Using multiple energy gears in MPI programs on a power-scalable cluster

Vincent W. Freeh, Feng Pan, Nandini Kappiah, David K Lowenthal

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

154 Citations (Scopus)

Abstract

Recently, system architects have built low-power, high-performance clusters, such as Green Destiny. The idea behind these clusters is to improve the energy efficiency of nodes. However, these clusters save power at the expense of performance. Our approach is instead to use high-performance cluster nodes that are frequency-and voltage-scalable; energy can than be saved by scaling down the CPU. Our prior work has examined the costs and benefits of executing an entire application at a single reduced frequency. This paper presents a framework for executing a single application in several frequency-voltage settings. The basic idea is to first divide programs into phases and then execute a series of experiments, with each phase assigned a prescribed frequency. During each experiment, we measure energy consumption and time and then use a heuristic to choose the assignment of frequency to phase for the next experiment. Our results show that significant energy can be saved without an undue performance penalty; particularly, our heuristic finds assignments of frequency to phase that is superior to any fixed-frequency solution. Specifically, this paper shows that more than half of the NAS benchmarks exhibit a better energy-time tradeoff using multiple gears than using a single gear. For example, IS using multiple gears uses 9% less energy and executes in 1% less time than the closest single-gear solution. Compared to no frequency scaling, multiple gear IS uses 16% less energy while executing only 1% longer.

Original languageEnglish (US)
Title of host publicationProceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP
Pages164-173
Number of pages10
DOIs
StatePublished - 2005
Externally publishedYes
Event2005 ACM SIGPLAN Symposium on Principles and Practise of Parallel Programming, PROPP 05 - Chicago, IL, United States
Duration: Jun 15 2005Jun 17 2005

Other

Other2005 ACM SIGPLAN Symposium on Principles and Practise of Parallel Programming, PROPP 05
CountryUnited States
CityChicago, IL
Period6/15/056/17/05

Fingerprint

Gears
Experiments
Electric potential
Program processors
Energy efficiency
Energy utilization
Costs

Keywords

  • High-performance computing
  • Power-aware computing

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Freeh, V. W., Pan, F., Kappiah, N., & Lowenthal, D. K. (2005). Using multiple energy gears in MPI programs on a power-scalable cluster. In Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP (pp. 164-173) https://doi.org/10.1145/1065944.1065967

Using multiple energy gears in MPI programs on a power-scalable cluster. / Freeh, Vincent W.; Pan, Feng; Kappiah, Nandini; Lowenthal, David K.

Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP. 2005. p. 164-173.

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

Freeh, VW, Pan, F, Kappiah, N & Lowenthal, DK 2005, Using multiple energy gears in MPI programs on a power-scalable cluster. in Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP. pp. 164-173, 2005 ACM SIGPLAN Symposium on Principles and Practise of Parallel Programming, PROPP 05, Chicago, IL, United States, 6/15/05. https://doi.org/10.1145/1065944.1065967
Freeh VW, Pan F, Kappiah N, Lowenthal DK. Using multiple energy gears in MPI programs on a power-scalable cluster. In Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP. 2005. p. 164-173 https://doi.org/10.1145/1065944.1065967
Freeh, Vincent W. ; Pan, Feng ; Kappiah, Nandini ; Lowenthal, David K. / Using multiple energy gears in MPI programs on a power-scalable cluster. Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP. 2005. pp. 164-173
@inproceedings{4dcf1835b7c24ec68248e4a073fa2a88,
title = "Using multiple energy gears in MPI programs on a power-scalable cluster",
abstract = "Recently, system architects have built low-power, high-performance clusters, such as Green Destiny. The idea behind these clusters is to improve the energy efficiency of nodes. However, these clusters save power at the expense of performance. Our approach is instead to use high-performance cluster nodes that are frequency-and voltage-scalable; energy can than be saved by scaling down the CPU. Our prior work has examined the costs and benefits of executing an entire application at a single reduced frequency. This paper presents a framework for executing a single application in several frequency-voltage settings. The basic idea is to first divide programs into phases and then execute a series of experiments, with each phase assigned a prescribed frequency. During each experiment, we measure energy consumption and time and then use a heuristic to choose the assignment of frequency to phase for the next experiment. Our results show that significant energy can be saved without an undue performance penalty; particularly, our heuristic finds assignments of frequency to phase that is superior to any fixed-frequency solution. Specifically, this paper shows that more than half of the NAS benchmarks exhibit a better energy-time tradeoff using multiple gears than using a single gear. For example, IS using multiple gears uses 9{\%} less energy and executes in 1{\%} less time than the closest single-gear solution. Compared to no frequency scaling, multiple gear IS uses 16{\%} less energy while executing only 1{\%} longer.",
keywords = "High-performance computing, Power-aware computing",
author = "Freeh, {Vincent W.} and Feng Pan and Nandini Kappiah and Lowenthal, {David K}",
year = "2005",
doi = "10.1145/1065944.1065967",
language = "English (US)",
pages = "164--173",
booktitle = "Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP",

