Workshop on Performance Optimization for High-Level Languages and Libraries
Full-Day Workshop in conjunction with
20th IEEE International Parallel & Distributed Processing Symposium
April 29, 2006
Rodos Palace Resort Hotel, Rhodes Island, Greece
Call for Papers in ASCII
Submit papers through the
EDAS submission system;
Deadline: December 27, 2005
The complexity of software development has led to many efforts aimed
at raising the level of abstraction for the programmer. This includes
both object-oriented general-purpose approaches as well as
domain-specific languages and libraries. While performance
considerations are not paramount for all domains, there are many
domains where high performance is essential. This workshop aims to
bring together researchers from different domains, who have addressed
performance optimization issues in the context of high-level
languages/libraries and problem solving environments, to share their
successes as well as the challenges they face.
Submissions are invited on topics including, but not limited to:
This workshop will be of interest to researchers and graduate students
in several areas such as compilation technology, domain-specific
languages, library development, problem-solving environments, etc.
- program synthesis to facilitate the development of high-performance
programs for specific application domains such as signal processing,
computational chemistry, etc.
- compile/runtime techniques for scalable implementation of
"high-productivity" high-performance languages like Chapel,
- compiler techniques for optimization of high-level mathematical
languages like MATLAB.
- compile/runtime techniques for scalable implementations of parallel
global-address space languages and libraries, such as Co-Array Fortran,
Global Arrays, OpenMP, SHMEM, Titanium, UPC etc.
- development of high-performance implementations of algorithms (e.g. FFT)
for a variety of architectures, by exploiting special structural
properties of the algorithms.
- automatic optimization of library implementations together with the
optimization of programs that use them.
- efficient synthesis of recursive linear algebra codes that exploit
deep memory hierarchies in current computer systems.
- problem solving environments for high-performance computing
- high-performance computing with object-oriented and component-based
The format of this full-day workshop will include invited speakers and
presentations of contributed papers. All submitted papers will be
peer-reviewed by the program committee, with help from other external
|Paper Submission Deadline:
||December 27, 2005
||January 17, 2006
||February 1, 2006 (very strict deadline)
|Hotel cut-off date:
|IPDPS 2006 Dates:
||April 25--29, 2006
|POHLL 2006 Date:
||April 29, 2006
Authors should submit and register their paper by December 27, 2005
midnight Pacific time through the
EDAS submission system.
All submission will be reviewed.
Submissions should be in PDF format (alternatively in level 2
PostScript format or Word) no more than 8 pages long.
Papers must be formatted in
LaTeX and Word style files are available.
Authors should make sure that the submission can be viewed
using ghostscript and will print on standard letter size paper (8.5" x 11").
IEEE CS Press will publish the IPDPS symposium and workshop
abstracts as a printed volume. The complete IPDPS symposium and
workshop proceedings will also be published by IEEE CS Press
as a CD-ROM disk.
Organizers of POHLL 2006
Universitat de Politècnica de Catalunya
Louisiana State University
David Bernholdt, Oak Ridge National Laboratory
Daniel Chavarria Miranda, Pacific Northwest National Laboratory
Jack Dongarra, University of Tennessee
Robert van de Geijn, The University of Texas at Austin
John Gilbert, University of California, Santa Barbara
Jeremy Johnson, Drexel University
Ricky Kendall, Oak Ridge National Laboratory
Calvin Lin, The University of Texas at Austin
John Mellor-Crummey, Rice University
- Jarek Nieplocha, Pacific Northwest National Laboratory
David Padua, University of Illinois at Urbana-Champaign
- Keshav Pingali, Cornell University
Marcus Pueschel, Carnegie Mellon University
J. (Ram) Ramanujam, Louisiana State University
P. (Saday) Sadayappan, The Ohio State University
Rob Schreiber, Hewlett Packard Laboratories
Rich Vuduc, Lawrence Livermore National Laboratory
Trey White, Oak Ridge National Laboratory
Qing Yi, The University of Texas at San Antonio
Last modified: Thu Jan 19 15:00:00 CST 2006