This four day online course serves as a general comprehensive introduction to the LUMI architecture and programming environment. It will include lessons about compiling and using software, programming models (HIP and OpenMP offload), porting, executing jobs, and optimizing applications to run on AMD MI250X. After the course you will be able to work efficiently on both the CPU (LUMI-C) as well as GPU partition (LUMI-G).

Please note, that this is comprehensive course with an emphasis on code development. LUST is also organizing recurring 1-day introduction courses to LUMI. It includes lessons about the most important topics needed to install and use software on LUMI and run jobs efficiently on LUMI-C and -G. More information is available here: https://www.lumi-supercomputer.eu/events/lumi-intro-course-16may23/. All courses do expect some familiarity with HPC already, e.g., from courses organised by most local compute centres, and are designed to focus on LUMI-specific elements.

Event info

The course will be jointly conducted by the LUMI HPE Centre of Excellence (HPE CoE), AMD and the LUMI User Support Team (LUST).

We intend this course for users with ongoing projects on LUMI, users with project proposals in one of the national or EuroHPC channels, and support staff of local organisations of the LUMI consortium members.

The course is first and foremost an in-person event. All sessions will be broadcasted via Zoom, but direct interaction with the speakers is only possible in the lecture room. There will be an on-line document where others can leave questions, but questions from the audience in the lecture room take priority. Several staff from HPE, AMD and LUST will be on-site, so this is the perfect moment for interaction with them.

The venue for in-person attendance is at IT Kolledž, Raja 4c, Tallinn, Estonia. See the bottom of this page for more information on the venue. Participants are responsible themselves for all travel bookings.

We will keep a waiting list if registrations exceed the number of planned participants. See the link to the registration at the bottom of this page. Registration deadline is 23. May 2023 16:00 CEST. As capacity is limited, participants who only intend to attend part of the course are kindly requested to leave their spot to others who want to benefit from the whole course.

Attendance both in-person and online is free of charge. A sandwich lunch will be provided to in-person participants.

For doing the hands-on exercises and access the slides and training material on the course day, participants will have to join a course specific training project. This project is Puhuri managed which means that CSC users have to set up a new LUMI user account. Step-by-step instructions will be sent out after the registration on how to join the project and set up an account (if needed).

Registration

Register for the course latest by 23. May 2023 16:00 CEST. We reserve up to 20 in-person places for people traveling to Estonia from abroad, and they will get a quick confirmation on a first come, first serve basis so that they can arrange travel. Other participants will receive confirmation shortly after the deadline. If your plans change, we kindly ask you to cancel your registration as soon as possible (ideally before the registration deadline). The email acknowledging your registration will contain a link to manage it.

Users who don’t have an account on LUMI yet will receive temporary access for the purpose of the course. The compute time allocated to the course should only be used for the purpose of doing the exercises of the course. Any abuse will lead to removal from the allocation for this and future courses.

Please, do not hesitate to contact the LUMI User Support Team if you need any assistance https://lumi-supercomputer.eu/user-support/need-help/ Thank you.

Agenda

The main topics day by day. Each day 9:00 til 17:00 EEST  / 8:00 til 16:00 CEST.

Day 1 – Connecting to the system, building and executing applications and simple use of GPUs via libraries.
Day 2 – Programming GPUs via OpenACC and OpenMP, Optimizations techniques, additional software on LUMI, LUMI support.
Day 3 – Debugging, I/O, HIP programming, ROCm tools.
Day 4 – Profiling, Advanced ROCm tools.