Parallel discrete event simulation on shared-memory multiprocessors

Konas, Pavlos; Yew, Pen-Chung

doi:10.1109/simsym.1991.151498

Cited by 11 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Synchronous PDES methods have shown significant potential in the parallel execution of such simulations (Konas 1994). On the other hand, asynchronous PDES methods (both conservative and optimistic) are less attractive due to the significant overheads they introduce in attempting to find parallelism during a simulation (Konas and Yew 1991).…”

Section: Introductionmentioning

confidence: 99%

Processor self-scheduling in parallel discrete event simulation

Konas

Yew

1995

Proceedings of the 27th Conference on Winter Simulation - WSC '95

View full text Add to dashboard Cite

This paper describes a novel data structure and an algorithm for processor self-scheduling in parallel discrete event simulation. The presented data structure allows the efficient scheduling of future computations, it facilitates the inexpensive use of processor affinity information, it reduces the contention on the scheduling queue, and it integrates load balancing and locality management methods into a single mechanism. We use the behavioral simulation of a multiprocessor system to characterize the behavior of the proposed data structure and the associated scheduling algorithm. The results of our study show that it is important to maintain as detailed affinity information as possible and exploit this information at run time.

show abstract

Section: Introductionmentioning

confidence: 99%

Processor self-scheduling in parallel discrete event simulation

Konas

Yew

1995

Proceedings of the 27th Conference on Winter Simulation - WSC '95

View full text Add to dashboard Cite

show abstract

“…Synchronous PDES methods have shown significant potential in the parallel execution of such simulations (Konas 1994). On the other hand, asynchronous PDES methods (both conservative and optimistic) are less attractive due to the significant overheads they introducein attempting to find parallelism during a simulation (Konas and Yew 1991).…”

Section: Introductionmentioning

confidence: 99%

Processor self-scheduling in parallel discrete event simulation

Konas¹,

Yew²

Winter Simulation Conference Proceedings, 1995.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The approach of DES has been adopted for analytic purpose and virtual environment (VE) for many years. Over the past two decades, the rapid expansion of Internet and increasing accessibility to high performance parallel computer has made parallel and Analytic PADS has been successful in the areas of telecommunications [22,32,79], digital logic circuits [15,72,74,77], computer architectures [39,75,76] and transportation systems [147]. It has proven to be a cost-and time-effective way for developing new systems, particularly those that involve a high capital investment, and in testing design changes or policy changes to existing systems.…”

mentioning

confidence: 99%

Causal order in parallel and distributed simulation systems

Zeng¹

View full text Add to dashboard Cite

The causal order captures the most basic and important event ordering in distributed systems. In our research, it is applied to solve major problems in two categories of parallel and distributed simulation (PADS) applications, i.e., consistency in distributed virtual environments (DVEs) and performance in Time Warp simulation. In order to achieve more strict consistency in DVEs, inconsistency problems caused by receiving order of concurrent messages are identified. To solve the problems, a causal order based event ordering scheme, the Direct Follow Order (DFO), which enforces uninterrupted delivery of directly coupled causal messages, i.e. , direct-follow messages, is proposed. The DFO is proved to be a stricter ordering scheme than the causal order. However, as discovered in our research, the DFO cannot be always ensured. The sufficiency and necessity conditions under which the DFO can be guaranteed on direct-follow messages are derived. Implementation issues of DFO are also discussed. Performance in Time Warp simulation is greatly determined by the effective advancement of individual logical processes (LPs). Effective advancement can be addressed from various aspects, among which fast cancellation schemes and measures to reduce rollbacks are of our major concerns. These drive our research into two parts: (1) By capturing state dependency and scheduling dependency among events, batch based cancellation scheme is able to carry out rollback optimal cancellation, in which recovery of LPs caused by a straggler message can be done at the cost of at most one rollback; and (2) In view of noteworthy communication latency and possible non-FIFO transmission in distributed simulations, LPs may suffer more rollbacks from their uncontrolled optimistic advancement. To alleviate this problem, the causal order based T i m e Warp simulation is proposed and relevant techniques making the causal order and the time-stamp order consistent are discussed.

show abstract

Parallel discrete event simulation on shared-memory multiprocessors

Cited by 11 publications

References 7 publications

Processor self-scheduling in parallel discrete event simulation

Processor self-scheduling in parallel discrete event simulation

Processor self-scheduling in parallel discrete event simulation

Causal order in parallel and distributed simulation systems

Contact Info

Product

Resources

About