Skip to main content
News and Articles    Open call for help with porting and optimizing software, including AI software, to LUMI-G and AMD GPUs

Open call for help with porting and optimizing software, including AI software, to LUMI-G and AMD GPUs

10.5.2024

Apply for help to port and optimize your software to LUMI-G with AMD GPUs!

You can apply if you are a researcher or a company located in either one of the LUMI consortium countries or a member state that has chosen to become a member of the EuroHPC Joint Undertaking. Ph.D. students and holders of postdoctoral fellowships are also eligible to apply. Up to six (6) projects will be selected in this round. There will be more rounds in the future, approximately one per year. The selected projects will receive porting  and optimization help from the HPE Center of Excellence for LUMI and the LUMI User Support Team, amounting to 2-6 person-months. You are expected to contribute at least two (2) person-months yourself.

The deadline for applications is Sunday, 2 June 2024, 23h59 CEST.

IMPORTANT: the selected teams are invited to the hackathon organized by the LUMI User Support Team and the HPE Center of Excellence for LUMI in Brussels (Belgium) – 14-18 October 2024. The material from a previous hackathon held at CSC in April 2023 is available online for your information: https://lumi-supercomputer.github.io/LUMI-training-materials/Hackathon-20230417/

Who can apply?

This is an open call. Anyone who is a member of an organization eligible to receive an allocation for LUMI compute resources is also welcome to apply to this program. In brief, this means that a research software developer affiliated with a research organization in the EuroHPC JU-associated countries and/or countries part of the LUMI consortium can apply. A company, which has its headquarters in such countries, is also eligible. By partnering with European research groups and/or companies, a non-European applicant can also participate, but please note that the principal investigator of any project that applies will need to be based in the EU or a Joint Undertaking associated country. Ph.D. students and holders of postdoctoral fellowships are also eligible to apply, but we may ask for further letters of support in such cases.

For more information, please see:

What we are looking for?

We are looking for research groups and companies interested in making their scientific software, including AI software, utilize the new AMD GPU-compute architecture in LUMI to the fullest in collaboration with LUMI experts. Please note that this call is not an allocation scheme for compute time, e.g., to enable porting by the applicants. Instead, we are looking for proposals outlining a team porting or optimization effort of existing software. The scope should be limited so that the task can be accomplished in less than six months with a project team of ca. four (4) people working part-time. If the proposal is selected, a team will be formed consisting of the applicants, one or more staff from HPE’s Center of Excellence, and one member of the LUMI User Support Team. This team will work together on enabling the software on LUMI-G.

We expect that the software is already parallelized to use multiple CPUs, preferably across many nodes using MPI (or equivalent). The main focus is to enable the use of AMD GPUs, although, depending on the use of the programming paradigm, it may also run on other GPUs and accelerators as a result of the work. We are mainly looking for software projects with open-source licenses or at least free academic use. We will consider commercially licensed software only in exceptional cases. In such cases, a high-level description of the implementation, such as a scientific publication describing the algorithms, will still have to be made public. In any case, the applicant must agree to grant access to the source code to the HPE’s Center of Excellence and the member of the LUMI User Support Team assigned to the project.

How to apply

Opening date: 10 May 2024
Closing date: 2 June 2024
Project start: 2024H2

Proposals need to be provided using the template, which can be download here. The completed proposals should be submitted as a PDF file using the LUMI support forms available at https://lumi-supercomputer.eu/user-support/need-help/generic (please select the “General” category and put “LUMI Porting Program” in the subject).

The application form (4 pages) is structured as follows:
• Introduction/Background to the software and its use in the scientific field (ca 1 page).
• A scientific motivation (ca. 1 page) describing the potential impact of a successful porting project, e.g., what kinds of simulations could be made possible.
• A technical description of the software from a software development perspective (ca 1 page). The template provides guidance on the relevant information to provide.
• A brief project plan/description of how (parts of) the software could be ported to the GPU and the reason why (ca. 1 page).
• Call_application_form

How we will assess your application

Assessment process

The project will be selected in a two-stage process. The proposals are first subject to scientific and technical review and then ranked. The scientific review is performed by the LUMI consortium and/or external evaluators. The technical review is performed by the LUMI User Support Team and HPE Center of Excellence (“CoE”). A shortlist is then made, and the top proposals are invited to an interview (done remotely, ca. 1 hour). Applicants will be provided with comments prior to the interview to provide them with the opportunity to add further details to their applications. The interview will only be focused on the technical feasibility and not on the scientific merit.

Assessment criteria

The scientific assessment is mainly done with respect to the potential impact in the specific field of science where the software will be used. Relatively less importance will be paid to the scientific track record of the applicant. Furthermore, the proposed software and/or implementation is evaluated relative to the state-of-the-art in the field, and if a successful porting project would fill a gap in the currently available software on LUMI.

The technical assessment is mainly done with respect to the technical feasibility of porting the software to AMD GPUs and subsequently running on the LUMI supercomputer. These include both:

1) technical aspects of the software, such as programming language, the use of libraries and frameworks, and the internal data structures and algorithms, and
2) the practical aspects, such as the project plan and the applicant’s ability to participate in the proposed project. In particular, the software development track record of the applicant (or applicants), and the balance of skills in the final project team, which will include staff from the HPE CoE and the LUMI User Support Team, will be taken into account.

Projected software speed-ups or preliminary benchmarks are helpful in the evaluation but are not required.

Don’t hesitate to contact the LUMI User Support Team at https://lumi-supercomputer.eu/user-support/need-help/ if you need any assistance.