QUARTERLY March 2025

RSVP for ICL35

2024 marked ICL’s 35th year of Innovative Computing. To commemorate this milestone, ICL is hosting a 35th anniversary workshop on May 29-30, 2025.

Registration is now open through April 11th. If you have not yet done so, please submit a response via one of the following options:

I will attend I will not be able to attend

ICL Winter Reception

PausePlayPlayPrev|Next

On February 28, ICL members gathered at Calhoun’s on the River for the 2025 Winter Reception, joined by family and some former colleagues for a relaxed dinner and conversation. This year’s gathering was especially meaningful as attendees marked the retirement of Tracy Lee, who has served as ICL’s business manager in recent years. The group presented Tracy with gifts in honor of her time at ICL.

ICL 2024/25 Report

The ICL 2024/25 Report is available to download as a PDF and print copies are available from ICL’s main office.

ICL Alumni Named Editors-in-Chief of ACM TOMS

ICL alumni Hatem Ltaief and Piotr Luszczek have been appointed as the new Editors-in-Chief of ACM Transactions on Mathematical Software (TOMS), a prestigious journal in the field of computational mathematics. With their combined expertise and leadership, they are set to guide the publication in advancing high-quality research in mathematical software.

Submit your research paper to them at: https://dl.acm.org/journal/toms

ACM TOMS Teaser Videos

In their introduction video, Hatem and Piotr announced a new initiative from TOMS for creating teaser videos of accepted papers. The first teaser video posted by ACM TOMS highlights work by ICL’s Neil Lindquist, Piotr Luszczek, and Jack Dongarra on “Generalizing Random Butterfly Transforms to Arbitrary Matrix Sizes.” Check out the full paper at: https://dl.acm.org/doi/10.1145/3699714

Software Engineering Daily Podcast Features A Conversation with Jack Dongarra

In a recent podcast from Software Engineering Daily, Jack Dongarra reflected on his pioneering career in high-performance computing, highlighting the continuous evolution of supercomputers and the numerical libraries essential for them. The wide-ranging discussion includes topics such as the shift from scalar to parallel architectures, the increasing importance of managing data movement as a bottleneck, and the evolving role of benchmarking beyond LINPACK with the emergence of metrics like HPCG. Dongarra also addressed the impact of AI and lower precision arithmetic, requiring a rethinking of algorithms, and touched upon the future of HPC with the potential augmentation from technologies like quantum computing.

Jack Dongarra Co-Authors Call for Long-Term Vision in High-Performance Computing

Jack Dongarra is among seven leading computer scientists calling for a comprehensive and forward-looking strategy for the future of HPC in the United States. Jack co-authored an article published in the February 2025 issue of Science titled “High-performance computing at a crossroads: Long-term plans and comprehensive vision are needed.” The piece underscores the critical role of HPC in driving scientific discovery and technological advancements while highlighting the growing challenges that threaten its continued progress.

Over the past four decades, high-performance computing (HPC) has enabled considerable advances in scientific discovery and engineering, spurring technological development across the globe. However, with the demand for precision and fidelity of computational models continuing to grow, HPC faces bottlenecks in data handling, algorithm efficiency, and the scalability of new architectures, especially in fields such as chemistry and biology, where molecular simulations increasingly strain hardware and software limits. Governments worldwide are heavily investing in HPC infrastructure to support research, industrial innovation, and national security, each adopting distinct approaches shaped by national interests and regulatory landscapes. Conversely, in the US, there is no long-term plan or comprehensive vision for the next era of HPC advancements, leaving the future trajectory of US HPC and scientific and technological leadership uncertain.

At a time when national priorities in computing and artificial intelligence are rapidly evolving, Dongarra and his colleagues emphasize the urgency of developing a sustainable path forward for HPC. Their work calls on policymakers, researchers, and industry leaders to coordinate efforts in ensuring that the U.S. remains at the forefront of scientific computing.