High-performance computer architecture
High-performance computer architecture
Performance analysis of a scheme for concurrency/synchronization using queueing network models
International Journal of Parallel Programming
Communications of the ACM
Approximate Analysis of Fork/Join Synchronization in Parallel Queues
IEEE Transactions on Computers
Performance Analysis of Parallel Processing Systems
IEEE Transactions on Software Engineering
Analysis of the Fork-Join Queue
IEEE Transactions on Computers
Speedup Versus Efficiency in Parallel Systems
IEEE Transactions on Computers
Acyclic fork-join queuing networks
Journal of the ACM (JACM)
Characterizations of parallelism in applications and their use in scheduling
SIGMETRICS '89 Proceedings of the 1989 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Bounds for Two Server Fork-Join Queueing Systems
Bounds for Two Server Fork-Join Queueing Systems
Analysis of Fork-Join Jobs Using Processor-Sharing
Analysis of Fork-Join Jobs Using Processor-Sharing
Multiple feedback queue as a model of general purpose multiprocessor systems
CSC '92 Proceedings of the 1992 ACM annual conference on Communications
ISSAC '92 Papers from the international symposium on Symbolic and algebraic computation
The influence of random delays on parallel execution times
SIGMETRICS '93 Proceedings of the 1993 ACM SIGMETRICS conference on Measurement and modeling of computer systems
A performance evaluation of several priority policies for parallel processing systems
Journal of the ACM (JACM)
Bounds on the speedup and efficiency of partial synchronization in parallel processing systems
Journal of the ACM (JACM)
Including queueing effects in Amdahl's law
Communications of the ACM - Electronic supplement to the December issue
The impact of I/O on program behavior and parallel scheduling
SIGMETRICS '98/PERFORMANCE '98 Proceedings of the 1998 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems
Performance analysis for parallel solutions to generic search problems
SAC '97 Proceedings of the 1997 ACM symposium on Applied computing
Models of Parallel Applications with Large Computation and I/O Requirements
IEEE Transactions on Software Engineering
The Circulating Processor Model of Parallel Systems
IEEE Transactions on Computers
LISPACK-A Methodology and Tool for the Performance Analysis of Parallel Systems and Algorithms
IEEE Transactions on Software Engineering
Performance modeling and analysis of correlated parallel computations
Parallel Computing
A Superscalar software architecture model for Multi-Core Processors (MCPs)
Journal of Systems and Software
Hi-index | 0.00 |
In this paper we analyze a model of a parallel processing system. In our model there is a single queue which is K ≥ 1 identical processors. Jobs are assumed to consist of a sequence of barrier synchronizations where, at each step, the number of tasks that must be synchronized is random with a known distribution. An exact analysis of the model is derived. The model leads to a rich set of results characterizing the performance of parallel processing systems. We show that the number of jobs concurrently in execution, as well as the number of synchronization variables, grows linearly with the load of the system and strongly depends on the average number of parallel tasks found in the workload. Properties of expected response time or such systems are extensively analyzed and, in particular, we report on some non-obvious response time behavior that arises as a function of the variance of parallelism found in the workload. Based on exact response time analysis, we propose a simple calculation that can be used as a rule of thumb to predict speedups. This can be viewed as a generalization of Amdahl's law that includes queueing effects. This generalization is reformulated when precise workloads cannot be characterized, but rather when only the fraction or sequential work and the average number of parallel tasks arc assumed to be known.