Publication: Message Passing vs. Shared-Data Programming - Wish vs. Reality

All || By Area || By Year

Title	Message Passing vs. Shared-Data Programming - Wish vs. Reality
Authors/Editors*	Angela C. Sodan
Where published*	Int. Symp. on High Performance Computing Systems (HPCS)
How published*	Proceedings
Year*	2005
Volume	-1
Number	-1
Pages	131-139
Publisher	IEEE
Keywords
Link
Abstract	Typically, only technical arguments like performance, cost or scalability are discussed if programming models and languages on High Performance Computing facilities are under consideration. In this paper, we investigate the impact of human factors such as personal preferences and perceptions, and personal experience on making technical decisions. We have queried a large HPC community of the Sharcnet project in Ontario in regards to general preferences and in regards to detailed usage of language features and programming style. The main result of our study is thatâas often claimed in the past but never provenâshared-memory programming models and architectures appear to be the ideal for the majority of users, even if the main architecture of the project is a distributed-memory cluster. However, experience appears to be able to quickly overcome initial difficulties in using message passing.