Copilot on HPC Devana: Building Your Own AI Programming Assistant

Date: 27 March 2026

In this hands-on training course, participants will build their own AI copilot – a chatbot capable of assisting with programming tasks, answering technical questions, and generating code.

The course is based entirely on open-source models, while the underlying infrastructure runs on the Devana HPC system. This approach offers significant advantages in terms of security, performance, efficient data processing, and flexibility for experimentation.

Prerequisites

• Basic knowledge of Python
• Basic understanding of large language models (LLMs)

Note: This course is organised within the Hopero service portfolio. Registration must be completed through the Hopero client portal.

PERUN Discovery Workshop

Date: 27 March 2026
Time: 10:00–12:00
Venue: Computing Centre of the Slovak Academy of Sciences, Bratislava
Format: Hybrid (in-person and online via Zoom)
Language: Slovak
Speakers: HPC Team of the SAS Computing Centre and representatives of Eviden/Bull Slovakia

This technical workshop is dedicated to the new Slovak supercomputer PERUN and provides a practical introduction to its architecture, compute partitions, node types, and the basic principles of working with the system.

The programme will also include a comparison with the existing Devana HPC system, as well as demonstrations of job scheduling and workload management. Participants may join either in person or online. Registered online participants will receive a Zoom link by email several days before the workshop.

Programme

9:30–10:00

Registration, coffee and refreshments

10:00–11:30

• Welcome and introduction of the speakers and the HPC team
• Introduction to HPC PERUN: overall architecture, hardware overview, MDC, cooling, and technology infrastructure
• Compute partitions and node types, storage systems, and network infrastructure
• HPC PERUN and HPC Devana – similarities and key differences
• User authentication, access, security, and user environment
• File systems, data management, and usage accounting
• Practical demonstration of the system: SLURM workload manager, parallel jobs, and GPU computing

11:30–12:00

Questions and open discussion

Registration

If you would like to attend the workshop, please register via the REGISTRATION FORM.

Please note that the number of in-person places is limited.

Target Audience

The workshop is intended primarily for:

• Existing users of the SAS HPC infrastructure
• Researchers and PhD students using HPC resources
• New users interested in gaining access to the PERUN system