Authors: David Bernholdt (Oak Ridge National Laboratory (ORNL)), Anshu Dubey (RIKEN Center for Computational Science (R-CCS)), Robert Haines (University of Manchester), Mozhgan Kabiri chimeh (NVIDIA Corporation), Daniel Katz (University of Illinois Urbana-Champaign), Lauren Milechin (Massachusetts Institute of Technology (MIT)), Spencer Smith (McMaster University), Sheri Voelz (NSF National Center for Atmospheric Research (NCAR)), Marion Weinzierl (University of Cambridge)
Abstract: Software has become central to all aspects of modern science and technology. Especially in high performance computing (HPC) and computational science and engineering (CSE), it is becoming ever larger and more complex while computer platforms evolve and become more diverse. Simultaneously, the teams behind the software are becoming larger, more technically diverse, and more geographically distributed. AI tools add both great potential and significant caution.
This BoF will address these issues and more, sharing experiences and best practices, and building community around software topics. Presentations and discussion notes will be made available at the BoF series website (http://bit.ly/swe-cse-bof).
Long Description: The engineering of software for modeling, simulation, and data analytics for computational science and engineering (CSE) continues to receive insufficient attention within our community.. We celebrate the big machines, the scientific discoveries they enable when driven by sophisticated software, and the ingenuity and creativity of the software itself. We pay much less attention to how the software was developed and many other aspects of the entire lifecycle of a CSE application, including portability, sustainability, overall productivity, and usability by and for the community. Major concerns, such as reproducibility, start with good software development practices.
At the same time, the pace of change and level of diversity in architectures have increased dramatically, and the drive to exascale exacerbates the situation. CSE software developers must now also contend with significant architectural changes, in addition to the existing scientific demands for “bigger, better, and faster” modeling and simulation capabilities, which entail larger, more multidisciplinary, and geographically dispersed development teams. Further, increases in data volume and complexity, and the increasing integration of “big data” (analytics & AI/ML) infrastructures (both hardware and software) raise additional SWE challenges.
Finally, the teams behind the software are growing in size, technical diversity, and geographical distribution. Emerging roles, such as Research Software Engineers are often part of these teams, but so are many others.
Fortunately, a growing number of individuals and organizations are paying more attention to addressing this challenge. But their work is not yet widely shared, and the sharing and uptake of good practices is fragmented. Meanwhile, AI tools have the potential to up-end traditional practices of software development and maintenance. We believe that the next step in the process is a concerted effort to increase awareness and sharing of work on SWE for HPC CSE to help build the community of practice, capable of fostering good practices, including AI usage, that will result in software fit to power CSE through the next era of computing and recognizing and empowering the people who strive for better scientific software.
Our goal is to bring together people who are concerned and passionate about this topic to share existing activities, explore avenues of expansion and improvement, and share the results, complementing “traditional” venues for the academic (often versus practical) discussion of SWE for CSE, such as conferences and workshops. An interactive Google Doc will be used to collaboratively take notes of the discussion. These notes will be made publicly available.
The SC Conference Series provides an ideal venue for these discussions. A large fraction of the attendees are CSE practitioners or researchers who support such activities. Past editions of this BoF (SC15-25, and ISC2019, 2022-2023), have been very well attended and the discussions highly engaged. Supercomputing will also host a number of complementary activities, including workshops on software correctness, research software engineering and performance portability, a software-oriented tutorials, and, likely, other BOFs. There is also the overall SC Reproducibility Initiative. We believe these activities are highly complementary and will be synergistic in generating interest and participation from the SC community.
Website: http://bit.ly/swe-cse-bof