Decades after its origins and its study in academia, parallel computing is
finally becoming pervasive. Today's PCs have multiple cores, and some
predict 1000-core machines in the near future. Google, Yahoo and others run
MapReduce or Hadoop on thousands of machines to answer search queries, among
other things. D. E. Shaw Research is building a massively parallel machine
to simulate molecular dynamics. Climate scientists predict the evolution of
the earth's climate on parallel machines. Amazon's EC^2 enables users to run
jobs on a "cloud" of PCs.
The evolution of parallel computing from primarily an academic subject in
the '80s to its realization today is an exciting development. This DIMACS
workshop will bring together some of the leading researchers and
practitioners involved in parallel computing to describe their work.
Attendees will discuss, for example:
* how parallel computing in its various forms is used today;
* what new uses and programming abstractions will arise by 2020;
* what parallel computers will look like in 2020; and
* how to model parallelism theoretically.
Those wishing to give a contributed talk must submit a one-page description
of their work, with additional material (such as a paper) optional, to
howard@research.att.com by February 9, 2011. Should there be an excess of
submissions, the organizers will select the contributed talks according to
the summaries submitted.
Posts
