Power management framework for post-petascale supercomputers

Masaaki Kondo, Ikuo Miyoshi, Koji Inoue, Shinobu Miwa

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Power consumption is a first class design constraint for developing future exascale computing systems. To achieve exascale system performance with realistic power provisioning of 20-30MW, we need to improve power-performance efficiency significantly compared to today's supercomputer systems. In order to maximize effective performance within a power constraint, investigating how to optimize power resource allocation to each hardware component or each job submitted to the system is necessary. We have been conducting research and development on a software framework for code optimization and system power management for the power-constraint adaptive systems. We briefly introduce the research efforts for maximizing application performance under a given power constraint, power-aware resource manager, and power-performance simulation and analysis framework for future supercomputer systems.

Original languageEnglish
Title of host publicationAdvanced Software Technologies for Post-Peta Scale Computing
Subtitle of host publicationThe Japanese Post-Peta CREST Research Project
PublisherSpringer Singapore
Pages249-269
Number of pages21
ISBN (Electronic)9789811319242
ISBN (Print)9789811319235
DOIs
Publication statusPublished - Dec 6 2018

Fingerprint

Supercomputers
Adaptive systems
Resource allocation
Managers
Electric power utilization
Hardware
Power management

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Kondo, M., Miyoshi, I., Inoue, K., & Miwa, S. (2018). Power management framework for post-petascale supercomputers. In Advanced Software Technologies for Post-Peta Scale Computing: The Japanese Post-Peta CREST Research Project (pp. 249-269). Springer Singapore. https://doi.org/10.1007/978-981-13-1924-2_13

Power management framework for post-petascale supercomputers. / Kondo, Masaaki; Miyoshi, Ikuo; Inoue, Koji; Miwa, Shinobu.

Advanced Software Technologies for Post-Peta Scale Computing: The Japanese Post-Peta CREST Research Project. Springer Singapore, 2018. p. 249-269.

Research output: Chapter in Book/Report/Conference proceedingChapter

Kondo, M, Miyoshi, I, Inoue, K & Miwa, S 2018, Power management framework for post-petascale supercomputers. in Advanced Software Technologies for Post-Peta Scale Computing: The Japanese Post-Peta CREST Research Project. Springer Singapore, pp. 249-269. https://doi.org/10.1007/978-981-13-1924-2_13
Kondo M, Miyoshi I, Inoue K, Miwa S. Power management framework for post-petascale supercomputers. In Advanced Software Technologies for Post-Peta Scale Computing: The Japanese Post-Peta CREST Research Project. Springer Singapore. 2018. p. 249-269 https://doi.org/10.1007/978-981-13-1924-2_13
Kondo, Masaaki ; Miyoshi, Ikuo ; Inoue, Koji ; Miwa, Shinobu. / Power management framework for post-petascale supercomputers. Advanced Software Technologies for Post-Peta Scale Computing: The Japanese Post-Peta CREST Research Project. Springer Singapore, 2018. pp. 249-269
@inbook{30242ad57339485c91f5891b5666bf45,
title = "Power management framework for post-petascale supercomputers",
abstract = "Power consumption is a first class design constraint for developing future exascale computing systems. To achieve exascale system performance with realistic power provisioning of 20-30MW, we need to improve power-performance efficiency significantly compared to today's supercomputer systems. In order to maximize effective performance within a power constraint, investigating how to optimize power resource allocation to each hardware component or each job submitted to the system is necessary. We have been conducting research and development on a software framework for code optimization and system power management for the power-constraint adaptive systems. We briefly introduce the research efforts for maximizing application performance under a given power constraint, power-aware resource manager, and power-performance simulation and analysis framework for future supercomputer systems.",
author = "Masaaki Kondo and Ikuo Miyoshi and Koji Inoue and Shinobu Miwa",
year = "2018",
month = "12",
day = "6",
doi = "10.1007/978-981-13-1924-2_13",
language = "English",
isbn = "9789811319235",
pages = "249--269",
booktitle = "Advanced Software Technologies for Post-Peta Scale Computing",
publisher = "Springer Singapore",

}

TY - CHAP

T1 - Power management framework for post-petascale supercomputers

AU - Kondo, Masaaki

AU - Miyoshi, Ikuo

AU - Inoue, Koji

AU - Miwa, Shinobu

PY - 2018/12/6

Y1 - 2018/12/6

N2 - Power consumption is a first class design constraint for developing future exascale computing systems. To achieve exascale system performance with realistic power provisioning of 20-30MW, we need to improve power-performance efficiency significantly compared to today's supercomputer systems. In order to maximize effective performance within a power constraint, investigating how to optimize power resource allocation to each hardware component or each job submitted to the system is necessary. We have been conducting research and development on a software framework for code optimization and system power management for the power-constraint adaptive systems. We briefly introduce the research efforts for maximizing application performance under a given power constraint, power-aware resource manager, and power-performance simulation and analysis framework for future supercomputer systems.

AB - Power consumption is a first class design constraint for developing future exascale computing systems. To achieve exascale system performance with realistic power provisioning of 20-30MW, we need to improve power-performance efficiency significantly compared to today's supercomputer systems. In order to maximize effective performance within a power constraint, investigating how to optimize power resource allocation to each hardware component or each job submitted to the system is necessary. We have been conducting research and development on a software framework for code optimization and system power management for the power-constraint adaptive systems. We briefly introduce the research efforts for maximizing application performance under a given power constraint, power-aware resource manager, and power-performance simulation and analysis framework for future supercomputer systems.

UR - http://www.scopus.com/inward/record.url?scp=85063797825&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063797825&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-1924-2_13

DO - 10.1007/978-981-13-1924-2_13

M3 - Chapter

AN - SCOPUS:85063797825

SN - 9789811319235

SP - 249

EP - 269

BT - Advanced Software Technologies for Post-Peta Scale Computing

PB - Springer Singapore

ER -