Year: 2013
Type: preprint
Abstract: We present FooPar, an extension for highly efficient Parallel Computing in the multi-paradigm programming language Scala. Scala offers concise and clean syntax and integrates functional programming features. Our framework FooPar combines these features with parallel computing techniques. FooPar is designed modular and supports easy access to different communication backends for distributed memory architectures as well as high performance math libraries. In this article we use it to parallelize matrix matrix multiplication and show its scalability by a isoefficiency analysis. In addition, results based on a empirical analysis on two supercomputers are given. We achieve close-to-optimal performance wrt. theoretical peak performance. Based on this result we conclude that FooPar allows to fully access Scala's design features without suffering from performance drops when compared to implementations purely based on C and MPI.
Source: arXiv (Cornell University)
Authors: Hargreaves, Felix P., Merkle, Daniel
Institution: University of Southern Denmark
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2952283623