Ordering sparse matrices for cache-based systems

Conference · Thu Jan 11 00:00:00 EST 2001

OSTI ID:787125

Biswas, Rupak; Oliker, Leonid

The Conjugate Gradient (CG) algorithm is the oldest and best-known Krylov subspace method used to solve sparse linear systems. Most of the coating-point operations within each CG iteration is spent performing sparse matrix-vector multiplication (SPMV). We examine how various ordering and partitioning strategies affect the performance of CG and SPMV when different programming paradigms are used on current commercial cache-based computers. However, a multithreaded implementation on the cacheless Cray MTA demonstrates high efficiency and scalability without any special ordering or partitioning.

• Research Organization: Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
• Sponsoring Organization: USDOE Director, Office of Science. Office of Advanced Scientific Computing Research. Mathematical, Information, and Computational Sciences Division (US)
• DOE Contract Number: AC03-76SF00098
• OSTI ID: 787125
• Report Number(s): LBNL-47805; R&D Project: 618110; TRN: AH200134%%182
• Resource Relation: Conference: Tenth SIAM Conference on Parallel Processing for Scientific Computing, Portmouth, VA (US), 03/12/2001--03/14/2001; Other Information: PBD: 11 Jan 2001
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
ALGORITHMS
COMPUTERS
EFFICIENCY
IMPLEMENTATION
MATRICES
PARALLEL PROCESSING
PERFORMANCE
PROGRAMMING