Assessing the Usability of Parallel Programming Systems: The Cowichan Problems (1993)
| Venue: | In Proceedings of the IFIP Working Conference on Programming Environments for Massively Parallel Distributed Systems |
| Citations: | 23 - 3 self |
BibTeX
@INPROCEEDINGS{Wilson93assessingthe,
author = {Gregory V. Wilson},
title = {Assessing the Usability of Parallel Programming Systems: The Cowichan Problems},
booktitle = {In Proceedings of the IFIP Working Conference on Programming Environments for Massively Parallel Distributed Systems},
year = {1993},
pages = {183--193}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
The only control-parallel programming model to win wide acceptance to date has been procedural message passing. One reason that higher-level systems have not been widely accepted is that there is no consensus on what they should offer; one reason for this is that there has been no systematic comparison of the usability of alternatives models and systems. This paper describes a problem suite with which the usability, rather than performance, of parallel programming systems may be assessed. Introduction While data parallelism is now widely accepted, most control-parallel programming systems are used only by their authors, or not used at all. The only general exceptions are low-level procedural message-passing (PMP) systems such as PVM and PARMACS [GS92, BRH90]. While these are appropriate for systems-level programming, they make applications programming tedious and error-prone. Like the VT100, the PMP model does not offer much, but is the only reliable common denominator between ...
