Fast detection of communication patterns in distributed executions
CASCON '97 Proceedings of the 1997 conference of the Centre for Advanced Studies on Collaborative research
On the development of a communication-aware task mapping technique
Journal of Systems Architecture: the EUROMICRO Journal
ScalaExtrap: Trace-based communication extrapolation for SPMD programs
ACM Transactions on Programming Languages and Systems (TOPLAS)
| Hi-index | 0.00 |
The CAPSE environment for Computer Aided Parallel Software Engineering is intended to assist the developer in the crucial task of parallel programming. The methodology of CAPSE is based on direct manipulative graphical creation and editing of scalable workload characterizations of MIMD algorithms. This paper presents the basic concepts of this methodology and an example of a parallel Poisson solver. The workload characterization representing the computation and communication behavior of the algorithm is based on directed acyclic task graphs, which achieve scalability by composing the task graph of scalable basic patterns instead of single nodes and arcs. The composition and the usage of these basic patterns is described in the light of designing the Poisson solver algorithm. The resulting task graph is used to predict the program's performance on an nCUBE~2 distributed memory machine with the PAPS simulator. The comparison of this prediction and measurements of an actual implementation prove the quality of this toolset.