ABOUT THIS AWARD

The ACM - IEEE CS Ken Kennedy Award is awarded annually and recognizes substantial contributions to programmability and productivity in computing and substantial community service or mentoring contributions. The award includes a $5,000 honorarium. The recipient will give a presentation, normally technical, at the SC conference at which it is announced, or at an ACM or IEEE conference of the winner's choosing during the year following the announcement.

Jack Dongarra Named for influential contributions to mathematical software

Jack Dongarra of the University of Tennessee is the recipient of the ACM-IEEE Computer Society Ken Kennedy Award for his leadership in designing and promoting standards for mathematical software used to solve numerical problems common to high performance computing (HPC).  His work has led to the development of major software libraries of algorithms and methods that boost performance and portability in HPC environments, which rely on supercomputers and parallel processing techniques for solving complex computational problems.  Dongarra, the Distinguished University Professor at the University of Tennessee, is the founder and director of the Innovative Computing Laboratory at the University, and holds positions at Oak Ridge National Laboratory and the University of Manchester. 

ACM President Vint Cerf cited Dongarra’s role in anticipating the staggering challenges facing the HPC world.  “Jack saw the need to keep pace with the evolution in HPC hardware and software in a world that demands higher speeds and performance levels.  His innovations have contributed immensely to the steep growth of high performance computing and its ability to illuminate a wide range of scientific questions facing our society.”

IEEE Computer Society President David Alan Grier said Dongarra’s work remains authoritative. “I’m so pleased to see this award go to Jack Dongarra because he did such foundational work in scientific computing. That work was important in my early career and it remains an influential body of work.”

Dongarra is a leader in research on implementing linear algebra algorithms for high performance computing architecture that has defined the mathematical software field. Many supercomputer vendors have adopted these software packages as the basis of their own numerical libraries.  The software involves the use of memory hierarchies, performance tuning parameters, and other techniques to achieve performance and portability.

He has also been a major force in developing standards for mathematical software that are widely accepted in computer and computational science for evaluating the performance of supercomputers.  They include LINPACK and LAPACK, software packages used since the 1970s for solving systems of linear equations.  In 1993, he formed the Top500 table which used his LINPACK benchmark to show the 500 most powerful commercially available computer systems. These benchmarks enable users to exploit their existing computer hardware to solve much larger problems at lower additional cost.