School of Computer Science
Klaus Advanced Computing Building
Georgia Tech
266 Ferst Drive
Atlanta, GA 30332-0765

Voice: (+1) (404) 385 2169
Fax: (+1) (404) 385 2295
E-mail: santosh at cc.gatech.edu

Santosh Pande's primary interest is in investigating static and dynamic compiler optimizations on evolving architectures. His research philosophy involves tackling practical problems which are relevant and important to the current issues in systems research and propose foundational solutions to them for good impact. Currently, his research is focussed on developing compiler optimizations for embedded and configurable systems to improve code size, efficiency and power consumption. His work in this area has resulted in several techniques for efficient compilation given limited memory sizes, limited addressing modes and data paths on embedded processors. He has also developed unified framework for mapping loops on configurable processors combining issues of parallelism, data re-use and reconfiguration overheads for modern processors such as Xilinx 6200 and Virtex series. He has also done work on efficient type inferencing and MOD analysis for OO languages and Java bytecode compilation. In addition to this, in past, he has done work on loop and task parallelism for distributed memory systems. He has published over 40 papers in journals and conferences which include ACM Programming Language Design and Implementation (PLDI), IEEE Real Time Systems Symposium (RTSS) and Journal of Parallel and Distributed Computing (JPDC) and IEEE Transactions on Parallel and Distributed Systems (TPDS). He has also done extensive compiler development and is a part of SUIF collaborative program amongst universities. He has also managed and delivered large scale software projects to the funding agencies such as DARPA. 

He served as a co-guest editor for the special issue of Journal of Parallel and Distributed Systems on `Compilation Techniques for Distributed Memory Systems' published in December '96 and also for the special issue of the Parallel Processing Letters journal on `Challenges in Compiler Optimizations for Scalable Parallel Systems' published in December '97. He has also served on program committees of many conferences. Currently he is co-chairing ACM LCTES '01 to be held in conjunction with PLDI '01. He recently served on the program committee of PLDI '01. He served as an IEEE Distinguished Visitor for the period of 1996-2000. His research is primarily supported by the NSF and DARPA.