Harshvardhan and Adam Fidel, and Dr. Lawrence Rauchwerger and Dr. Nancy Amato were presented with the Best Paper Award at PACT 2014 (Parallel Architectures and Compilation Techniques). Their paper “KLA: A New Algorithmic Paradigm for Parallel Graph Computations” was judged by an independent awards committee based on originality, significance, impact and interest.
PACT is a highly selective, top-ranked conference in the area of high-performance computing and parallel processing, and aims to bring together researchers from architecture, compilers, applications and languages to present and discuss innovative research of common interest. This year was the 23rd for the conference and it was held at the University of Alberta in Edmonton, Canada.
The group's paper presents a new paradigm for parallelizing graph algorithms that unifies and extends the existing level-synchronous and asynchronous approaches. The authors’ approach provides an order of magnitude improvement in performance of parallel graph algorithms, and scalability to beyond 98,000 cores on a Cray XE6 supercomputer.
Harshvardhan is a Ph.D. student in the Parasol Lab in the Department of Computer Science and Engineering with areas of research in parallel/distributed systems, parallel graph algorithms and frameworks working with Amato and Rauchwerger. He graduated magna cum laude from Texas A&M University with a Bachelor of Science degree in computer engineering in 2008. Harshvardhan also won the Association for Computing Machinery Student Research Competition first place medal at PACT.
Adam Fidel is a Ph.D. student in the Parasol Lab with areas of research in parallel programming and high-performance computing with Amato and Rauchwerger. He graduated summa cum laude with a bachelor's degree in computer science from Texas Tech University in 2010.
Amato and Rauchwerger are co-directors of the Parasol Lab.