4/7/2011
Written by
University of Illinois computer science professor Laxmikant (Sanjay) Kale was elevated to fellow of the IEEE. This honor, the highest in the IEEE, is given to IEEE Senior Members with “an extraordinary record of accomplishments in any of the IEEE fields of interest.”
Kale was named an IEEE Fellow for his development of parallel programming techniques. Kale’s research interest is in the design and implementation of pragmatic tools that facilitate development of efficient, scalable parallel applications.
With his research team in the Parallel Programming Laboratory, Kale aims to help developers of complex irregular and dynamic applications to quickly develop applications that can perform and scale well on supercomputers with hundreds of thousands of processors.
One of the core technologies developed by Kale and PPL is the concept of processor virtualization. Using processor virtualization, the programmer divides the computation into a large number of entities, which are mapped to the available processors by an intelligent runtime system.
“This separation of concerns between programmers and the system is key to attaining our goals in both computing performance and programmer productivity,” says Kale.
Kale is the creator of the CHARM++, a C++-based parallel library, and AMPI, an adaptive MPI implementation that supports dynamic load balancing and multithreading for MPI applications. Charm++ is a machine independent parallel programming system. Programs written using this system will run unchanged on MIMD machines with or without a shared memory. It provides high-level mechanisms and strategies to facilitate the task of developing even highly complex parallel applications. Using AMPI, with minimal changes, MPI applications can benefit from the advantages of the Charm++ runtime such as processor virtualization, adaptive overlap and load balancing.
The tools are supported by PPL’s research on intelligent runtime systems, including load balancing and communication optimizations. Kale and his team are developing performance visualization and analysis tools that can provide intuitive and specific feedback for improving performance. In addition, Kale is developing frameworks that automate domain-specific parallelization techniques, and producing reusable libraries for parallel algorithms.
Kale conducts his research in the context of real applications. His collaborative research projects include biomolecular simulation, rocket simulation, cosmology, quantum chemistry, space-time meshes, and structural dynamics.
To be considered for IEEE Fellow, the nominee must have contributed significantly to the advancement or application of engineering, science, and technology; hold IEEE Senior Member or IEEE Life Senior Member grade at the time of the nomination; and have been a good standing member for at least 5 years, according to the IEEE Web site. In addition, the total number of fellows selected cannot exceed one-tenth of one percent of the total voting institute membership.