Krishna Nandivada Department of Computer Science and Engineering Areas of interest: Compilers, Program Analysis, Programming Languages, and Multicore Systems

V. Krishna Nandivada is currently an Associate Professor in the department of Computer Science and Engineering at IIT Madras. He is a senior member of ACM and IEEE. He was an Assistant Professor at IIT Madras from October 2011 to July 2015. Before joining IIT Madras, he spent nearly 5.5 years at IBM India Research Lab (Programming Technologies and Software Engineering group). Prior to joining IBM Research, he was associated with Hewlett Packard (2000-2001). He holds a BE degree from REC (now known as NIT) Rourkela, ME degree from IISc Bangalore, and PhD degree from UCLA. His research interests are Compilers, Program Analysis, Programming Languages, and Multicore systems.

How does your group keep HPCE cluster busy?

Our goal is to realize programs that are easy to write and efficient to run. We mainly work towards developing compilers and runtime to run parallel programs efficiently on parallel hardware. We target both shared memory and distributed memory setups. We develop new and efficient techniques to optimize (for both performance and energy) programs written in languages like OpenMP, X10, MPI and Java.

How do you see HPCE landscape in the domain of your research area change over the years?

With the power-wall firmly in place, multi-core systems have become the norm. We have to reinvent/redesign both the application and the system software to be able to take advantage of the changing landscape. More and more cores will be packed in a processor and multi-node-multi-core systems, research in both homogeneous and heterogeneous systems, will remain hot for next many years to come.

What would you suggest to new faculty members and new students in your research area?

The new Moore's law says that parallelism will double in every 1.5 years. The question we should ask ourselves is "Are we ready for that?". For both CS and non-CS folks (working in algorithms/systems and applications) we have to really start thinking in parallel and about parallel execution to be ready for the future. This includes both shared memory and distributed memory systems.