|
Dr.
Issam Damaj,
Assistant Professor of Electrical and Computer
Engineering, with his collaborators from Lebanese
American University (Dr. Ramzi Harati and Miss
Safaa Kasbah), published a paper, under the affiliation
of Dhofar University, in the SIAM Conference
on Computational Science and Engineering (CS&E),
Costa Mesa, California, USA, 19 – 23 February,
2007. The paper is entitled “Accurate
High-Performance Multigrid Solvers in Reconfigurable
Hardware”.
The published paper comes as an outcome of the
collaborative research project on “High-Speed Hardware Systems for Computationally Intensive
Applications”. This
project has been running since 2004 with collaborators
from the Lebanese American University and Hariri
Canadian University in Lebanon. Technically, this
paper presents an accurate high-speed hardware
implementation of the V-cycle Multi-grid method
for finding the solution of a 2D-Poisson equation.
Various hardware design, analysis and testing tools
have been used including Handel-C a modern high-level
hardware compiler.
The targeted CS&E conference draws the attention
to the tremendous range of major computational
efforts on large problems in science and engineering,
to promote the interdisciplinary culture required
to meet large-scale challenges, and to encourage
the training of the next generation of computational
scientists. The motivation behind holding this
international meeting is that Computational Science
and Engineering (CS&E) is now widely accepted,
along with theory and experiment, as a crucial
third mode of scientific investigation and engineering
design. Aerospace, automotive, biological, chemical,
semiconductor, and other industrial sectors now
rely on simulation for technical decision support.
For government agencies also, CS&E has become
an essential support for decisions on resources,
transportation, and defense. Finally, in many new
areas such as medicine, the life sciences, management
and marketing (e.g. data- and stream mining), and
finance techniques and algorithms from CS&E
are of growing importance. CS&E is by nature
interdisciplinary. It grows out of physical applications
and it depends on computer architecture, but at
its heart are powerful algorithms. Much of CS&E
has involved analysis, but the future surely includes
optimization and design, especially in the presence
of uncertainty. Another mathematical frontier is
the assimilation of very large data sets through
such techniques as adaptive multi-resolution, automated
feature search, and low-dimensional parameterization.
The conference was funded by SIAM and supported
by the National Science Foundation in the USA.
|
