Recursive Array Layouts and Fast Parallel Matrix Multiplication

Recursive Array Layouts and Fast Parallel Matrix Multiplication (1999)

Cached

Download Links

[www.cs.duke.edu]
[ftp.cs.unc.edu]
[ftp.cs.unc.edu]

Other Repositories/Bibliography

DBLP

by Siddhartha Chatterjee , Alvin R. Lebeck , Praveen K. Patnala , Mithuna Thottethodi

Venue:	In Proceedings of Eleventh Annual ACM Symposium on Parallel Algorithms and Architectures
Citations:	44 - 3 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Recursive Array Layouts and Fast Parallel Matrix Multiplication	user correction - Legacy Corrections
AUTHOR NAME	Siddhartha Chatterjee	user correction - Legacy Corrections
AUTHOR AFFIL	y	user correction - Legacy Corrections
AUTHOR NAME	Alvin R. Lebeck	user correction - Legacy Corrections
AUTHOR AFFIL	z	user correction - Legacy Corrections
AUTHOR NAME	Praveen K. Patnala	user correction - Legacy Corrections
AUTHOR AFFIL	y	user correction - Legacy Corrections
AUTHOR NAME	Mithuna Thottethodi	user correction - Legacy Corrections
AUTHOR AFFIL	z	user correction - Legacy Corrections
ABSTRACT	Matrix multiplication is an important kernel in linear algebra algorithms, and the performance of both serial and parallel implementations is highly dependent on the memory system behavior. Unfortunately, due to false sharing and cache conflicts, traditional column-major or row-major array layouts incur high variability in memory system performance as matrix size varies. This paper investigates the use of recursive array layouts for improving the performance of parallel recursive matrix multiplication algorithms. We extend previous work by Frens and Wise on recursive matrix multiplication to examine several recursive array layouts and three recursive algorithms: standard matrix multiplication, and the more complex algorithms of Strassen and Winograd. We show that while recursive array layouts significantly outperform traditional layouts (reducing execution times by a factor of 1.2--2.5) for the standard algorithm, they offer little improvement for Strassen's and Winograd's algorithms;...	user correction - Legacy Corrections
YEAR	1999	INFERENCE
VENUE	In Proceedings of Eleventh Annual ACM Symposium on Parallel Algorithms and Architectures	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	222--231	INFERENCE
VOLUME	13	INFERENCE
CITATIONS	41 found	ParsCit 1.0