Boost Interest :
Subject: [Boost-interest] CfP: Parallel/High-Performance Object-Oriented Scientific Computing (POOSC'10)
From: Kei Davis (kei_at_[hidden])
Date: 2010-07-12 20:01:33
9th Workshop on
PARALLEL/HIGH-PERFORMANCE OBJECT-ORIENTED SCIENTIFIC COMPUTING (POOSC'10)
October 18, 2010
Systems, Programming, Languages, and Applications: Software for Humanity
October 17-21, 2010, Renoe-Tahoe Nevada, USA
While object-oriented programming has been embraced in industry, particularly in
the form of C++, Java, and Python, its acceptance by the parallel scientific
programming community has been relatively slow. Nonetheless, various factors
practically dictate the use of language features that provide higher level
abstractions than do C or older FORTRAN standards. These include increasingly
complex physics models, numerical algorithms, and hardware, e.g. deep memory
hierarchies, ever-increasing numbers of processors, the advent of multi-core
processors; more recently the use of heterogeneous architectures using the IBM
Cell/BE or GP-GPUs, and soon the experimentation with many-core processors.
This workshop seeks to bring together researchers and practitioners in this
growing and evolving field to `compare notes' on their work. The emphasis is on
how object-oriented programming can benefit scientific computing specifically:
new or novel frameworks, approaches, techniques, or idioms that use object
orientation. Multi-paradigmatic approaches are also of definite interest.
Presentations of work in progress are welcome.
Specific areas of interest include, but are not limited to:
- alternatives or extensions, including multi-paradigmatic
approaches, to mainstream object-oriented languages (e.g. C++, Java, Python);
- performance issues and their realized or proposed resolution;
- issues specific to handling or abstracting parallelism, including the
handling or abstraction of heterogeneous/multicore/accelerated
- higher level languages (e.g. domain specific languages) or their embedding
into OO languages to support parallelism or specific tasks in scientific
- frameworks and tools for object-oriented scientific computing;
- proposed or realized solutions to problems hindering acceptance of
object-oriented scientific computing;
- grand visions (of relevance).
The workshop will consist of a sequences of presentations each
followed by a discussion session. The workshop will conclude with an
overall discussion. We expect the majority of the participants to
NOTE: Full papers are not required for acceptance/presentation, but they
are strongly encouraged.
For authors of accepted presentations who require justification for travel the
organizers can provide official letters of invitation.
Full papers accepted to the workshop will be published as a workshop proceedings
in the ACM Digital Library. (Too be determined: SPLASH is currently in
negotiations with the ACM.)
Prospective authors are invited to submit abstracts, papers, or presentations
(slides) in ASCII, PDF, MS Word, postscript, or PowerPoint. Submitted materials
will be distributed at the workshop. Submission and email correspondence to
-Aug 9, 2010: Initial submissions due;
-Aug 30, 2010: Author notification;
-mid-Sept, 2010: SPLASH early registration deadline;
-Oct 4, 2010: Final versions of materials to be distributed due;
-Oct 18, 2010: Workshop.
This workshop is a joint organization by Los Alamos National Laboratory, USA;
and the Technical University of Regensburg, Germany.