Experiences implementing a parallel ATMS on a shared-memory multiprocessor

Authors:
Edward Rothberg;Anoop Gupta
Affiliations:
Department of Computer Science, Stanford University, Stanford, CA;Department of Computer Science, Stanford University, Stanford, CA
Venue:
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Year:
1989

Citing 3
Cited 0

An assumption-based TMS

Artificial Intelligence
The connection machine

The connection machine
Reasoning with worlds and truth maintenance in a knowledge-based programming environment

Communications of the ACM

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Assumption-Based Truth Maintenance System (ATMS) is an important tool in AI. So far its wider use has been limited due to the enormous computational resources which it requires. We investigate the possibility of speeding it up by using a modest number of processors in parallel. We begin with a highly efficient sequential version written in C and then extend this version to allow parallel execution on the Encore Multimax, a 16 node shared-memory multiprocessor. We describe our experiences in implementing this shared-memory parallel version of the ATMS, present detailed results of its execution, and discuss the factors which limit the available speedup.