Evaluation of Sparse LU Factorization and Triangular Solution on Multicore Platforms

The Chip Multiprocessor (CMP) will be the basic building block for computer systems ranging from laptops to supercomputers. New software developments at all levels are needed to fully utilize these systems. In this work, we evaluate performance of different high-performance sparse LU factorization a...

Full description

Saved in:
Bibliographic Details
Published inHigh Performance Computing for Computational Science - VECPAR 2008 pp. 287 - 300
Main Author Li, Xiaoye Sherry
Format Book Chapter
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2008
SeriesLecture Notes in Computer Science
Subjects
Chip Multiprocessor
Hardware Thread
Memory Bandwidth
Multicore Platform
Task Queue
Online AccessGet full text
ISBN3540928588
9783540928584
ISSN0302-9743
1611-3349
DOI10.1007/978-3-540-92859-1_26

Cover

More Information
Summary:The Chip Multiprocessor (CMP) will be the basic building block for computer systems ranging from laptops to supercomputers. New software developments at all levels are needed to fully utilize these systems. In this work, we evaluate performance of different high-performance sparse LU factorization and triangular solution algorithms on several representative multicore machines. We include both pthreads and MPI implementations in this study, and found that the pthreads implementation consistently delivers good performance and a left-looking algorithm is usually superior.
Bibliography:This research was supported by the Director, Office of Science, Office of Advanced Scientific Computing Research, of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231.
ISBN:3540928588
9783540928584
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-540-92859-1_26