Allocating Independent Subtasks on Parallel Processors
IEEE Transactions on Software Engineering
A performance model of block structured parallel programs
Proceedings of the international workshop on Parallel algorithms & architectures
Performance and Reliability Analysis Using Directed Acyclic Graphs
IEEE Transactions on Software Engineering
A framework for determining useful parallelism
ICS '88 Proceedings of the 2nd international conference on Supercomputing
Determining average program execution times and their variance
PLDI '89 Proceedings of the ACM SIGPLAN 1989 Conference on Programming language design and implementation
Parallel sorting by regular sampling
Journal of Parallel and Distributed Computing
A static parameter based performance prediction tool for parallel programs
ICS '93 Proceedings of the 7th international conference on Supercomputing
Static performance prediction of data-dependent programs
Proceedings of the 2nd international workshop on Software and performance
Probability and Statistics with Reliability, Queuing and Computer Science Applications
Probability and Statistics with Reliability, Queuing and Computer Science Applications
Performance of Synchronous Parallel Algorithms with Regular Structures
IEEE Transactions on Parallel and Distributed Systems
Integrated Compilation and Scalability Analysis for Parallel Systems
PACT '98 Proceedings of the 1998 International Conference on Parallel Architectures and Compilation Techniques
Performance Prediction in Production Environments
IPPS '98 Proceedings of the 12th. International Parallel Processing Symposium on International Parallel Processing Symposium
Symbolic Performance Prediction of Data-Dependent Parallel Programs
TOOLS '02 Proceedings of the 12th International Conference on Computer Performance Evaluation, Modelling Techniques and Tools
EUROMICRO '05 Proceedings of the 31st EUROMICRO Conference on Software Engineering and Advanced Applications
| Hi-index | 0.00 |
Current analytic solutions to the execution time prediction Y of binary parallel compositions of tasks with arbitrary execution time distributions X1 and X2 are either computationally complex or very inaccurate. In this paper we introduce an analytical approach based on the use of lambda distributions to approximate execution time distributions. This allows us to predict the first 4 statistical moments of Y in terms of the first 4 moments of Xi at negligible solution complexity. The prediction method applies to a wide range of workload distributions as found in practice, while its accuracy is better or equal compared to comparable low-cost approaches.