An adaptive non-blocking GVT algorithm

Eric Mikida, Laxmikant V Kale

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In optimistic Parallel Discrete Event Simulations (PDES), the Global Virtual Time (GVT) computation is an important aspect of performance. It must be performed frequently enough to ensure simulation progress and free memory, while still incurring minimal overhead. Many algorithms have been studied for computing the GVT eciently under a variety of simulation conditions for a variety of models. In this paper we propose a new GVT algorithm which aims to do two things. First, it incurs a very low overhead on the simulation by not requiring the simulation to block execution. Secondly, and most importantly, it has the ability to adapt to simulation conditions while it’s running. This allows it to perform well for a variety of models, and helps remove some burden from developers by not requiring intensive tuning.

Original languageEnglish (US)
Title of host publicationSIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation
PublisherAssociation for Computing Machinery, Inc
Pages25-36
Number of pages12
ISBN (Electronic)9781450367233
DOIs
StatePublished - May 29 2019
Event2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, SIGSIM-PADS 2019 - Chicago, United States
Duration: Jun 3 2019Jun 5 2019

Publication series

NameSIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation

Conference

Conference2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, SIGSIM-PADS 2019
CountryUnited States
CityChicago
Period6/3/196/5/19

Fingerprint

Discrete event simulation
Simulation
Tuning
Data storage equipment
Parallel Discrete Event Simulation
Thing
Computing
Model

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Modeling and Simulation

Cite this

Mikida, E., & Kale, L. V. (2019). An adaptive non-blocking GVT algorithm. In SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation (pp. 25-36). (SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation). Association for Computing Machinery, Inc. https://doi.org/10.1145/3316480.3322896

An adaptive non-blocking GVT algorithm. / Mikida, Eric; Kale, Laxmikant V.

SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation. Association for Computing Machinery, Inc, 2019. p. 25-36 (SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mikida, E & Kale, LV 2019, An adaptive non-blocking GVT algorithm. in SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation. SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, Association for Computing Machinery, Inc, pp. 25-36, 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, SIGSIM-PADS 2019, Chicago, United States, 6/3/19. https://doi.org/10.1145/3316480.3322896
Mikida E, Kale LV. An adaptive non-blocking GVT algorithm. In SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation. Association for Computing Machinery, Inc. 2019. p. 25-36. (SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation). https://doi.org/10.1145/3316480.3322896
Mikida, Eric ; Kale, Laxmikant V. / An adaptive non-blocking GVT algorithm. SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation. Association for Computing Machinery, Inc, 2019. pp. 25-36 (SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation).
@inproceedings{b4cc737e2c92467899519915669921b7,
title = "An adaptive non-blocking GVT algorithm",
abstract = "In optimistic Parallel Discrete Event Simulations (PDES), the Global Virtual Time (GVT) computation is an important aspect of performance. It must be performed frequently enough to ensure simulation progress and free memory, while still incurring minimal overhead. Many algorithms have been studied for computing the GVT eciently under a variety of simulation conditions for a variety of models. In this paper we propose a new GVT algorithm which aims to do two things. First, it incurs a very low overhead on the simulation by not requiring the simulation to block execution. Secondly, and most importantly, it has the ability to adapt to simulation conditions while it’s running. This allows it to perform well for a variety of models, and helps remove some burden from developers by not requiring intensive tuning.",
author = "Eric Mikida and Kale, {Laxmikant V}",
year = "2019",
month = "5",
day = "29",
doi = "10.1145/3316480.3322896",
language = "English (US)",
series = "SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation",
publisher = "Association for Computing Machinery, Inc",
pages = "25--36",
booktitle = "SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation",

}

TY - GEN

T1 - An adaptive non-blocking GVT algorithm

AU - Mikida, Eric

AU - Kale, Laxmikant V

PY - 2019/5/29

Y1 - 2019/5/29

N2 - In optimistic Parallel Discrete Event Simulations (PDES), the Global Virtual Time (GVT) computation is an important aspect of performance. It must be performed frequently enough to ensure simulation progress and free memory, while still incurring minimal overhead. Many algorithms have been studied for computing the GVT eciently under a variety of simulation conditions for a variety of models. In this paper we propose a new GVT algorithm which aims to do two things. First, it incurs a very low overhead on the simulation by not requiring the simulation to block execution. Secondly, and most importantly, it has the ability to adapt to simulation conditions while it’s running. This allows it to perform well for a variety of models, and helps remove some burden from developers by not requiring intensive tuning.

AB - In optimistic Parallel Discrete Event Simulations (PDES), the Global Virtual Time (GVT) computation is an important aspect of performance. It must be performed frequently enough to ensure simulation progress and free memory, while still incurring minimal overhead. Many algorithms have been studied for computing the GVT eciently under a variety of simulation conditions for a variety of models. In this paper we propose a new GVT algorithm which aims to do two things. First, it incurs a very low overhead on the simulation by not requiring the simulation to block execution. Secondly, and most importantly, it has the ability to adapt to simulation conditions while it’s running. This allows it to perform well for a variety of models, and helps remove some burden from developers by not requiring intensive tuning.

UR - http://www.scopus.com/inward/record.url?scp=85067130912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067130912&partnerID=8YFLogxK

U2 - 10.1145/3316480.3322896

DO - 10.1145/3316480.3322896

M3 - Conference contribution

T3 - SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation

SP - 25

EP - 36

BT - SIGSIM-PADS 2019 - Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation

PB - Association for Computing Machinery, Inc

ER -