ACM Transactions on Programming Languages and Systems (TOPLAS)
Statistics for parallelism and abstraction level in digital simulation
DAC '87 Proceedings of the 24th ACM/IEEE Design Automation Conference
Probability and Statistics with Reliability, Queuing and Computer Science Applications
Probability and Statistics with Reliability, Queuing and Computer Science Applications
Computer Architecture and Parallel Processing
Computer Architecture and Parallel Processing
Unified Methods for VLSI Simulation and Test Generation
Unified Methods for VLSI Simulation and Test Generation
Interconnection Networks for Parallel and Distributed Processing
Interconnection Networks for Parallel and Distributed Processing
A Distributed Prolog System with And Parallelism
IEEE Software
Sequential circuit test generation on a distributed system
DAC '93 Proceedings of the 30th international Design Automation Conference
Parallel logic simulation of VLSI systems
ACM Computing Surveys (CSUR)
An important factor for optimistic protocol on distributed systems: granularity
WSC '95 Proceedings of the 27th conference on Winter simulation
Performance analysis for parallel solutions to generic search problems
SAC '97 Proceedings of the 1997 ACM symposium on Applied computing
Predicting the performance of synchronous discrete event simulation systems
Proceedings of the 2001 IEEE/ACM international conference on Computer-aided design
IEEE Transactions on Parallel and Distributed Systems
Optimal Remapping in Dynamic Bulk Synchronous Computations via a Stochastic Control Approach
IEEE Transactions on Parallel and Distributed Systems
Application Load Imbalance on Parallel Processors
IPPS '96 Proceedings of the 10th International Parallel Processing Symposium
Optimal periodic remapping of dynamic bulk synchronous computations
Journal of Parallel and Distributed Computing
Predicting the Performance of Synchronous Discrete Event Simulation
IEEE Transactions on Parallel and Distributed Systems
The Journal of Supercomputing
Performance modeling and analysis of correlated parallel computations
Parallel Computing
| Hi-index | 0.00 |
A statistical model of parallel processing and a performance evaluation technique areintroduced. A task is characterized by the number of atoms and by activity. An atom isthe smallest part of computation that cannot be distributed to multiple processors and allatoms of a task are assumed to be equal in computational effort. Furthermore, atoms ofthe task became active with a fixed probability a called the activity. The task is equallydivided among processors and the computation is synchronized at periodic instanceswhen the results can be shared. The amount of computational activity of a processorwithin the period between synchronizations is assumed to be a binomial random variable.The performance of the multiprocessor system is derived from the maximumorder-statistic of these random variables. The theoretical performance predicted by theanalysis agrees well with the reported experimental performance of logic simulation ofproduction VLSI chips, and several observed phenomena are explainable.