Why the End-Game for Moore’s Law will be driven by a Compiler Renaissance by Prof. Vivek Sarkar, Georgia Institute of Technology

Location: CSA Seminar Hall (Room No. 254, First Floor)

Department of Computer Science and Automation
CSA Distinguished Lecture

Speaker : Prof. Vivek Sarkar, Georgia Institute of Technology

Title : Why the End-Game for Moore’s Law will be driven by a Compiler

Date : Tuesday, June 04, 2019

Time : 11:00 AM

Venue : CSA Seminar Hall (Room No. 254, First Floor)


It is widely recognized that a major disruption is under way in computer hardware as processors strive to extend, and go beyond, the end-game of Moore’s Law. This disruption will include new forms of heterogenous processors, heterogeneous memories, near-memory computation structures, and, in some cases, Non-von Neumann computing elements. Unlike previous generations of hardware  evolution,  these “extreme heterogeneity” systems will have a profound impact on future software. In this talk, we summarize the software challenges for extreme scale computing, with a focus on the  growing role of programming models and compilers in future software stacks. These challenges anticipate a new vision for compilers that goes beyond their traditional role of mapping a specific program to a specific hardware platform, to a world view in which compilers guide both the selection of algorithms in an application and the customization of hardware components to implement those algorithms.

Biography of the speaker

Vivek Sarkar is a Professor in the School of Computer Science, and the Stephen Fleming Chair for Telecommunications in the College of Computing at Georgia Tech. He conducts research in multiple  aspects of parallel computing software including programming languages, compilers, runtime systems, and debuggers for parallel and high performance computer systems. Prof. Sarkar currently leads the Habanero Extreme Scale Software Research Laboratory at Georgia Tech, is PI of the DDARING project in the DARPA Software Defined Hardware program, and is co-director of the Center for Research into Novel Computing Hierarchies (CRNCH). Prof. Sarkar is also the instructor for a 3-course online specialization on Parallel, Concurrent, and Distributed Programming hosted on Coursera.

Prior to joining Georgia Tech in 2017, Prof. Sarkar was the E.D. Butcher Chair in Engineering at Rice University, where he created the Habanero Lab, served as Chair of the Department of Computer Science during 2013–2016, and created an undergraduate course on Fundamentals of Parallel Programming (COMP 322). Prior to joining Rice in 2007, Sarkar was Senior Manager of Programming Technologies at  IBM Research. His research projects at IBM included the X10 programming language, the Jikes Research Virtual Machine for the Java language, the ASTI optimizer used in IBM’s XL Fortran product compilers, and the PTRAN automatic parallelization system. Sarkar became a member of the IBM Academy of Technology in 1995, and was inducted as an ACM Fellow in 2008. He has been serving as a member of the US Department of Energy’s Advanced Scientific Computing Advisory Committee (ASCAC) since 2009, and on CRA’s Board of Directors since 2015.

Host Faculty : Prof. Uday Kumar reddy

Scroll Up