Introduction - Research
- Information
Introduction
- What is parallel processing?
Parallel processing is running a (sequential) program on multiple
processors
to get the job done in less time. Herefore we parallelise the
program
by assigning parts of the job to the different processors. The
goal
is to have a performance gain, which we call the speedup. The
main
problem is that parallelisation is problem-dependent and cannot yet be
automated, furthermore, speedup is not guaranteed.
- Parallel Processing: scalable performance for free (by
W.
Brissinck):
"A few years ago more or less everybody was sure about one thing:
parallel
processing was the ONLY solution to our more and more demanding
computational
problems. Today, enthusiasm has been replaced by scepticism, as both
the
development cost of parallel software and the maintenance cost of a
parallel
machine has proven to be out of reach for most. Networks of powerful
PCs,
readily available (and maintained !) in most companies and
universities,
running public domain parallel operating systems like PVM or MPI, can
offer
cheap and yet truly scalable performance directly at your desktop. Now
if we would just get this software development problem solved." A
presentation [121K].
- Some Examples
(upcoming)
- Overall scheme of Parallelisation.
- Our "Parallel
System" course provides a good introduction.
Research
Our research focusses on:
- Distributed systems (not shared-address space architectures),
especially
clusters running under LINUX and the MPI message-passing communication
protocol.
- General purpose parallelisation, opposite to instantiated
parallelisation
of algorithms.
- Performance analysis, we are developing a standard analysis and a
tool
to do the analysis automatically.
- Visualisation of the algorithm, the parallelisation, the system
and the
performance.
The problems that have to be solved to get an
ideal
parallelisator.
A Generic solution for
automated parallel processing needs intelligence?
See also the project
topics on parallel processing.
Information
Conferences
Upcoming
Compiler
and Parallel Computing Conferences
International
SuperComputer
Conference
(ISC 2004)
CCGRID-2002, 2nd IEEE
International
Conference on Cluster Computing and the Grid
Journals
Links