Implementation of dense matrix multiplication on 2D mesh

Author

Samantray, Bhabani Sankar ; Kanhar, Debananda

Author_Institution

Comput. Sci. & Eng., Nat. Inst. of Sci. & Technol., Berhampur, India

fYear

2014

Firstpage

1

Lastpage

5

Abstract

A large number of algorithms have been developed for solving large dimension matrix multiplication through parallel computation. Lots of algorithms have been developed keeping performance matrices such as speed up, efficiency, isoefficiency etc. in linear order. We have compared the performance of simple block checkerboard partitioning algorithm with cannon´s algorithm over 2D mesh topology in HPC Maverick (Rocks 5.4) by taking the mathematical problem matrix multiplication. Till the date not any of the algorithms clearly claimed to be superior then the others. It seems to be advantageous to partition matrix into blocks for multiplying on the 2D Mesh.

Keywords

mathematics computing; matrix multiplication; mesh generation; parallel algorithms; 2D mesh topology; HPC Maverick; Rocks 5.4; block checkerboard partitioning algorithm; dense matrix multiplication; large dimension matrix multiplication; linear order; mathematical problem matrix multiplication; parallel computation; partition matrix; performance matrices; Clustering algorithms; Hypercubes; Libraries; Program processors; Terminology; Tutorials; 2D mesh topology; matrix multiplication algorithms; parallel processing;

fLanguage

English

Publisher

ieee

Conference_Titel

High Performance Computing and Applications (ICHPCA), 2014 International Conference on

Print_ISBN

978-1-4799-5957-0

Type

conf

DOI

10.1109/ICHPCA.2014.7045321

Filename

7045321