Communications of the ACM
Keshav Pingali Recognized with ACM-IEEE CS Ken Kennedy Award
Pingali was cited for his contributions to high-performance parallel computing for irregular algorithms such as graph algorithms.
Credit: ACM
ACM (the Association for Computing Machinery) and the IEEE Computer Society have named Keshav Pingali, the W.A. "Tex" Moncrief Chair of Grid and Distributed Computing at the University of Texas at Austin, to receive the 2023 ACM-IEEE CS Ken Kennedy Award, which recognizes groundbreaking achievements in parallel and high-performance computing. Pingali was cited for his contributions to high-performance parallel computing for irregular algorithms such as graph algorithms, as well as for his leadership on the Galois Project, which provides a unifying framework for parallelizing both irregular and regular algorithms.
Pingali has made deep, wide-ranging contributions to many areas of parallel computing, including programming languages, compilers, and runtime systems for multicore, manycore and distributed computers. These include program transformation algorithms for cache optimization, representations for program restructuring, and symbolic analysis techniques for complex numerical algorithms. These contributions have been incorporated into most open-source and commercial compilers.
Pingali's most recent research has focused on foundational parallel programming abstractions and implementations for irregular algorithms, which use complex data structures like sparse matrices and graphs. Traditional techniques for exploiting parallelism in regular dense matrix algorithms fail when applied to irregular algorithms. The Ken Kennedy award recognizes Pingali's "operator formulation of algorithms," which is a programming and execution model that is remarkably simple yet powerful enough to capture patterns of parallelism in both regular and irregular algorithms. The Galois system implements this model, and it is used in diverse areas including real-time intrusion detection in computer networks, parallel tools for asynchronous circuit design, and machine learning on graphs for drug discovery. In addition, Pingali is being recognized for his distinguished mentoring of computer science leaders and students during his career.
From ACM
View Full Article
No entries found