Cluster computing performances using virtual processors and mathematical software

TL;DR

This paper investigates the use of Intel Hyper Threading virtual processors to enhance MATLAB-based parallel computations in cluster environments, demonstrating increased concurrency and utility for memory and disk operations.

Contribution

It provides an empirical evaluation of virtual processors in cluster computing, highlighting their benefits and limitations for parallel MATLAB programs.

Findings

Virtual processors double the number of concurrent processes in clusters.

Hyper Threading improves performance for memory and disk-intensive tasks.

The approach has utility but also inherent limits.

Abstract

In this paper I describe some results on the use of virtual processors technology for parallelize some SPMD computational programs in a cluster environment. The tested technology is the INTEL Hyper Threading on real processors, and the programs are MATLAB 6.5 Release 13 scripts for floating points computation. By the use of this technology, I tested that a cluster can run with benefit a number of concurrent processes double the amount of physical processors. The conclusions of the work concern on the utility and limits of the used approach. The main result is that using virtual processors is a good technique for improving parallel programs not only for memory-based computations, but in the case of massive disk-storage operations too.