BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:derkling

The blue social bookmark and publication sharing system.

entry of derkling:

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

Energy management for real-time embedded applications with compiler support

by: Nevine AbouGhazaleh, Bruce Childers, Daniel Mosse, Rami Melhem, and Matthew Craven

In: LCTES '03: Proceedings of the 2003 ACM SIGPLAN conference on Language, compiler, and tool for embedded systems New York, NY, USA: ACM (2003) , p. 284--293.

Resources (URL, PDF, PS...)

URL:	http://portal.acm.org/citation.cfm?id=780771
DOI:	10.1145/780732.780771

Reducing device energy has become one of the most important challenges to embedded systems designers. Processors with dynamic voltage scaling permit trading performance for reduced energy consumption as a program executes. In this paper, we first present a novel hybrid scheme that uses dynamic voltage scaling to adjust the performance of embedded applications to reduce energy consumption while also meeting time constraints. Our fine grained approach uses the compiler to insert power management hints in the application code. These hints convey path specific run-time information about the program's progress to power management points invoked by the operating system that adjust processor performance. Second we present an algorithm for inserting power management hints along different program paths. Finally, we experimentally evaluate our approach and show that signi cant energy reduction can be achieved. On two embedded applications, MPEG movie decoding and automatic target recognition, our scheme reduces energy by up to 79% over no power management and by up to over 50% static power management. We also experimentally demonstrate that our scheme achieves more energy savings compared to two purely compiler directed schemes.

Description

Energy management for real-time embedded applications with compiler support

BibTeX record

@inproceedings{aboughazaleh03energy,
  abstract = {Reducing device energy has become one of the most important challenges to embedded systems designers. Processors with dynamic voltage scaling permit trading performance for reduced energy consumption as a program executes. In this paper, we first present a novel hybrid scheme that uses dynamic voltage scaling to adjust the performance of embedded applications to reduce energy consumption while also meeting time constraints. Our fine grained approach uses the compiler to insert power management hints in the application code. These hints convey path specific run-time information about the program's progress to power management points invoked by the operating system that adjust processor performance. Second we present an algorithm for inserting power management hints along different program paths. Finally, we experimentally evaluate our approach and show that signi cant energy reduction can be achieved. On two embedded applications, MPEG movie decoding and automatic target recognition, our scheme reduces energy by up to 79% over no power management and by up to over 50% static power management. We also experimentally demonstrate that our scheme achieves more energy savings compared to two purely compiler directed schemes.},
  added-at = {2009-09-06T11:42:47.000+0200},
  address = {New York, NY, USA},
  author = {AbouGhazaleh, Nevine and Childers, Bruce and Mosse, Daniel and Melhem, Rami and Craven, Matthew},
  biburl = {http://www.bibsonomy.org/bibtex/21c917639bb5d8a08d5aa3b34b5ff4d54/derkling},
  booktitle = {LCTES '03: Proceedings of the 2003 ACM SIGPLAN conference on Language, compiler, and tool for embedded systems},
  description = {Energy management for real-time embedded applications with compiler support},
  doi = {http://doi.acm.org/10.1145/780732.780771},
  interhash = {63bc2f219ca6a76fa860ed24cf737619},
  intrahash = {1c917639bb5d8a08d5aa3b34b5ff4d54},
  isbn = {1-58113-647-1},
  keywords = {Compiler Cross-Layer PhD_Background_Mechanisms PhD_Biblio Power-Aware},
  location = {San Diego, California, USA},
  pages = {284--293},
  publisher = {ACM},
  timestamp = {2009-09-06T11:42:47.000+0200},
  title = {Energy management for real-time embedded applications with compiler support},
  url = {http://portal.acm.org/citation.cfm?id=780771},
  year = 2003
}

Endnote record

%0 Conference Paper
%1 aboughazaleh03energy
%A AbouGhazaleh, Nevine
%A Childers, Bruce
%A Mosse, Daniel
%A Melhem, Rami
%A Craven, Matthew
%B LCTES '03: Proceedings of the 2003 ACM SIGPLAN conference on Language, compiler, and tool for embedded systems
%@ 1-58113-647-1
%C New York, NY, USA
%D 2003
%I ACM
%K 
%P 284--293
%T Energy management for real-time embedded applications with compiler support
%R http://doi.acm.org/10.1145/780732.780771
%U http://portal.acm.org/citation.cfm?id=780771
%X Reducing device energy has become one of the most important challenges to embedded systems designers. Processors with dynamic voltage scaling permit trading performance for reduced energy consumption as a program executes. In this paper, we first present a novel hybrid scheme that uses dynamic voltage scaling to adjust the performance of embedded applications to reduce energy consumption while also meeting time constraints. Our fine grained approach uses the compiler to insert power management hints in the application code. These hints convey path specific run-time information about the program's progress to power management points invoked by the operating system that adjust processor performance. Second we present an algorithm for inserting power management hints along different program paths. Finally, we experimentally evaluate our approach and show that signi cant energy reduction can be achieved. On two embedded applications, MPEG movie decoding and automatic target recognition, our scheme reduces energy by up to 79% over no power management and by up to over 50% static power management. We also experimentally demonstrate that our scheme achieves more energy savings compared to two purely compiler directed schemes.

BibSonomy :: publication ::

Energy management for real-time embedded applications with compiler support

Resources (URL, PDF, PS...)

Abstract

Description

BibTeX record

Endnote record