An intra-task DVFS technique based on statistical analysis of hardware events

Hiroshi Sasaki, Yoshimichi Ikeda, Masaaki Kondo, Hiroshi Nakamura

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

8 Citations (Scopus)

Abstract

The importance and demand for various types of optimization techniques for program execution is growing rapidly. In particular, dynamic optimization techniques are regarded as important. Although conventional techniques usually generated an execution model for dynamic optimization by qualitatively analyzing the behaviors of computer systems in a knowledge-based manner, the proposed technique generates models by statistically analyzing the behaviors from quantitative data of hardware events. In the present paper, a novel dynamic voltage and frequency scaling (DVFS) method based on statistical analysis is proposed. The proposed technique is a hybrid technique in which static information, such as the breakpoint of program phases and, dynamic information, such as the number of cache misses given by the performance counter, are used together. Relationships between the performance and values of performance counters are learned statistically in advance. The compiler then inserts a run-time code for predicting the performance and setting the appropriate frequency/voltage depending on the predicted performance. The proposed technique can greatly reduce the energy consumption while satisfying soft timing constraints.

Original languageEnglish
Title of host publication2007 Computing Frontiers, Conference Proceedings
Pages123-130
Number of pages8
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event4th Conference On Computing Frontiers 2007 - Ischia, Italy
Duration: 2007 May 72007 May 9

Publication series

Name2007 Computing Frontiers, Conference Proceedings

Conference

Conference4th Conference On Computing Frontiers 2007
Country/TerritoryItaly
CityIschia
Period07/5/707/5/9

Keywords

  • DVFS
  • Hardware performance counters
  • Performance estimation
  • Statistical analysis

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'An intra-task DVFS technique based on statistical analysis of hardware events'. Together they form a unique fingerprint.

Cite this