design approaches, by modelling the inverse design function. In this talk, we discuss the general problems/approaches to inverse design, and we present two recent applications which show the feasibility and power of inverse design with deep learning. We then discuss other potential applications of these new modelling approaches.
Vergangene Q&A-Veranstaltungen mit einem besonderen Fokus
Title | Presentations, Links, Information | |
| "Optimization with Omniopt" - Peter Winkler | A tool for hyperparameter optimization when you work with neural networks and Big Data. |
| "Efficient Access on many small files on HPC file systems - Ratarmount" - Sebastian Döbel |
|
| "Experiences running AI applications on Intel Ponte Vecchio systems" - Nicolas Charron (25.07.2024) | |
| "Tracking Deep Learning Experiments with Weights & Biases" - Nicolas Charron | |
| "Easy PyTorch HPC" - Nicholas Charron, Fritz Niesel | https://lightning.ai/, https://github.com/ashleve/lightning-hydra-template |
| "The Virtual Environment Template" - Stefan Kesselheim | The Virtual Environment Template is a simple, customizable template how to build Python Virtual Environments on top of Easybuild packages. At the Jülich Supercomputing Centre, the environment can be readily used to create Jupyter Kernels. |
HPC resources to get started
You can apply for projects at the GCS centers and at NHR können Sie die HPC-Ressourcen beantragen.
If you have no previous experience with the application process and the use of high-performance computers, we recommend the NHR Starter projects with a shortened application procedure.
AI Events
Are you interested in events that are relevant for working with artificial intelligence methods on high-performance computers?
Here we offer you a filtered view of the Gauss Alliance calendar (not just NHR organizers!): AI Events