Adaptive software for scientific computing: Co-managing quality-performance-power tradeoffs

P. Raghavan, Mary Jane Irwin, L. C. Mclnnes, B. Norris

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

Abstract

Current trends in microprocessor design indicate that chips are approaching their packaging thermal limits, and the power-related costs of high-performance clusters and multiprocessors continue to grow as a quadratic function of peak execution rates and clock frequencies. Although a faster scientific simulation, such as one obtained by exploiting quality-performance tradeoffs, is also often one that consumes less power by using fewer compute cycles, a major challenge is developing explicitly power-aware scientific computing tools that can exploit special energy-saving features of the circuit fabric. Such tools are perhaps most natural when scientific computing involved sparse or irregular computations, for example, simulations based on partial differential equations in two or three spatial dimensions solved using implicit or semi-implicit schemes. Sparse kernels typically cannot execute near peak rates of the CPU's, and there is potential for tuning them to co-manage both power and performance characteristics. Furthermore, each sparse kernel often has a variety of implementations offering a wide range of tradeoffs in solution quality (e.g., accuracy, reliability, and scalability) and performance (e.g., execution time/rate and parallel efficiency/speedup). Consequently, proper method selection to meet changing application quality-of-service requirements and changing technologies can potentially provide dramatic performance improvements and savings in energy by using circuit fabric features such as dynamic voltage scaling. Our goal is to design adaptive tools for sparse computations that deliver reduced-energy realizations without adversely impacting application performance. In this paper, we provide an overview of our project and discuss some initial results.

Original languageEnglish (US)
Title of host publicationProceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005
DOIs
StatePublished - Dec 1 2005
Event19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005 - Denver, CO, United States
Duration: Apr 4 2005Apr 8 2005

Publication series

NameProceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005
Volume2005

Other

Other19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005
CountryUnited States
CityDenver, CO
Period4/4/054/8/05

Fingerprint

Natural sciences computing
Networks (circuits)
Partial differential equations
Program processors
Microprocessor chips
Scalability
Clocks
Packaging
Energy conservation
Quality of service
Tuning
Costs

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Raghavan, P., Irwin, M. J., Mclnnes, L. C., & Norris, B. (2005). Adaptive software for scientific computing: Co-managing quality-performance-power tradeoffs. In Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005 [1420130] (Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005; Vol. 2005). https://doi.org/10.1109/IPDPS.2005.83
Raghavan, P. ; Irwin, Mary Jane ; Mclnnes, L. C. ; Norris, B. / Adaptive software for scientific computing : Co-managing quality-performance-power tradeoffs. Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005. 2005. (Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005).
@inproceedings{ad6442f1c8a14c49a2285c380e1b081f,
title = "Adaptive software for scientific computing: Co-managing quality-performance-power tradeoffs",
abstract = "Current trends in microprocessor design indicate that chips are approaching their packaging thermal limits, and the power-related costs of high-performance clusters and multiprocessors continue to grow as a quadratic function of peak execution rates and clock frequencies. Although a faster scientific simulation, such as one obtained by exploiting quality-performance tradeoffs, is also often one that consumes less power by using fewer compute cycles, a major challenge is developing explicitly power-aware scientific computing tools that can exploit special energy-saving features of the circuit fabric. Such tools are perhaps most natural when scientific computing involved sparse or irregular computations, for example, simulations based on partial differential equations in two or three spatial dimensions solved using implicit or semi-implicit schemes. Sparse kernels typically cannot execute near peak rates of the CPU's, and there is potential for tuning them to co-manage both power and performance characteristics. Furthermore, each sparse kernel often has a variety of implementations offering a wide range of tradeoffs in solution quality (e.g., accuracy, reliability, and scalability) and performance (e.g., execution time/rate and parallel efficiency/speedup). Consequently, proper method selection to meet changing application quality-of-service requirements and changing technologies can potentially provide dramatic performance improvements and savings in energy by using circuit fabric features such as dynamic voltage scaling. Our goal is to design adaptive tools for sparse computations that deliver reduced-energy realizations without adversely impacting application performance. In this paper, we provide an overview of our project and discuss some initial results.",
author = "P. Raghavan and Irwin, {Mary Jane} and Mclnnes, {L. C.} and B. Norris",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/IPDPS.2005.83",
language = "English (US)",
isbn = "0769523129",
series = "Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005",
booktitle = "Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005",

