Functional Programming Approaches for Virtual Shared Memory and Distributed Memory Clusters

Abstract

The enhancements in processor technologies have given birth to multi-threaded, multi-core and multi-processor computer systems (clusters). To exploit all the par- allelism available in these current and future computer systems, programmers' must invent new parallel programming approaches in the software they develop. Though conventional programming models exist for parallel programming neither of them address the emerging power processor technologies. Each programming model shows di®erent performance based on the context they used. The thesis evaluates how functional programming can be used with common distributed memory and shared memory languages to exploit the scalability, hetero- geneity and °exibility of computer clusters in solving the recursive Strassen's matrix multiplication problem. The experiments show that the selected functional language Erlang is more ef- ¯cient than virtual shared memory approach and can be made more scalable than distributed memory approaches by incorporating with OpenMP.