|
Published Articles >> Table of Contents >> Abstract
18th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD'06)
pp. 159-166
Runtime System Support for Running Applications with Dynamic and Asynchronous Task Parallelism in Software DSM Systems
Rafael Mendes, COPPE-UFRJ, Brazil
Lauro Whately, COPPE-UFRJ, Brazil
Maria Clicia de Castro, IME-UERJ, Brazil
Cristiana Bentes, DESC-UERJ, Brazil
Claudio Luis Amorim, COPPE-UFRJ, Brazil
Full Article Text:
 
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/SBAC-PAD.2006.25
Send link to a friend
| Abstract |
|
State-of-the-art software distributed shared-memory
systems (SDSMs) provide a cost-effective solution to
run single-program-multiple-data (SPMD) applications on
clusters of distributed memory computers. However,
SDSMs are unsuitable for running applications with dynamic,
highly asynchronous task parallelism (ATP), such
as graphics, simulators, and decision support systems. In
ATP-based applications, the execution of tasks depends not
only on the input data but also on the variable amount of
data that each task produces at runtime, which generates
high load imbalance and communication traffic that degrades
performance of SDSM systems drastically. In this
work, we propose a new load balancing (LB) mechanism
to enable SDSM systems to support dynamic task scheduling
as required by ATP applications. To evaluate the benefits
of our LB mechanism, we developed Clik a new multithreaded
SDSM system with automatic load balancing. Our
preliminary performance results of Clik running on a 16-
node Linux SMP cluster for five ATP applications showed
that Clik attained significant speedups. For four of our five
applications, the speedups varied from 7.2 up to 13.8 on 16
processors.
|
 Additional Information
|
Citation:
Rafael Mendes, Lauro Whately, Maria Clicia de Castro, Cristiana Bentes, Claudio Luis Amorim,
"Runtime System Support for Running Applications with Dynamic and Asynchronous Task Parallelism in Software DSM Systems,"
sbac-pad,
pp. 159-166,
18th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD'06),
2006
|
|
