Sim-X: Parallel system software for interactive multi-experiment computational studies

Siu Man Yau, Eitan Grinspun, Vijay Karamcheti, Denis Zorin

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

Abstract

Advances in high-performance computing have led to the broad use of computational studies in everyday engineering and scientific applications. A single study may require thousands of computational experiments, each corresponding to individual runs of simulation software with different parameter settings; in complex studies, the pattern of parameter changes is complex and may have to be adjusted by the user based on partial simulation results. Unfortunately, existing tools have limited high-level support for managing large ensembles of simultaneous computational experiments. In this paper, we present a system architecture for interactive computational studies targeting two goals. The first is to provide a framework for high-level user interaction with computational studies, rather than individual experiments; the second is to maximize the size of the studies that can be performed at close to interactive rates. We describe a prototype implementation of the system and demonstrate performance improvements obtained using our approach for a simple model problem.

Original languageEnglish (US)
Title of host publication20th International Parallel and Distributed Processing Symposium, IPDPS 2006
Volume2006
DOIs
StatePublished - 2006

Fingerprint

Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yau, S. M., Grinspun, E., Karamcheti, V., & Zorin, D. (2006). Sim-X: Parallel system software for interactive multi-experiment computational studies. In 20th International Parallel and Distributed Processing Symposium, IPDPS 2006 (Vol. 2006). [1639373] https://doi.org/10.1109/IPDPS.2006.1639373

Sim-X : Parallel system software for interactive multi-experiment computational studies. / Yau, Siu Man; Grinspun, Eitan; Karamcheti, Vijay; Zorin, Denis.

20th International Parallel and Distributed Processing Symposium, IPDPS 2006. Vol. 2006 2006. 1639373.

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

Yau, SM, Grinspun, E, Karamcheti, V & Zorin, D 2006, Sim-X: Parallel system software for interactive multi-experiment computational studies. in 20th International Parallel and Distributed Processing Symposium, IPDPS 2006. vol. 2006, 1639373. https://doi.org/10.1109/IPDPS.2006.1639373
Yau SM, Grinspun E, Karamcheti V, Zorin D. Sim-X: Parallel system software for interactive multi-experiment computational studies. In 20th International Parallel and Distributed Processing Symposium, IPDPS 2006. Vol. 2006. 2006. 1639373 https://doi.org/10.1109/IPDPS.2006.1639373
Yau, Siu Man ; Grinspun, Eitan ; Karamcheti, Vijay ; Zorin, Denis. / Sim-X : Parallel system software for interactive multi-experiment computational studies. 20th International Parallel and Distributed Processing Symposium, IPDPS 2006. Vol. 2006 2006.
@inproceedings{1599fcfab5d5452ea245123cf5c415a2,
title = "Sim-X: Parallel system software for interactive multi-experiment computational studies",
abstract = "Advances in high-performance computing have led to the broad use of computational studies in everyday engineering and scientific applications. A single study may require thousands of computational experiments, each corresponding to individual runs of simulation software with different parameter settings; in complex studies, the pattern of parameter changes is complex and may have to be adjusted by the user based on partial simulation results. Unfortunately, existing tools have limited high-level support for managing large ensembles of simultaneous computational experiments. In this paper, we present a system architecture for interactive computational studies targeting two goals. The first is to provide a framework for high-level user interaction with computational studies, rather than individual experiments; the second is to maximize the size of the studies that can be performed at close to interactive rates. We describe a prototype implementation of the system and demonstrate performance improvements obtained using our approach for a simple model problem.",
author = "Yau, {Siu Man} and Eitan Grinspun and Vijay Karamcheti and Denis Zorin",
year = "2006",
doi = "10.1109/IPDPS.2006.1639373",
language = "English (US)",
isbn = "1424400546",
volume = "2006",
booktitle = "20th International Parallel and Distributed Processing Symposium, IPDPS 2006",

}

TY - GEN

T1 - Sim-X

T2 - Parallel system software for interactive multi-experiment computational studies

AU - Yau, Siu Man

AU - Grinspun, Eitan

AU - Karamcheti, Vijay

AU - Zorin, Denis

PY - 2006

Y1 - 2006

N2 - Advances in high-performance computing have led to the broad use of computational studies in everyday engineering and scientific applications. A single study may require thousands of computational experiments, each corresponding to individual runs of simulation software with different parameter settings; in complex studies, the pattern of parameter changes is complex and may have to be adjusted by the user based on partial simulation results. Unfortunately, existing tools have limited high-level support for managing large ensembles of simultaneous computational experiments. In this paper, we present a system architecture for interactive computational studies targeting two goals. The first is to provide a framework for high-level user interaction with computational studies, rather than individual experiments; the second is to maximize the size of the studies that can be performed at close to interactive rates. We describe a prototype implementation of the system and demonstrate performance improvements obtained using our approach for a simple model problem.

AB - Advances in high-performance computing have led to the broad use of computational studies in everyday engineering and scientific applications. A single study may require thousands of computational experiments, each corresponding to individual runs of simulation software with different parameter settings; in complex studies, the pattern of parameter changes is complex and may have to be adjusted by the user based on partial simulation results. Unfortunately, existing tools have limited high-level support for managing large ensembles of simultaneous computational experiments. In this paper, we present a system architecture for interactive computational studies targeting two goals. The first is to provide a framework for high-level user interaction with computational studies, rather than individual experiments; the second is to maximize the size of the studies that can be performed at close to interactive rates. We describe a prototype implementation of the system and demonstrate performance improvements obtained using our approach for a simple model problem.

UR - http://www.scopus.com/inward/record.url?scp=33847114446&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847114446&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2006.1639373

DO - 10.1109/IPDPS.2006.1639373

M3 - Conference contribution

AN - SCOPUS:33847114446

SN - 1424400546

SN - 9781424400546

VL - 2006

BT - 20th International Parallel and Distributed Processing Symposium, IPDPS 2006

ER -