Sparse matrix vector multiplication techniques on the IBM 3090 VF

Parallel Computing

Volumn 17, Issue 12, 1991, Pages 1409-1424

  Peters, Alexander ^a  

^a IBM   (Germany)

Author keywords

IBM 3090 VF; Matrix vector multiplications; sparse matrices; sparse storage techniques; timing results

Indexed keywords

COMPUTER PROGRAMMING LANGUAGES - FORTRAN; COMPUTER SYSTEMS PROGRAMMING - MULTIPROCESSING PROGRAMS; MATHEMATICAL TECHNIQUES - MATRIX ALGEBRA;

MATRIX VECTOR MULTIPLICATION; PARALLEL ALGORITHMS; SPARSE MATRICES;

COMPUTER PROGRAMMING;

EID: 0026381244     PISSN: 01678191     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-8191(05)80007-9     Document Type: Article

References (17)

1. Sparse matrix test problems
2. A new storage scheme for an efficient implementation of the sparse matrix-vector product
3. The ITPACK project: Past, Present and Future
4. Programming in VS Fortran on the IBM 3090 for maximum vector performance
5. Matrix multiplication by diagonals on a vector/parallel processor
6. Parallel solution of linear systems with striped sparse matrices
7. Data structures to vectorize CG algorithms for general sparsity patterns
8. A graphic tool to plot the structure of large sparse matrices
9. Vectorized Implementation of Some MCG Codes for the FE Solution of Large Groundwater Flow Problems
10. Sparse matrix-vector product and storage representations on the IBM 3090 with Vector Facility
11. Krylov subspace methods on supercomputers
12. A vectorizing Fortran compiler
13. The IBM 3090 System: An overview
14. Architectural approach to the IBM 3090 E vector performance