}

TY - GEN

T1 - Using multiple energy gears in MPI programs on a power-scalable cluster

AU - Freeh, Vincent W.

AU - Pan, Feng

AU - Kappiah, Nandini

AU - Lowenthal, David K

PY - 2005

Y1 - 2005

N2 - Recently, system architects have built low-power, high-performance clusters, such as Green Destiny. The idea behind these clusters is to improve the energy efficiency of nodes. However, these clusters save power at the expense of performance. Our approach is instead to use high-performance cluster nodes that are frequency-and voltage-scalable; energy can than be saved by scaling down the CPU. Our prior work has examined the costs and benefits of executing an entire application at a single reduced frequency. This paper presents a framework for executing a single application in several frequency-voltage settings. The basic idea is to first divide programs into phases and then execute a series of experiments, with each phase assigned a prescribed frequency. During each experiment, we measure energy consumption and time and then use a heuristic to choose the assignment of frequency to phase for the next experiment. Our results show that significant energy can be saved without an undue performance penalty; particularly, our heuristic finds assignments of frequency to phase that is superior to any fixed-frequency solution. Specifically, this paper shows that more than half of the NAS benchmarks exhibit a better energy-time tradeoff using multiple gears than using a single gear. For example, IS using multiple gears uses 9% less energy and executes in 1% less time than the closest single-gear solution. Compared to no frequency scaling, multiple gear IS uses 16% less energy while executing only 1% longer.

AB - Recently, system architects have built low-power, high-performance clusters, such as Green Destiny. The idea behind these clusters is to improve the energy efficiency of nodes. However, these clusters save power at the expense of performance. Our approach is instead to use high-performance cluster nodes that are frequency-and voltage-scalable; energy can than be saved by scaling down the CPU. Our prior work has examined the costs and benefits of executing an entire application at a single reduced frequency. This paper presents a framework for executing a single application in several frequency-voltage settings. The basic idea is to first divide programs into phases and then execute a series of experiments, with each phase assigned a prescribed frequency. During each experiment, we measure energy consumption and time and then use a heuristic to choose the assignment of frequency to phase for the next experiment. Our results show that significant energy can be saved without an undue performance penalty; particularly, our heuristic finds assignments of frequency to phase that is superior to any fixed-frequency solution. Specifically, this paper shows that more than half of the NAS benchmarks exhibit a better energy-time tradeoff using multiple gears than using a single gear. For example, IS using multiple gears uses 9% less energy and executes in 1% less time than the closest single-gear solution. Compared to no frequency scaling, multiple gear IS uses 16% less energy while executing only 1% longer.

KW - High-performance computing

KW - Power-aware computing

UR - http://www.scopus.com/inward/record.url?scp=31844450952&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=31844450952&partnerID=8YFLogxK

U2 - 10.1145/1065944.1065967

DO - 10.1145/1065944.1065967

M3 - Conference contribution

SP - 164

EP - 173

BT - Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP

ER -