[CSEE Talk] Talk: Lee on Structured Parallel Programming, 12:00pm Thur Feb 20, ITE325b

[Tim Finin]

                            Colloquium

            Computer Science and Electrical Engineering
             University of Maryland, Baltimore County

Linguistic and System Support for Structured Parallel Programming

                      Dr. I-Ting Angelina Lee
      Computer Science and Artificial Intelligence Laboratory
               Massachusetts Institute of Technology

       12:00-1:00 Thursday, 20 February 2014, ITE 325b, UMBC

Parallel programming is hard, due to issues such as scheduling
and synchronization.  Most parallel programs today deal with
these issues using low-level system primitives such as pthreads,
locks, and conditional variables.  Although these low-level
primitives are flexible, they, like goto statements, lack
structure and make it difficult for the programmer to reason
locally about the program state.  Just as the use of goto has
been mostly deprecated in favor of structured control constructs,
we can simplify parallel programming by replacing these low-level
primitives with linguistics that enable well-structured parallel
programs.

To enable structured parallel programming is not merely a matter
of linguistic design.  The underlying system must also
efficiently support the linguistics.  In this talk, I will
describe my work on pipeline parallelism, a parallel pattern
commonly used in streaming applications, as an example of
linguistics for structured parallel programming.  I will also
draw examples from my research to demonstrate how novel
mechanisms in operating systems and hardware, not just the
runtime, can help provide efficient support for the linguistics.


I-Ting Angelina Lee is a postdoctoral associate in the Computer
Science and Artificial Intelligence Laboratory at MIT, working
with Prof. Charles E. Leiserson.  Her areas of interest include
designing linguistics for parallel programming, developing
runtime system support for multithreaded software, and building
novel mechanisms in operating systems and hardware to efficiently
support parallel abstractions.  Her work on "memory-mapped
reducers" won best paper at SPAA 2012.  Intel has released an
experimental branch of Cilk Plus that incorporates support for
parallel pipelining based on her work.  She received her
Ph.D. from MIT in 2012 under the supervision of Prof. Charles
E. Leiserson.  She received her Bachelor of Science in Computer
Science from UC San Diego in 2003.


Host: Tim Oates, oates at umbc.edu

     -- more information and directions: http://bit.ly/UMBCtalks --