About
The Accelerating Devices Lab (X-Dev) is an Algorithms, Tools, and Methods Lab at Jülich Supercomputing Centre (JSC). We focus on GPUs and other devices for accelerating computations by optimization applications for the platforms.
We are doing many different things, some within third-party-funded projects, some outside. Here, we want to talk about them.
Projects
Read more about our projects at dedicated pages:
Authors
-
Albert Kahira
(Albert) -
Andreas Herten
(Andreas) -
Carolin Penke
(Carolin) -
Chelsea John
(Chelsea) -
Sebastian Achilles
(Sebastian) -
Stepan Nassyr
(Stepan)
Tags
There are various tags used on this site to sort articles and pages into categories.
XDev
General
GPU
Conference
ISC22
Tutorial
MAELSTROM
Presentation
FZJ
NVLab
Workshop
OpenGPTX
OPTIMA
Deliverable
X-Dev
AMD
DOI
Open-Science
Poster
HPC
MSA
modular
heterogeneous
Cluster
Booster
MExMeMo
Hackathon
Training
NCCL
MPI
XDev
- X-Dev Website at fz-juelich.de 24 Jun 2022
- Hello, X-Dev Blog! 29 May 2022
General
- Hello, X-Dev Blog! 29 May 2022
GPU
- MPI as API: Using UCC's NCCL Backend for MPI's Allreduce 18 Jul 2023
- Helmholtz GPU Hackathon 2023 03 Jul 2023
- MSA Introduction Workshop 28 Jun 2023
- ISC23 Project Poster: OpenGPT-X – Training Large Language Models on HPC Systems 26 May 2023
- GPU Vendor/Programming Model Compatibility Table 02 Nov 2022
- Multi-GPU Computing Tutorial at ISC22 02 Jun 2022
Conference
- Multi-GPU Computing Tutorial at ISC22 02 Jun 2022
ISC22
- MAELSTROM: First benchmarks at ISC22 24 Jun 2022
- Multi-GPU Computing Tutorial at ISC22 02 Jun 2022
Tutorial
- Multi-GPU Computing Tutorial at ISC22 02 Jun 2022
MAELSTROM
- Talk: Introduction to HPC 10 Oct 2022
- MAELSTROM: First benchmarks at ISC22 24 Jun 2022
Presentation
- MAELSTROM: First benchmarks at ISC22 24 Jun 2022
FZJ
- X-Dev Website at fz-juelich.de 24 Jun 2022
NVLab
Workshop
- Poster: OpenGPT-X - Training Large Language Models on HPC Systems 06 Oct 2022
- A mathematician's introduction to transformers and large language models 13 Jul 2022
- 10 Year Anniversary Workshop of NVIDIA Application Lab at Jülich 29 Jun 2022
OpenGPTX
- ISC23 Project Poster: OpenGPT-X – Training Large Language Models on HPC Systems 26 May 2023
- Poster: OpenGPT-X - Training Large Language Models on HPC Systems 06 Oct 2022
- A mathematician's introduction to transformers and large language models 13 Jul 2022
OPTIMA
- OOPS Version 1 Release 21 Jul 2022
Deliverable
- OOPS Version 1 Release 21 Jul 2022
X-Dev
- DOIng it Right! (DOIs for This Blog) 05 Oct 2022
- First Benchmarks with AMD Instinct MI250 GPUs at JSC 01 Aug 2022
AMD
DOI
- DOIng it Right! (DOIs for This Blog) 05 Oct 2022
Open-Science
- DOIng it Right! (DOIs for This Blog) 05 Oct 2022
Poster
- ISC23 Project Poster: OpenGPT-X – Training Large Language Models on HPC Systems 26 May 2023
- Poster: OpenGPT-X - Training Large Language Models on HPC Systems 06 Oct 2022
HPC
- MPI as API: Using UCC's NCCL Backend for MPI's Allreduce 18 Jul 2023
- MSA Introduction Workshop 28 Jun 2023
- ISC23 Project Poster: OpenGPT-X – Training Large Language Models on HPC Systems 26 May 2023
- GPU Vendor/Programming Model Compatibility Table 02 Nov 2022
- Talk: Introduction to HPC 10 Oct 2022
MSA
- MSA Introduction Workshop 28 Jun 2023
modular
- MSA Introduction Workshop 28 Jun 2023
heterogeneous
- MSA Introduction Workshop 28 Jun 2023
Cluster
- MSA Introduction Workshop 28 Jun 2023
Booster
- MSA Introduction Workshop 28 Jun 2023
MExMeMo
- MSA Introduction Workshop 28 Jun 2023
Hackathon
- Helmholtz GPU Hackathon 2023 03 Jul 2023
Training
- Helmholtz GPU Hackathon 2023 03 Jul 2023