BoF: International HPC Certification Program

There is a generally accepted set of skills and competencies necessary to efficiently use HPC resources. Making clear what skills are required or recommended for a competent HPC user would benefit both the HPC service providers and practitioners. This BoF will present the status of the recently founded International HPC Certification Forum aiming to categorize, define, and examine these skills to create an ecosystem. To ensure this is an independent community-wide effort, we invite anyone interested in HPC teaching/ training to participate in the discussion and get involved. Inputs from academia, industry and HPC centres will steer the future effort.

The BoF is held in conjunction with the Supercomputing conference. The official schedule is listed here.

The HPC community has always considered the training of new and existing HPC practitioners to be of high importance to its growth. The significance of training will increase even further in the era of Exascale when HPC encompasses even more scientific disciplines. This diversification of HPC practitioners challenges the traditional training approaches, which are not able to satisfy the specific needs of users, often coming from non-traditionally HPC disciplines, and only interested in learning a particular set of skills. HPC centres are struggling to identify and overcome the gaps in users’ knowledge. How should we support prospective and existing users who are not aware of their own knowledge gaps?

During the session, we will introduce the HPC Certification Forum, its roles and responsibilities, and describe the current status including skill tree and tools to exploit this data. Similar to a school curriculum, the Forum defines skills with their encompanied knowledge and will aim to provide tests to obtain certificates. It won’t produce any teaching material but will allow the existing teaching materials to be branded and listed for the use of HPC community. Voices from academia, HPC centers, and industry will describe how this initiative may help to mitigate educational issues they encounter in their work. Next, we illustrate how the provided tools can be used by practitioners to indicate domain scientists what skills are recommended for their roles or how to disseminate their own teaching materials on their own webpages. To steer the activity, we aim to obtain feedback on the overall strategy, the developed HPC skill tree and methods of their examination. We will also discuss next steps and and governance model. After creating an international consortium we hope for the certificates to be recognized and respected by the HPC community and industry.

Our target audience is anyone involved or interested in HPC Education and Training, including but not limited to HPC training providers, educators and trainers, user support personnel, HPC users of different proficiency levels, domain scientists, people responsible for recruitment in academia and industry, and industry representatives. The aim of this session is to scope the needs of the HPC community (including its users) and the diversity of opinions is one of the ways to make sure this effort is moving in the right direction. So we welcome anyone interested in this conversation to participate to make sure this becomes an independent community-wide effort. We expect that the outcome of this BoF will strongly steer the direction of this community effort.

The BoF is organized by

• Julian Kunkel (University of Reading, UK)
• Weronika Filinger (University of Edinburgh, UK)
• Jean-Thomas Acquaviva (DDN, France)

We have a series of talks followed by a discussion:

• Introduction of the HPC Certification Program – Julian Kunkel
• Short presentations from representatives of data centers, academia and industry describing how this could help to mitigate the issues
  • Weronika Filinger
  • Jean-Thomas Acquaviva
• Introduction of the current skill tree – Anja Gerbes
• Tools for interacting with the skill tree – Julian Kunkel
• Roadmap – Lev Lafayette
• Panel and discussion

Julian Kunkel – Dr. Kunkel is a Lecturer at the Computer Science Department at the University of Reading. He manages several research projects revolving around High-Performance Computing and particularly high-performance storage. The efficient teaching of practical skills and software engineering for scientific software are part of his interest. Julian strongly believes that international recognition of skills will help the HPC ecosystem.

Anja Gerbes – Anja is employed at the Center for Scientific Computing in Frankfurt. In Frankfurt she is responsible for the LOEWE-CSC and FUCHS cluster at Goethe University. As a member at the Hessian Competence Center for High Performance Computing (HKHLR) for the location of Goethe University in Frankfurt am Main, her task is to help scientists for the Universities of Hessen with their programs, to optimize and improve them. She is giving lectures in different HPC topics to introduce users to the cluster environment.