Remora : implementing adaptive parallelism on a heterogeneous cluster of networked workstations

Rehmet, Geoffrey Michael (1995) Remora : implementing adaptive parallelism on a heterogeneous cluster of networked workstations. Masters thesis, Rhodes University.

[img] Text
REHMET-MSC-TR95-51.pdf

11Mb

Abstract

Computers connected to a local area network are often only fully utilized for short periods of time. In fact, most workstations are not used at all for a significant portion of the day. The combined "idle time" of the workstations on a network constitutes a significant computing resource, which is generally wasted. If harnessed properly, such a resource could constitute a cheap alternative to expensive high-performance computers. Adaptive parallelism refers to the parallel execution of a computation on a dynamically changing set of processors. This thesis investigates the viability of this approach as a vehicle to harness the "idle cycles" available on a heterogeneous cluster of networked computers. A system, called Remora, which implements adaptive parallelism via the Linda programming paradigm, is presented. Experiments, performed using Remora, show that adaptive parallelism provides an efficient vehicle for using idle processor cycles, without having an adverse effect on the tasks which constitute the normal workload of the computers being used.

Item Type:Thesis (Masters)
Uncontrolled Keywords:LINDA, Computer networks, Remora
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Faculty > Faculty of Science > Computer Science
Supervisors:Clayton, Peter
ID Code:3983
Deposited By: Mrs Carol Perold
Deposited On:06 Nov 2012 13:30
Last Modified:06 Nov 2012 13:30
0 full-text download(s) since 06 Nov 2012 13:30
0 full-text download(s) in the past 12 months
More statistics...

Repository Staff Only: item control page