Discrete Event Execution with One-Sided and Two-Sided GVT Algorithms on 216,000 Processor Cores

Perumalla, Kalyan S; Park, Alfred J; Tipparaju, Vinod

doi:10.1145/2611561

Discrete Event Execution with One-Sided and Two-Sided GVT Algorithms on 216,000 Processor Cores

Journal Article · Tue Dec 31 23:00:00 EST 2013 · ACM Transactions on Modeling and Computer Simulation

DOI:https://doi.org/10.1145/2611561· OSTI ID:1132340

Perumalla, Kalyan S ^[1]; Park, Alfred J ^[1]; Tipparaju, Vinod ^[1]

ORNL

Global virtual time (GVT) computation is a key determinant of the efficiency and runtime dynamics of parallel discrete event simulations (PDES), especially on large-scale parallel platforms. Here, three execution modes of a generalized GVT computation algorithm are studied on high-performance parallel computing systems: (1) a synchronous GVT algorithm that affords ease of implementation, (2) an asynchronous GVT algorithm that is more complex to implement but can relieve blocking latencies, and (3) a variant of the asynchronous GVT algorithm to exploit one-sided communication in extant supercomputing platforms. Performance results are presented of implementations of these algorithms on up to 216,000 cores of a Cray XT5 system, exercised on a range of parameters: optimistic and conservative synchronization, fine- to medium-grained event computation, synthetic and non-synthetic applications, and different lookahead values. Performance of up to 54 billion events executed per second is registered. Detailed PDES-specific runtime metrics are presented to further the understanding of tightly-coupled discrete event dynamics on massively parallel platforms.

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF); Oak Ridge National Laboratory (ORNL)

Sponsoring Organization:: DOE Office of Science; USDOE

DOE Contract Number:: AC05-00OR22725

OSTI ID:: 1132340

Journal Information:: ACM Transactions on Modeling and Computer Simulation, Journal Name: ACM Transactions on Modeling and Computer Simulation Journal Issue: 3 Vol. 24; ISSN 1049-3301

Publisher:: Association for Computing Machinery

Country of Publication:: United States

Language:: English

References (14)

Scalable Time Warp on Blue Gene Supercomputers Bauer Jr., David W.; Carothers, Christopher D.; Holder, Akintayo 2009 ACM/IEEE/SCS 23rd Workshop on Principles of Advanced and Distributed Simulation (PADS) https://doi.org/10.1109/PADS.2009.21	conference	June 2009
Efficient Algorithms for Distributed Snapshots and Global Virtual Time Approximation Mattern, F. Journal of Parallel and Distributed Computing, Vol. 18, Issue 4 https://doi.org/10.1006/jpdc.1993.1075	journal	August 1993
Discrete event modeling and massively parallel execution of epidemic outbreak phenomena Perumalla, Kalyan S.; Seal, Sudip K. SIMULATION, Vol. 88, Issue 7 https://doi.org/10.1177/0037549711413001	journal	July 2011
The cost of conservative synchronization in parallel discrete event simulations Nicol, David M. Journal of the ACM, Vol. 40, Issue 2 https://doi.org/10.1145/151261.151266	journal	April 1993
Virtual time Jefferson, David R. ACM Transactions on Programming Languages and Systems, Vol. 7, Issue 3 https://doi.org/10.1145/3916.3988	journal	July 1985
GVT algorithms and discrete event dynamics on 129K+ processor cores Perumalla, Kalyan S.; Park, Alfred J.; Tipparaju, Vinod 2011 18th International Conference on High Performance Computing (HiPC) https://doi.org/10.1109/HiPC.2011.6152725	conference	December 2011
Reducing null messages in Misra's distributed discrete event simulation method De Vries, R. C. IEEE Transactions on Software Engineering, Vol. 16, Issue 1 https://doi.org/10.1109/32.44366	journal	January 1990
Scaling time warp-based discrete event execution to 104 processors on a Blue Gene supercomputer Perumalla, Kalyan S. Proceedings of the 4th international conference on Computing frontiers - CF '07 https://doi.org/10.1145/1242531.1242543	conference	January 2007
Providing determinism in the Time Warp operating system-costs, benefits, and implications Reiher, P. L.; Wieland, F.; Hontalas, P. IEEE Workshop on Experimental Distributed Systems https://doi.org/10.1109/EDS.1990.138060	conference	January 1990
On deciding between conservative and optimistic approaches on massively parallel platforms Carothers, Christoph; Perumalla, Kalyan S. 2010 Winter Simulation Conference - (WSC 2010), Proceedings of the 2010 Winter Simulation Conference https://doi.org/10.1109/WSC.2010.5679119	conference	December 2010
Computing global virtual time in shared-memory multiprocessors Fujimoto, Richard M.; Hybinette, Maria ACM Transactions on Modeling and Computer Simulation, Vol. 7, Issue 4 https://doi.org/10.1145/268403.268404	journal	October 1997
MPI Collective Communications on The Blue Gene/P Supercomputer: Algorithms and Optimizations Faraj, Ahmad; Kumar, Sameer; Smith, Brian 2009 17th Annual IEEE Symposium on High-Performance Interconnects (HOTI), 2009 17th IEEE Symposium on High Performance Interconnects https://doi.org/10.1109/HOTI.2009.12	conference	August 2009
Middleware for real-time distributed simulations McLean, Thom; Fujimoto, Richard; Fitzgibbons, Brad Concurrency and Computation: Practice and Experience, Vol. 16, Issue 15 https://doi.org/10.1002/cpe.874	journal	January 2004
DSIM: Scaling Time Warp to 1,033 Processors Chen, G.; Szymanski, B. K. Proceedings of the Winter Simulation Conference, 2005. https://doi.org/10.1109/WSC.2005.1574269	conference	January 2005

Similar Records

GVT Algorithms and Discrete Event Dynamics on 128K+ Processor Cores

Conference · Fri Dec 31 23:00:00 EST 2010 · OSTI ID:1034668

Reversible Parallel Discrete-Event Execution of Large-scale Epidemic Outbreak Models

Conference · Thu Dec 31 23:00:00 EST 2009 · OSTI ID:982395

Virtual Time III, Part 1: Unified Virtual Time Synchronization for Parallel Discrete Event Simulation

Journal Article · Tue Jan 10 23:00:00 EST 2023 · ACM Transactions on Modeling and Computer Simulation · OSTI ID:1986609

Discrete Event Execution with One-Sided and Two-Sided GVT Algorithms on 216,000 Processor Cores

Citation Formats

References (14)

Similar Records

Related Subjects