LUMI: Europe's fastest supercomputer
Advantages
Unprecedented scale
Sustainability
Easy access
Do you have a question about LUMI? Get in touch.
Computing power
HPC and AI workloads
LUMI's large GPU partition consists of 2978 nodes, each containing 4 AMD MI250x GPUs. The GPUs are directly connected to the Slingshot-11 interconnect, which makes LUMI especially suitable for processing GPU-accelerated workloads and AI projects on a large scale.
Support
Support for LUMI is available through SURF and the LUMI User Support Team (LUST). Our experts will support you in installing the software required for your research, running your applications and making efficient use of the resources that LUMI offers.
Training
With a training from the LUMI User Support Team, on-site in the Netherlands, you will learn how to work with large supercomputing systems directly from the experts at one of the largest supercomputers in the world. View the current training offer on the LUMI website.
Information for users
Related services
-
Would you like to use the largest system in the Netherlands in terms of high-performance computing, fast processors and GPUs, a very fast internal network, lots of memory space and the ability to process large data sets? Meet our National Supercomputer Snellius.Product
-
High-performance data processing
ProductDo you want to process and store large amounts of data? Our team of experts will support you in using our high-throughput data processing systems and storage solutions.Product