On the Usage of 16 Bit Indices in Recursively Stored Sparse Matrices

Author

Martone, Michele ; Filippone, Salvatore ; Paprzycki, Marcin ; Tucci, Salvatore

Author_Institution

Univ. of Rome Tor Vergata, Rome, Italy

fYear

2010

fDate

23-26 Sept. 2010

Firstpage

57

Lastpage

64

Abstract

In our earlier work, we have investigated the feasibility of utilization of recursive partitioning in basic (BLAS oriented) sparse matrix computations, on multi-core cache-based computers. Following encouraging experimental results obtained for SpMV and SpSV operations, here we proceed to tune the storage format. To limit the memory bandwidth overhead we introduce usage of shorter (16 bit) indices in leaf sub matrices (at the end of the recursion). Experimental results obtained for the proposed approach on 8-core machines illustrate speed improvements, when performing sparse matrix-vector multiplication.

Keywords

cache storage; multiprocessing systems; sparse matrices; memory bandwidth; multicore cache based computers; recursive partitioning utilization; sparse matrix vector multiplication; storage format; Artificial neural networks; Bandwidth; Indexing; Patents; Sparse matrices; Symmetric matrices; blas; multicore; recursive; recursive CSR; sparse matrix; spmv;

fLanguage

English

Publisher

ieee

Conference_Titel

Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), 2010 12th International Symposium on

Conference_Location

Timisoara

Print_ISBN

978-1-4244-9816-1

Type

conf

DOI

10.1109/SYNASC.2010.77

Filename

5715269