The BSSw Fellowship Program gives recognition and funding to leaders and advocates of high-quality scientific software. The program aims to foster and promote practices, processes and tools to improve developer productivity and software sustainability of scientific codes. This year each of the six 2022 BSSw Fellows will receive up to $25,000 for an activity that promotes better scientific software.
In his project titled “I/O sleuthing to track down errors in performance or correctness – at scale!” Rob noted that he wants to make scientific applications use I/O more efficiently. “Too often,” he said, “computational science codes focus on I/O only when something has gone wrong – a job took longer than expected, data was incorrect, or obscure failure messages come back from the storage system.”
As a BSSw Fellow, Rob will develop and teach a 1-day course on I/O problems in performance and correctness that are likely to be encountered in high-performance computing. The tutorial will include how to investigate these problems and how to fix them. Both the tutorial and associated resources will be available to the community.
Rob earned his B.S. and M.S. degrees in computer engineering at Lehigh University. After working for a Linux cluster start-up, he joined Argonne, where he has worked on the ROMIO MPI-IO implementation, the parallel file systems PVFS, and Parallel NetCD. Most recently he was on the team that won an R&D 100 award in 2021 for Mochi, which provides data services that scientists can select from and compose to suit their particular application requirements.
The 2022 class of BSSw Fellows will be recognized during the 2022 Exascale Computing Project Annual Meeting in May 2022. The announcement and list of the 2021 BSSw Fellows is on the BSSw website: https://bssw.io/blog_posts/introducing-the-2022-bssw-fellows.