Visual data-analytics of large-scale parallel discrete-event simulations

Caitlin Ross, Christopher D. Carothers, Misbah Mubarak, Philip Carns, Robert Ross, Jianping Kelvin Li, Kwan-Liu Ma

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

4 Citations (Scopus)

Abstract

Parallel discrete-event simulation (PDES) is an important tool in the codesign of extreme-scale systems because PDES provides a cost-effective way to evaluate designs of high-performance computing systems. Optimistic synchronization algorithms for PDES, such as Time Warp, allow events to be processed without global synchronization among the processing elements. A rollback mechanism is provided when events are processed out of timestamp order. Although optimistic synchronization protocols enable the scalability of large-scale PDES, the performance of the simulations must be tuned to reduce the number of rollbacks and provide an improved simulation runtime. To enable efficient large-scale optimistic simulations, one has to gain insight into the factors that affect the rollback behavior and simulation performance. We developed a tool for ROSS model developers that gives them detailed metrics on the performance of their large-scale optimistic simulations at varying levels of simulation granularity. Model developers can use this information for parameter tuning of optimistic simulations in order to achieve better runtime and fewer rollbacks. In this work, we instrument the ROSS optimistic PDES framework to gather detailed statistics about the simulation engine. We have also developed an interactive visualization interface that uses the data collected by the ROSS instrumentation to understand the underlying behavior of the simulation engine. The interface connects real time to virtual time in the simulation and provides the ability to view simulation data at different granularities. We demonstrate the usefulness of our framework by performing a visual analysis of the dragonfly network topology model provided by the CODES simulation framework built on top of ROSS. The instrumentation needs to minimize overhead in order to accurately collect data about the simulation performance. To ensure that the instrumentation does not introduce unnecessary overhead, we perform a scaling study that compares instrumented ROSS simulations with their noninstrumented counterparts in order to determine the amount of perturbation when running at different simulation scales.

Original languageEnglish (US)
Title of host publicationProceedings of PMBS 2016
Subtitle of host publication7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages87-97
Number of pages11
ISBN (Electronic)9781509052189
DOIs
StatePublished - Jan 30 2017
Event7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems, PMBS 2016 - Salt Lake City, United States
Duration: Nov 14 2016 → …

Other

Other7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems, PMBS 2016
CountryUnited States
CitySalt Lake City
Period11/14/16 → …

Fingerprint

Parallel Discrete Event Simulation
Discrete event simulation
Synchronization
Simulation
Engines
Information use
Instrumentation
Scalability
Simulation Framework
Visualization
Tuning
Topology
Vision
Statistics
Granularity
Engine
Processing
Time Warp
Co-design
Global Synchronization

ASJC Scopus subject areas

  • Hardware and Architecture
  • Modeling and Simulation

Cite this

Ross, C., Carothers, C. D., Mubarak, M., Carns, P., Ross, R., Li, J. K., & Ma, K-L. (2017). Visual data-analytics of large-scale parallel discrete-event simulations. In Proceedings of PMBS 2016: 7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 87-97). [7836417] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PMBS.2016.014

Visual data-analytics of large-scale parallel discrete-event simulations. / Ross, Caitlin; Carothers, Christopher D.; Mubarak, Misbah; Carns, Philip; Ross, Robert; Li, Jianping Kelvin; Ma, Kwan-Liu.

Proceedings of PMBS 2016: 7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2017. p. 87-97 7836417.

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

Ross, C, Carothers, CD, Mubarak, M, Carns, P, Ross, R, Li, JK & Ma, K-L 2017, Visual data-analytics of large-scale parallel discrete-event simulations. in Proceedings of PMBS 2016: 7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis., 7836417, Institute of Electrical and Electronics Engineers Inc., pp. 87-97, 7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems, PMBS 2016, Salt Lake City, United States, 11/14/16. https://doi.org/10.1109/PMBS.2016.014
Ross C, Carothers CD, Mubarak M, Carns P, Ross R, Li JK et al. Visual data-analytics of large-scale parallel discrete-event simulations. In Proceedings of PMBS 2016: 7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2017. p. 87-97. 7836417 https://doi.org/10.1109/PMBS.2016.014
Ross, Caitlin ; Carothers, Christopher D. ; Mubarak, Misbah ; Carns, Philip ; Ross, Robert ; Li, Jianping Kelvin ; Ma, Kwan-Liu. / Visual data-analytics of large-scale parallel discrete-event simulations. Proceedings of PMBS 2016: 7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 87-97
@inproceedings{4298e833383141e19068b640489cbc93,
title = "Visual data-analytics of large-scale parallel discrete-event simulations",
abstract = "Parallel discrete-event simulation (PDES) is an important tool in the codesign of extreme-scale systems because PDES provides a cost-effective way to evaluate designs of high-performance computing systems. Optimistic synchronization algorithms for PDES, such as Time Warp, allow events to be processed without global synchronization among the processing elements. A rollback mechanism is provided when events are processed out of timestamp order. Although optimistic synchronization protocols enable the scalability of large-scale PDES, the performance of the simulations must be tuned to reduce the number of rollbacks and provide an improved simulation runtime. To enable efficient large-scale optimistic simulations, one has to gain insight into the factors that affect the rollback behavior and simulation performance. We developed a tool for ROSS model developers that gives them detailed metrics on the performance of their large-scale optimistic simulations at varying levels of simulation granularity. Model developers can use this information for parameter tuning of optimistic simulations in order to achieve better runtime and fewer rollbacks. In this work, we instrument the ROSS optimistic PDES framework to gather detailed statistics about the simulation engine. We have also developed an interactive visualization interface that uses the data collected by the ROSS instrumentation to understand the underlying behavior of the simulation engine. The interface connects real time to virtual time in the simulation and provides the ability to view simulation data at different granularities. We demonstrate the usefulness of our framework by performing a visual analysis of the dragonfly network topology model provided by the CODES simulation framework built on top of ROSS. The instrumentation needs to minimize overhead in order to accurately collect data about the simulation performance. To ensure that the instrumentation does not introduce unnecessary overhead, we perform a scaling study that compares instrumented ROSS simulations with their noninstrumented counterparts in order to determine the amount of perturbation when running at different simulation scales.",
author = "Caitlin Ross and Carothers, {Christopher D.} and Misbah Mubarak and Philip Carns and Robert Ross and Li, {Jianping Kelvin} and Kwan-Liu Ma",
year = "2017",
month = "1",
day = "30",
doi = "10.1109/PMBS.2016.014",
language = "English (US)",
pages = "87--97",
booktitle = "Proceedings of PMBS 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Visual data-analytics of large-scale parallel discrete-event simulations

