Jack Dongarra, co-chair of the recently-released Department of Energy report on exascale computing, emphasizes that research into high-end mathematics is needed to keep the United States competent in cutting edge computing research.
Exascale computing (capable of one quintillion floating point operations per second) will enable us to solve problems in ways that are not feasible today and will result in significant scientific breakthroughs,” Dongarra said to The University of Tennessee’s Tennessee Today. “However, the transition to exascale poses numerous scientific and technological challenges.”
These challenges are the topic of the report released this month, which outlines approaches to circumvent these issues by analyzing current pitfalls in thinking about applied mathematics for exascale computing, identifying algorithmic approaches and mathematics to address emerging questions at the exascale level by integrating applied math sub-disciplines, and fostering conversations between application scientists and computer scientists.
Dongarra, a professor in the department of electrical engineering and computer science at the University of Tennessee, is a National Academy of Engineering member and a SIAM Fellow. Read his conversation with Tennessee Today here.