Adaptive real-time methodology for optimizing energy-efficient computing
Abstract
Dynamic voltage and frequency scaling (DVFS) is an effective way to reduce energy and power consumption in microprocessor units. Current implementations of DVFS suffer from inaccurate modeling of power requirements and usage, and from inaccurate characterization of the relationships between the applicable variables. A system and method is proposed that adjusts CPU frequency and voltage based on run-time calculations of the workload processing time, as well as a calculation of performance sensitivity with respect to CPU frequency. The system and method are processor independent, and can be applied to either an entire system as a unit, or individually to each process running on a system.
- Inventors:
- Issue Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1082651
- Patent Number(s):
- 8364998
- Application Number:
- 13/032,472
- Assignee:
- Los Alamos National Security, LLC (Los Alamos, NM)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y02 - TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE Y02D - CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THIR OWN ENERGY USE
- DOE Contract Number:
- W-7405-ENG-36
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 2011 Feb 22
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING
Citation Formats
Hsu, Chung-Hsing, and Feng, Wu-Chun. Adaptive real-time methodology for optimizing energy-efficient computing. United States: N. p., 2013.
Web.
Hsu, Chung-Hsing, & Feng, Wu-Chun. Adaptive real-time methodology for optimizing energy-efficient computing. United States.
Hsu, Chung-Hsing, and Feng, Wu-Chun. Tue .
"Adaptive real-time methodology for optimizing energy-efficient computing". United States. https://www.osti.gov/servlets/purl/1082651.
@article{osti_1082651,
title = {Adaptive real-time methodology for optimizing energy-efficient computing},
author = {Hsu, Chung-Hsing and Feng, Wu-Chun},
abstractNote = {Dynamic voltage and frequency scaling (DVFS) is an effective way to reduce energy and power consumption in microprocessor units. Current implementations of DVFS suffer from inaccurate modeling of power requirements and usage, and from inaccurate characterization of the relationships between the applicable variables. A system and method is proposed that adjusts CPU frequency and voltage based on run-time calculations of the workload processing time, as well as a calculation of performance sensitivity with respect to CPU frequency. The system and method are processor independent, and can be applied to either an entire system as a unit, or individually to each process running on a system.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Jan 29 00:00:00 EST 2013},
month = {Tue Jan 29 00:00:00 EST 2013}
}
Works referenced in this record:
System and method utilizing on-chip voltage controlled frequency modulation to manage power consumption
patent, January 2003
- Naffziger, Samuel D.; Josephson, Don D.
- US Patent Document 6,509,788
Power reduction by stage in integrated circuit
patent, November 2004
- Cohn, John M.; Goodnow, Kenneth J.; Gould, Scott Whitney
- US Patent Document 6,825,711
Systems and methods for process and user driven dynamic voltage and frequency scaling
patent, March 2011
- Mallik, Arindam; Lin, Bin; Memik, Gokhan
- US Patent Document 7,913,071
Adaptive real-time methodology for optimizing energy-efficient computing
patent, June 2011
- Hsu, Chung-Hsing; Feng, Wu-chun
- US Patent Document 7,971,073
Adaptive issue queue for reduced power at high performance
patent-application, May 2002
- Buyuktosunoglu, Alper; Schuster, Stanley E.; Brooks, David M.
- US Patent Application 09/971186; 20020053038
System and method utilizing on-chip voltage controlled frequency modulation to manage power consumption
patent-application, October 2002
- Naffziger, Samuel D.; Josephson, Don D.
- US Patent Application 09/811255; 20020140467
System and method for implementing an integrated circuit having dynamically variable power limit
patent-application, June 2004
- Naffziger, Samuel
- US Patent Application 10/320586; 20040117680
Reduced power consumption signal processing methods and apparatus
patent-application, August 2004
- Fitton, Michael Philip; Dolwin, Anthony Craig
- US Patent Application 10/714871; 20040153679
Dynamic voltage scaling for portable devices
patent-application, October 2005
- Kang, Inyup; Ethirajan, Karthikeyan; Severson, Matthew Levi
- US Patent Application 10/814935; 20050218871
System and method for optimized task scheduling in a heterogeneous data processing system
patent-application, July 2006
- Ghiasi, Soraya; Keller, JR., Thomas Walter; Kotla, Ramakrishna
- US Patent Application 11/044607; 20060168571
Scheduling processor voltages and frequencies based on performance prediction and power constraints
patent-application, November 2006
- Ghiasi, Soraya; Keller, JR., Thomas Walter; Kotla, Ramakrishna
- US Patent Application 11/120899; 20060253715
Comparing algorithm for dynamic speed-setting of a low-power CPU
conference, January 1995
- Govil, Kinshuk; Chan, Edwin; Wasserman, Hal
- Proceedings of the 1st annual international conference on Mobile computing and networking - MobiCom '95
A control-theoretic approach to dynamic voltage scheduling
conference, January 2003
- Varma, Ankush; Ganesh, Brinda; Sen, Mainak
- Proceedings of the international conference on Compilers, architectures and synthesis for embedded systems - CASES '03
Works referencing / citing this record:
Voltage droop mitigation in 3D chip system
patent, March 2017
- Xu, Yi; Hu, Xing; Xie, Yuan
- US Patent Document 9,595,508
System and method for improved processing performance
patent, July 2014
- Aguiling, Michael; Alecci, Donald V.
- US Patent Document 8,775,125