AU - Ross, Caitlin

AU - Carothers, Christopher D.

AU - Mubarak, Misbah

AU - Carns, Philip

AU - Ross, Robert

AU - Li, Jianping Kelvin

AU - Ma, Kwan-Liu

PY - 2017/1/30

Y1 - 2017/1/30

N2 - Parallel discrete-event simulation (PDES) is an important tool in the codesign of extreme-scale systems because PDES provides a cost-effective way to evaluate designs of high-performance computing systems. Optimistic synchronization algorithms for PDES, such as Time Warp, allow events to be processed without global synchronization among the processing elements. A rollback mechanism is provided when events are processed out of timestamp order. Although optimistic synchronization protocols enable the scalability of large-scale PDES, the performance of the simulations must be tuned to reduce the number of rollbacks and provide an improved simulation runtime. To enable efficient large-scale optimistic simulations, one has to gain insight into the factors that affect the rollback behavior and simulation performance. We developed a tool for ROSS model developers that gives them detailed metrics on the performance of their large-scale optimistic simulations at varying levels of simulation granularity. Model developers can use this information for parameter tuning of optimistic simulations in order to achieve better runtime and fewer rollbacks. In this work, we instrument the ROSS optimistic PDES framework to gather detailed statistics about the simulation engine. We have also developed an interactive visualization interface that uses the data collected by the ROSS instrumentation to understand the underlying behavior of the simulation engine. The interface connects real time to virtual time in the simulation and provides the ability to view simulation data at different granularities. We demonstrate the usefulness of our framework by performing a visual analysis of the dragonfly network topology model provided by the CODES simulation framework built on top of ROSS. The instrumentation needs to minimize overhead in order to accurately collect data about the simulation performance. To ensure that the instrumentation does not introduce unnecessary overhead, we perform a scaling study that compares instrumented ROSS simulations with their noninstrumented counterparts in order to determine the amount of perturbation when running at different simulation scales.

AB - Parallel discrete-event simulation (PDES) is an important tool in the codesign of extreme-scale systems because PDES provides a cost-effective way to evaluate designs of high-performance computing systems. Optimistic synchronization algorithms for PDES, such as Time Warp, allow events to be processed without global synchronization among the processing elements. A rollback mechanism is provided when events are processed out of timestamp order. Although optimistic synchronization protocols enable the scalability of large-scale PDES, the performance of the simulations must be tuned to reduce the number of rollbacks and provide an improved simulation runtime. To enable efficient large-scale optimistic simulations, one has to gain insight into the factors that affect the rollback behavior and simulation performance. We developed a tool for ROSS model developers that gives them detailed metrics on the performance of their large-scale optimistic simulations at varying levels of simulation granularity. Model developers can use this information for parameter tuning of optimistic simulations in order to achieve better runtime and fewer rollbacks. In this work, we instrument the ROSS optimistic PDES framework to gather detailed statistics about the simulation engine. We have also developed an interactive visualization interface that uses the data collected by the ROSS instrumentation to understand the underlying behavior of the simulation engine. The interface connects real time to virtual time in the simulation and provides the ability to view simulation data at different granularities. We demonstrate the usefulness of our framework by performing a visual analysis of the dragonfly network topology model provided by the CODES simulation framework built on top of ROSS. The instrumentation needs to minimize overhead in order to accurately collect data about the simulation performance. To ensure that the instrumentation does not introduce unnecessary overhead, we perform a scaling study that compares instrumented ROSS simulations with their noninstrumented counterparts in order to determine the amount of perturbation when running at different simulation scales.

UR - http://www.scopus.com/inward/record.url?scp=85015147166&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015147166&partnerID=8YFLogxK

U2 - 10.1109/PMBS.2016.014

DO - 10.1109/PMBS.2016.014

M3 - Conference contribution

AN - SCOPUS:85015147166

SP - 87

EP - 97

BT - Proceedings of PMBS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -