SCHEDULE: NOV 16-21, 2014

When viewing the Technical Program schedule, on the far righthand side is a column labeled "PLANNER." Use this planner to build your own schedule. Once you select an event and want to add it to your personal schedule, just click on the calendar icon of your choice (outlook calendar, ical calendar or google calendar) and that event will be stored there. As you select events in this manner, you will have your own schedule to guide you through the week.

What the $#@! Is Parallelism? (And Why Should Anyone Care?)

SESSION: Cray/Fernbach/Kennedy Award Recipients Talks

EVENT TYPE: Award Presentations & Award Talks, Keynote & Plenary Talks

TIME: 9:30AM - 10:00AM

SESSION CHAIR: Barbara Chapman

Presenter(s):Charles E. Leiserson

ROOM:New Orleans Theater

ABSTRACT:

Many people bandy about the notion of “parallelism,” saying such things as, “This optimization makes my application more parallel,” with only a hazy intuition about what they’re actually saying. Others cite Amdahl’s Law, which provides bounds on speedup due to parallelism, but which does not actually quantify parallelism. In this talk, I’ll review a general and precise quantification of parallelism provided by theoretical computer science, which every computer scientist and parallel programmer should know. I’ll also discuss why the impending end of Moore’s Law — the economic and technological trend that the number of transistors per semiconductor chip doubles every two years — will bring new poignancy to such theoretical concepts.

Charles E. Leiserson received a B.S. from Yale University in 1975 and a Ph.D. from Carnegie Mellon University in 1981. He joined the MIT faculty in 1981, where he is now the Edwin Sibley Webster Professor of Electrical Engineering and Computer Science in the MIT Department of Electrical Engineering and Computer Science and head of the Supertech research group in the MIT Computer Science and Artificial Intelligence Laboratory.

Professor Leiserson’s research centers on the theory of parallel computing, especially as it relates to engineering reality. His Ph.D. thesis Area-Efficient VLSI Computation won the first ACM Doctoral Dissertation Award, as well as the Fannie and John Hertz Foundation’s Doctoral Thesis Award. He coauthored the first paper on systolic architectures. He invented the retiming method of digital-circuit optimization and developed the algorithmic theory behind it. On leave from MIT at Thinking Machines Corporation, he designed and led the implementation of the network architecture for the Connection Machine Model CM-5 Supercomputer, which incorporated the fat-tree interconnection network he developed at MIT. Fat-trees are now the preferred interconnect strategy for Infiniband technology. He introduced the notion of cache-oblivious algorithms, which exploit the memory hierarchy near optimally while containing no tuning parameters for cache size or cache-line length. He developed the Cilk multithreaded programming technology, which featured the first provably efficient work-stealing scheduler. He led the development of several Cilk-based parallel chess-playing programs, winning numerous prizes in international competition. On leave from MIT as Director of System Architecture at Akamai Technologies, he led the engineering team that developed a worldwide content-distribution network numbering over 20,000 servers. He founded Cilk Arts, Inc., which developed the Cilk++ multicore concurrency platform and was acquired by Intel Corporation in 2009. Intel now embeds this technology in their Cilk Plus multithreaded programming environment.

Professor Leiserson has made numerous contributes to computer-science education. He is perhaps best known as coauthor of the textbook, Introduction to Algorithms (The MIT Press), which was named “Best 1990 Professional and Scholarly Book in Computer Science and Data Processing” by the Association of American Publishers. Currently in its third edition, it is the leading textbook on computer algorithms, having sold over 500,000 copies, and is one of the most cited publications in all of computer science. He developed the MIT undergraduate courses on algorithms and on discrete mathematics for computer science. He was for many years the head of the computer-science program for the Singapore-MIT Alliance, one of the first distance-education collaborations, which produced popular video lectures of his undergraduate course on algorithms and are viewable through MIT OpenCourseWare. He developed MIT’s undergraduate class on software performance engineering, which teaches parallel programming not as an end in itself, but as only one of several important techniques for writing fast code. His annual workshop on Leadership Skills for Engineering and Science Faculty has educated hundreds of faculty at MIT and around the world in the human issues involved in leading technical teams in academia. He was the founding Workshop Chair for the MIT Undergraduate Practice Opportunities Program (UPOP), which teaches MIT Engineering sophomores how leadership skills can leverage their technical skills in professional environments. He is a Margaret MacVicar Faculty Fellow at MIT, the highest recognition at MIT for undergraduate teaching. He is an ACM Fellow, an AAAS Fellow, a senior member of IEEE and SIAM, and recipient of the ACM Paris Kanellakis Theory and Practice Award and the IEEE Computer Society Taylor L. Booth Education Award. He has graduated over two dozen doctoral students and supervised more than 60 master’s and bachelor’s theses.

Chair/Presenter Details:

Barbara Chapman (Chair) - University of Houston

Charles E. Leiserson - MIT

  Click here to download .ics calendar file

  Click here to download .vcs calendar file

  Click here to add event to your Google Calendar