skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Holistic Approaches to HPC Power and Workflow Management

Abstract

Constraints on power consumption are having pervasive effects on high-performance computing (HPC) systems, the facilities in which they are housed, and the application codes themselves. Whether these constraints are driven by physical limits on available power within a facility, are due to utility demand response, result from opportunities to reduce utility costs, or are imposed by sponsoring agencies, power management must now be added to the traditional goals of application and algorithm correctness, scalability, and performance. The specifics of these power constraints are likely to vary from site to site, and optimal strategies for managing power will vary. In this paper, we present the results of implementing several strategies for managing HPC system power and quantify the impact of these power reductions on application performance. These can be added to the suite of extant options that can be used to manage power and workflow on HPC systems.

Authors:
 [1];  [1];  [2];  [2]
  1. National Renewable Energy Laboratory (NREL), Golden, CO (United States)
  2. Intel Corporation
Publication Date:
Research Org.:
National Renewable Energy Lab. (NREL), Golden, CO (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
OSTI Identifier:
1550779
Report Number(s):
NREL/CP-2C00-74539
DOE Contract Number:  
AC36-08GO28308
Resource Type:
Conference
Resource Relation:
Conference: Presented at the 2018 Ninth International Green and Sustainable Computing Conference (IGSC), 22-24 October 2018, Pittsburgh, Pennsylvania
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; high performance computing; exascale; power management; power constraints; demand response; core parking; DVFS; workflow management

Citation Formats

Purkayastha, Avi, Hammond, Steven W, Nagappan, Ramkumar, and Alt, Maxim. Holistic Approaches to HPC Power and Workflow Management. United States: N. p., 2019. Web. doi:10.1109/IGCC.2018.8752150.
Purkayastha, Avi, Hammond, Steven W, Nagappan, Ramkumar, & Alt, Maxim. Holistic Approaches to HPC Power and Workflow Management. United States. doi:10.1109/IGCC.2018.8752150.
Purkayastha, Avi, Hammond, Steven W, Nagappan, Ramkumar, and Alt, Maxim. Mon . "Holistic Approaches to HPC Power and Workflow Management". United States. doi:10.1109/IGCC.2018.8752150.
@article{osti_1550779,
title = {Holistic Approaches to HPC Power and Workflow Management},
author = {Purkayastha, Avi and Hammond, Steven W and Nagappan, Ramkumar and Alt, Maxim},
abstractNote = {Constraints on power consumption are having pervasive effects on high-performance computing (HPC) systems, the facilities in which they are housed, and the application codes themselves. Whether these constraints are driven by physical limits on available power within a facility, are due to utility demand response, result from opportunities to reduce utility costs, or are imposed by sponsoring agencies, power management must now be added to the traditional goals of application and algorithm correctness, scalability, and performance. The specifics of these power constraints are likely to vary from site to site, and optimal strategies for managing power will vary. In this paper, we present the results of implementing several strategies for managing HPC system power and quantify the impact of these power reductions on application performance. These can be added to the suite of extant options that can be used to manage power and workflow on HPC systems.},
doi = {10.1109/IGCC.2018.8752150},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {7}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: