Performance prediction of concurrent systems
Thesis/Dissertation
·
OSTI ID:6355327
Concurrent systems are computers that use multiple processors to solve a single problem. A means to predict the application performance on these systems is a useful tool in many areas of concurrent-system research. Earlier work in this area either dealt with very restricted program structures or used methods with exponential complexity. This dissertation describes a computationally efficient and accurate method to predict performance for a class of parallel computations on concurrent systems. A parallel computation is modeled as a task system with precedence relationships expressed as a series-parallel directed acyclic graph. Resources in concurrent systems are modeled as service centers in queueing network models. Using these two models as inputs, the method outputs predictions of both the time to complete the computation and the concurrent-system utilization. The algorithm used is based on the approximate Mean Value Analysis in queueing network modeling with extensions to model concurrency in the computation. The new algorithm was validated against both detailed simulation and actual execution on a commercial multiprocessor.
- Research Organization:
- Stanford Univ., CA (USA)
- OSTI ID:
- 6355327
- Country of Publication:
- United States
- Language:
- English
Similar Records
Performance prediction of concurrent systems
Predicting performance of parallel computations
Analytic queueing network models for parallel processing of task systems
Technical Report
·
Mon Nov 30 23:00:00 EST 1987
·
OSTI ID:6601078
Predicting performance of parallel computations
Journal Article
·
Sun Jul 01 00:00:00 EDT 1990
· IEEE Transactions on Parallel and Distributed Systems; (USA)
·
OSTI ID:6397847
Analytic queueing network models for parallel processing of task systems
Journal Article
·
Sun Nov 30 23:00:00 EST 1986
· IEEE Trans. Comput.; (United States)
·
OSTI ID:6891661