第69回プログラミング研究会招待講演

The Impact of Multicore Architectures on Software: Disaster or Opportunity?

Michael Hind (IBM Research)

Abstract:
Mainstream computer venders have announced two dramatic changes in
their future architectures.

First, the clock speed and the amount of cache memory per processor
will dramatically change. Namely, the increase in clock
frequency we've experienced over the past decades will cease to occur,
and in some cases processor speeds will decrease.  Also, the relative,
amount of cache memory for a processor will decrease.
Second, there will be exponentially increasing number of processor
cores on a chip.

These changes present two unprecedented challenges to the software
stack: 1) how does the software deal with the loss of single threaded,
performance and cache memory, and 2) how does the software utilize the
additional capabilities provided by multiple cores on a chip?
In this talk, I will argue why these challenges present great
opportunities for software optimization and suggest some approaches to
address these fundamental problems.

Bio:
Michael Hind received his Ph.D. from New York University in 1991. From
1992-1998, Michael was an assistant and associate professor of
computer science at the State University of New York at New Paltz. In
1998, Michael became a Research Staff Member in the Software
Technology Department at the IBM T.J. Watson Research Center, working
on the Jalapeno project, the project that produced the open source
Jikes RVM. In 2000, he became the manager of the Dynamic Optimization
Group at IBM Research, and in 2007, became Senior Manager of the
Programming Technologies Department at IBM Research. Michael is an
associate editor of ACM TACO, has served on over a dozen program
committees, given talks at top universities and conferences, and
co-authored over 40 publications. His research interests include
adaptive optimization, program analysis, and software optimizations
for multicore processors.