Comparison of techniques used for mapping parallel algorithms to message-passing multiprocessors
AuthorDikaiakos, Marios D.
SourceIEEE Symposium on Parallel and Distributed Processing - Proceedings
Proceeedings of the 6th IEEE Symposium on Parallel and Distributed Processing
Google Scholar check
MetadataShow full item record
This paper presents a comparison study of popular clustering and mapping heuristics which are used to map task-flow graphs to message-passing multiprocessors. To this end, we use task-graphs which are representative of important scientific algorithms running on data-sets of practical interest. The annotation which assigns weights to nodes and edges of the task-graphs is realistic. It reflects current trends in processor, communication channel, and message-passing interface technology and takes into consideration hardware characteristics of state-of-the-art multiprocessors. Our experiments show that applying realistic models for task-graph annotation affects the effectiveness and functionality of clustering and mapping techniques. Therefore, new heuristics are necessary that will take into account more practical models of communication costs. We present modifications to existing clustering and mapping algorithms which improve their efficiency and running-time for the practical models adopted.
Showing items related by title, author, creator and subject.
Pratas, F.; Trancoso, Pedro; Sousa, L.; Stamatakis, A.; Shi, G.; Kindratenko, V. (2012)Currently, we are facing a situation where applications exhibit increasing computational demands and where a large variety of parallel processor systems are available. In this paper we focus on exploiting fine-grain ...
Kannas, Christos C.; Nicolaou, Christos A.; Pattichis, Constantinos S. (2009)Multi-objective Evolutionary Algorithms (MOEAs) have features that can be exploited to harness the processing power offered by modern multi-core CPUs. Modern programming languages offer the ability to use threads and ...
Dikaiakos, Marios D.; Rogers, Anne; Steiglitz, Kenneth (Publ by IEEE, 1994)In this paper we extend the practical range of simulations of parallel executions by what we call 'functional algorithm simulation,' that is, simulation without actually performing most of the numerical computations involved. ...