Insulating the scientific programmer from perilous parallel architecture

Authors:
Sean Chester;Celina Gibbs;Fil Rossi;Andrew Brownsword;Poman So;Aaron Gulliver
Affiliations:
University of Victoria, Victoria, BC, Canada;University of Victoria, Victoria, BC, Canada;University of Victoria, Victoria, BC, Canada;Electronic Arts Blackbox, Burnaby, BC, Canada;University of Victoria, Victoria, BC, Canada;University of Victoria, Victoria, BC, Canada
Venue:
Proceedings of the 9th Workshop on Parallel/High-Performance Object-Oriented Scientific Computing
Year:
2010

Citing 2
Cited 0

Patterns for parallel programming

Patterns for parallel programming
Ubiquitous Parallel Computing from Berkeley, Illinois, and Stanford

IEEE Micro

Quantified Score

Hi-index	0.00

Visualization

Abstract

The resource requirements of modern-day scientific applications is making hardware acceleration a requisite design consideration. But typically these applications are created and implemented by scientists trained in other fields, not the intricacies of parallel processing. Consequently, there is a definite need for abstractions. In this paper, we discuss why the typically object-oriented abstractions that are commonly made available in such settings introduce accidental sequentiality and render the hardware acceleration ineffective. We hence propose a few research directions that we intend to pursue in order to generate new abstractions that better insulate the programmer from implementation details that do not relate to application logic.