Data and workload distribution in a multithreaded architecture
Document Type
Article
Publication Date
2-1-1997
Abstract
Matching data distribution to workload distribution is important in improving the performance of distributed-memory multiprocessors. While data and workload distribution can be tailored to fit a particular problem to a particular distributed-memory architecture, it is often difficult to do so for various reasons including complexity of address computation, runtime data movement, and irregular resource usage. This report presents our study on multithreading for distributed-memory multiprocessors. Specifically, we investigate the effects of multithreading ondatadistribution andworkloaddistribution withvariable, thread granularity. Various types of workload distribution strategies are defined along with thread granularity. Several types of data distribution strategies are investigated. These include row-wise cyclic,k-way partial-row cyclic, and blocked distribution. To investigate the performance of multithreading, two problems are selected: highly sequential Gaussian elimination with partial pivoting and highly parallel matrix multiplication. Execution results on the 80-processor EM-4 distributed-memory multiprocessor indicate that multithreading can off set the loss due to the mismatch between data distribution and workload distribution even for sequential and irregular problems while giving high absolute performance. © 1997 Academic Press.
Identifier
0031068502 (Scopus)
Publication Title
Journal of Parallel and Distributed Computing
External Full Text Location
https://doi.org/10.1006/jpdc.1996.1262
ISSN
07437315
First Page
256
Last Page
264
Issue
2
Volume
40
Grant
JOVE NAG8 1114-2
Fund Ref
National Aeronautics and Space Administration
Recommended Citation
Sohn, Andrew; Sato, Mitsuhisa; Yoo, Namhoon; and Gaudiot, Jean Luc, "Data and workload distribution in a multithreaded architecture" (1997). Faculty Publications. 16742.
https://digitalcommons.njit.edu/fac_pubs/16742