}

Raghavan, P, Irwin, MJ, Mclnnes, LC & Norris, B 2005, Adaptive software for scientific computing: Co-managing quality-performance-power tradeoffs. in Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005., 1420130, Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005, vol. 2005, 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005, Denver, CO, United States, 4/4/05. https://doi.org/10.1109/IPDPS.2005.83

Adaptive software for scientific computing : Co-managing quality-performance-power tradeoffs. / Raghavan, P.; Irwin, Mary Jane; Mclnnes, L. C.; Norris, B.

Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005. 2005. 1420130 (Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005; Vol. 2005).

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

TY - GEN

T1 - Adaptive software for scientific computing

T2 - Co-managing quality-performance-power tradeoffs

AU - Raghavan, P.

AU - Irwin, Mary Jane

AU - Mclnnes, L. C.

AU - Norris, B.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Current trends in microprocessor design indicate that chips are approaching their packaging thermal limits, and the power-related costs of high-performance clusters and multiprocessors continue to grow as a quadratic function of peak execution rates and clock frequencies. Although a faster scientific simulation, such as one obtained by exploiting quality-performance tradeoffs, is also often one that consumes less power by using fewer compute cycles, a major challenge is developing explicitly power-aware scientific computing tools that can exploit special energy-saving features of the circuit fabric. Such tools are perhaps most natural when scientific computing involved sparse or irregular computations, for example, simulations based on partial differential equations in two or three spatial dimensions solved using implicit or semi-implicit schemes. Sparse kernels typically cannot execute near peak rates of the CPU's, and there is potential for tuning them to co-manage both power and performance characteristics. Furthermore, each sparse kernel often has a variety of implementations offering a wide range of tradeoffs in solution quality (e.g., accuracy, reliability, and scalability) and performance (e.g., execution time/rate and parallel efficiency/speedup). Consequently, proper method selection to meet changing application quality-of-service requirements and changing technologies can potentially provide dramatic performance improvements and savings in energy by using circuit fabric features such as dynamic voltage scaling. Our goal is to design adaptive tools for sparse computations that deliver reduced-energy realizations without adversely impacting application performance. In this paper, we provide an overview of our project and discuss some initial results.

AB - Current trends in microprocessor design indicate that chips are approaching their packaging thermal limits, and the power-related costs of high-performance clusters and multiprocessors continue to grow as a quadratic function of peak execution rates and clock frequencies. Although a faster scientific simulation, such as one obtained by exploiting quality-performance tradeoffs, is also often one that consumes less power by using fewer compute cycles, a major challenge is developing explicitly power-aware scientific computing tools that can exploit special energy-saving features of the circuit fabric. Such tools are perhaps most natural when scientific computing involved sparse or irregular computations, for example, simulations based on partial differential equations in two or three spatial dimensions solved using implicit or semi-implicit schemes. Sparse kernels typically cannot execute near peak rates of the CPU's, and there is potential for tuning them to co-manage both power and performance characteristics. Furthermore, each sparse kernel often has a variety of implementations offering a wide range of tradeoffs in solution quality (e.g., accuracy, reliability, and scalability) and performance (e.g., execution time/rate and parallel efficiency/speedup). Consequently, proper method selection to meet changing application quality-of-service requirements and changing technologies can potentially provide dramatic performance improvements and savings in energy by using circuit fabric features such as dynamic voltage scaling. Our goal is to design adaptive tools for sparse computations that deliver reduced-energy realizations without adversely impacting application performance. In this paper, we provide an overview of our project and discuss some initial results.

UR - http://www.scopus.com/inward/record.url?scp=33746313657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746313657&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2005.83

DO - 10.1109/IPDPS.2005.83

M3 - Conference contribution

AN - SCOPUS:33746313657

SN - 0769523129

SN - 0769523129

SN - 9780769523125

T3 - Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005

BT - Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005

ER -

Raghavan P, Irwin MJ, Mclnnes LC, Norris B. Adaptive software for scientific computing: Co-managing quality-performance-power tradeoffs. In Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005. 2005. 1420130. (Proceedings - 19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005). https://doi.org/10.1109/IPDPS.2005.83