For his project "Communication-Optimal Parallel Algorithms for Solving Physical Equations."Scroll Up
Edgar Solomonik is a PhD candidate working on parallel numerical algorithms at University of California, Berkeley. Together with his advisor, Prof. James Demmel,he works on developing algorithms that avoid communication traffic and scale on high-performance parallel computers. As a graduate student, Edgar developed 2.5D algorithms for numerical linear algebra, which asymptotically lower communication at the cost of limited data replication. Concurrently, he engineered a distributed-memory tensor contraction library which provides key numerical abstractions to the field of high-accuracy electronic structure calculations.