5 minute read
Trailblazing Work
Turing Award Presented to Illinois Tech Alumnus
Jack Dongarra (M.S. CS ’73) jumped onto a Zoom meeting on March 1, 2022, after a colleague, Rodney Brooks, asked him to talk about Association for Computing Machinery business. When he logged on, it looked like he had walked into an ambush.
“There were nine other people on the Zoom, and I recognized many of them as leaders in the [computer science] field,” Dongarra says. “Rodney said they were members of the ACM Awards Committee and wanted to tell me that I was chosen as this year’s A. M. Turing Award recipient.”
The Turing Award often is referred to as the Nobel Prize of computing, and is the most prestigious award bestowed by ACM for major contributions of lasting importance to computing. ACM cited Dongarra’s pioneering contributions to numerical algorithms and libraries, which have enabled high-performance computational software to keep pace with more than 40 years of hardware improvements. The award also includes a $1 million prize funded by Google.
“It was quite a shock,” Dongarra says. “I know a number of previous winners. I’ve read their books. I used their theorems. My head is still spinning knowing that I’ve joined that group.”
Dongarra is the first to win the Turing Award for the field of high-performance computing. He says the award not only is a great personal achievement, but also is a great recognition by ACM of the field’s impact in computer science.
“HPC is a relatively new area of computer science,” he says. “Theory gets a lot of the recognition. To recognize that HPC is important to computer science is quite an honor.”
However, ACM could not ignore that Dongarra played a central part in directing the successful trajectory of the high-performance computing field.
“His trailblazing work stretches back to 1979, and he remains one of the foremost and actively engaged leaders in the HPC community. His career certainly exemplifies the Turing Award’s recognition of ‘major contributions of lasting importance,’” ACM President Gabriele Kotsis said in ACM’s announcement of the award.
“This award recognizes another Illinois Tech alum that has changed the face of computing,” says Lance Fortnow, dean of Illinois Institute of Technology’s College of Computing. “Building on the computer science and mathematical ideas he learned at Illinois Tech, Jack Dongarra led the development of LINPACK, a software package that helped supercomputers solve complex mathematical problems and set the stage for powering modern machine learning.”
Dongarra was born and raised in Chicago. When he enrolled at Chicago State University as an undergraduate student, he expected to graduate as a high school math or science teacher. It was during his last semester at Chicago State when he applied for a research position at Argonne National Laboratory. At Argonne he met researchers from Illinois Tech, who encouraged him to pursue a master’s degree in computer science at the university while he continued to conduct research at Argonne.
“Illinois Tech has a good, balanced education in computing,” he says. “The education I got there allowed me to work at national laboratories and universities, and do great things.”
Dongarra worked full-time at Argonne from 1980 until 1989, when he left to teach at University of Tennessee Knoxville and conduct research at Oak Ridge National Laboratory. Dongarra says that he never considered the accolades that could accompany his pioneering work, especially the Turing Award.
“It never entered my mind,” he says. “It’s not something you can arrange, or even whisper to your friends.”
Dongarra, who currently sits on the Illinois Tech Computer Science Board of Advisors, specializes in linear algebra, a form of mathematics that underpins many of the most ambitious tasks in computer science, including a critical part of the modeling of many natural systems in physics, astrophysics, climatology, chemistry and biology, human systems in economics, psychology, social science, and engineering. Early in his career, he worked with researchers
at several American universities to develop LINPACK, an open source set of algorithms that help scientists across a wide range of disciplines to do their work. They benefit a wide range of users through their incorporation into software, including MATLAB, Maple, Wolfram Mathematica, GNU Octave, the R programming language, and SciPy, among others—the building blocks of engineering and scientific discoveries.
In the 1990s Dongarra and his colleagues used the LINPACK benchmark to measure the progress of supercomputers, and today there is fierce international competition to be included in the TOP500 list, which is published twice a year and lists the fastest computers in the world. Dongarra and his fellow researchers currently work with the fastest computer in the world, called Frontier, an HPE-built system at Oak Ridge.
Dongarra is a member of the National Academy of Engineering and a fellow of several organizations, including the American Association for the Advancement of Science, the Institute for Electrical and Electronics Engineers (IEEE), the Society for Industrial and Applied Mathematics (SIAM), and ACM. He holds appointments at Tennessee, Oak Ridge, and the University of Manchester. He was awarded IEEE’s Sid Fernbach Award in 2004; was the recipient of the first IEEE Medal of Excellence in Scalable Computing in 2008; was the first recipient of the Society for Industrial and Applied Mathematics Special Interest Group on Supercomputing’s award for career achievement in 2010; was the recipient of the IEEE Charles Babbage Award in 2011; and received the ACM/IEEE Ken Kennedy Award in 2013. In 2019 Dongarra received the SIAM/ACM Prize in Computational Science and Engineering, and in 2020 he received the IEEE Computer Pioneer Award for leadership in the area of high-performance mathematical software.
Currently, Dongarra is professor emeritus of computer science at Tennessee and continues to conduct research in linear algebraic algorithms and software development in high-performance computing. He is participating in a $4 billion, seven-year U.S. Department of Energy research project in exascale computing, which includes more than 200 people conducting research for the Department of Energy. ●