PGAS for Large Scale Parallel Computing
Cray Supercomputer Center of Excellence
This talk will cover the advantages of using PGAS with MPI going forward in the
realm of utilizing many 100,000 of processors. While MPI has served the HPC
community extremely well it is having difficulty handling the number of
messages that occur when complex applications are running on 100,000s of
processors. The main difficulty is the message matching required by MPI.
This processing is needed when point to point messages are being used to
overlap computation and communication. Message matching is not required when
using a PGAS language like Co-Array Fortran and UPC. These languages allow the
programmer to "fire and forget" communications and easily overlap communication
with other communication and with computation. A tremendous advantage of these
language extensions are that they can incrementally be used to replace
ineffective MPI. The talk will concentrate on Co-Array Fortran and in
particular in the subset of CAF that has been proposed for incorporating into
the latest 2008 standard. Comparisons and examples will be shown to illustrate
is the director of the Cray Supercomputing Center of Excellence at the
Department of Energy's Oak Ridge National Laboratory (ORNL), the world's most
powerful supercomputer for open (non-classified) scientific research.
Levesque leads a team of engineers providing application and high performance
computing expertise to researchers using ORNL systems. The Center of Excellence
offers scientists and engineers from around the globe access to deep HPC
application performance knowledge, allowing them to focus on their science or
engineering challenge. Levesque also works closely with ORNL staff members to
optimize application performance on ORNL's XT supercomputers.
From 2001 to 2003, Levesque was a senior principal engineer responsible for the
benchmarking initiatives for the Cray XI system, playing a key role in helping
CINECA, Italy's national supercomputer center and the Department of Defense
Modernization Program optimize their applications. Prior to Cray, Levesque was
the director of the Advanced Computer Technology Center at IBM's Watson
Research Center where his team received the Scientific Achievement Award for
contributing more than $200 million in new business sales in 2000.
With more than 35 years experience in high performance computing, Levesque is
a recognized expert in the optimization of FORTRAN programs and parallel vector
system architectures. He has been involved in the Advanced Strategic Computing
Initiative at the US Department of Energy, the National Academy of Sciences,
and is a regular contributor to the Cray User Conference. Levesque has also
contributed to numerous publications on the optimization of programs for
advanced scientific computers including a collection of papers entitled
"Concurrency and Computations" in 2003 and a book entitled
Guidebook to FORTRAN on Supercomputers published in 1989.
Levesque has a Bachelor of Arts and Master of Arts in Mathematics from the
University of New Mexico in Albuquerque, New Mexico.
This talk is sponsored by the National Center for Atmospheric Research Computational & Information Systems Laboratory and will be held in the Main Seminar Room at the Mesa Lab.