Educloud Research
Educloud Research is a project-oriented self-service Platform as a Service. Educloud is designed for cross organization and cross border collaboration, linux and windows users, HPC users, massive storage, data analysis, sharing and collection. When you are PI of an an Educloud project, you are able to give access to any of your collaborators through self-service. For collaborators holding a BankID everything is selfserviced, for foreign users please contact contact Educloud on ec-contact@uio.no and we’ll help you out.
Educloud Research – Fox supercomputer
Fox is the 'general use' HPC system within Educloud, open to researchers and students at UiO and their external collaborators. There are 24 regular compute nodes with 3,000 total cores and five GPU accelerated nodes with NVIDIA RTX 3090 and NVIDIA A100 cards available.
The Fox cluster owned by UiO, this means that if you are a UiO researcher, access to low threshold HPC resources and scientific software is completely free! Only extras like extra storage or advanced user support might trigger a cost, see Educloud cost model. If you use a lot of CPU hours on Fox we will also help you get access to the national HPC clusters.
As Fox is connected to the same storage system as the rest of the Educloud it is straightforward to access the same data on a connected desktop as on Fox. Just by registering a project for HPC use, you’ll get 1 TB shared project specific storage for free, including backup to tape. And since the storage is within Educloud you can store anything up to and including most types of red data.
Not all workflows fit well with the traditional HPC setup with submitting jobs to a queueing system through a job script. For development, testing, experimental code etc. we have set up four nodes for interactive use outside the queueing system, each with 128 CPU cores, 1024 GiB of memory, 6 TiB NVMe scratch disk and InfiniBand interconnect. To avoid too many limits and restrictions, these nodes are currently governed by the Kardemommeloven (English: Law of Cardamom). More information about the interactive nodes here.
Access to Fox requires having an Educloud user, see registration instructions. For instructions and guidelines on how to use Fox, see Foxdocs - the Fox User Manual.
Lightweight HPC and Machine Learning Capabilites @UiO
Lightweight HPC is a resource for all UiO users interested in testing out or running their scientific applications, simulation software, parallel code etc., ideal for small-scale scientific needs. In addition, a set of ML nodes is available for GPU based workloads. These services are free of charge for all UiO users and offer access to stand-alone machines for lowthreshold use, with a limited best-effort user support. To get access to any of these resources, just fill in the Request access to Light-HPC and ML nodes registration form.
Happy computing!