Using data replication to reduce communication energy on chip multiprocessors

Mahmut Kandemir, G. Chen, F. Li, I. Demirkiran

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

6 Citations (Scopus)

Abstract

Chip multiprocessors are gaining popularity as they are very suitable for data-intensive embedded and high-end processing. In particular, array-intensive embedded image and video applications can benefit a lot from these architectures due to coarse-grain parallelization they offer. However, if not optimized, interprocessor communication can be a major energy consumer. Focusing on a distributed memory chip multiprocessor architecture and array-intensive embedded applications, this paper proposes a compiler-based communication minimization strategy based on data replication. The proposed scheme replicates shared data items across the memories of the processors in a controlled fashion (i.e., under a memory limit), with the goal of eliminating the otherwise necessary interprocessor communication.

Original languageEnglish (US)
Title of host publicationProceedings of the 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005
Pages769-772
Number of pages4
StatePublished - Dec 1 2005
Event2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005 - Shanghai, China
Duration: Jan 18 2005Jan 21 2005

Publication series

NameProceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
Volume2

Other

Other2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005
CountryChina
CityShanghai
Period1/18/051/21/05

Fingerprint

Data storage equipment
Communication
Processing

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering

Cite this

Kandemir, M., Chen, G., Li, F., & Demirkiran, I. (2005). Using data replication to reduce communication energy on chip multiprocessors. In Proceedings of the 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005 (pp. 769-772). [1466454] (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC; Vol. 2).
Kandemir, Mahmut ; Chen, G. ; Li, F. ; Demirkiran, I. / Using data replication to reduce communication energy on chip multiprocessors. Proceedings of the 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005. 2005. pp. 769-772 (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC).
@inproceedings{8da585faf141427ea05adb9d68a48517,
title = "Using data replication to reduce communication energy on chip multiprocessors",
abstract = "Chip multiprocessors are gaining popularity as they are very suitable for data-intensive embedded and high-end processing. In particular, array-intensive embedded image and video applications can benefit a lot from these architectures due to coarse-grain parallelization they offer. However, if not optimized, interprocessor communication can be a major energy consumer. Focusing on a distributed memory chip multiprocessor architecture and array-intensive embedded applications, this paper proposes a compiler-based communication minimization strategy based on data replication. The proposed scheme replicates shared data items across the memories of the processors in a controlled fashion (i.e., under a memory limit), with the goal of eliminating the otherwise necessary interprocessor communication.",
author = "Mahmut Kandemir and G. Chen and F. Li and I. Demirkiran",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
isbn = "0780387368",
series = "Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC",
pages = "769--772",
booktitle = "Proceedings of the 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005",

}

Kandemir, M, Chen, G, Li, F & Demirkiran, I 2005, Using data replication to reduce communication energy on chip multiprocessors. in Proceedings of the 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005., 1466454, Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC, vol. 2, pp. 769-772, 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005, Shanghai, China, 1/18/05.

Using data replication to reduce communication energy on chip multiprocessors. / Kandemir, Mahmut; Chen, G.; Li, F.; Demirkiran, I.

Proceedings of the 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005. 2005. p. 769-772 1466454 (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC; Vol. 2).

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

TY - GEN

T1 - Using data replication to reduce communication energy on chip multiprocessors

AU - Kandemir, Mahmut

AU - Chen, G.

AU - Li, F.

AU - Demirkiran, I.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Chip multiprocessors are gaining popularity as they are very suitable for data-intensive embedded and high-end processing. In particular, array-intensive embedded image and video applications can benefit a lot from these architectures due to coarse-grain parallelization they offer. However, if not optimized, interprocessor communication can be a major energy consumer. Focusing on a distributed memory chip multiprocessor architecture and array-intensive embedded applications, this paper proposes a compiler-based communication minimization strategy based on data replication. The proposed scheme replicates shared data items across the memories of the processors in a controlled fashion (i.e., under a memory limit), with the goal of eliminating the otherwise necessary interprocessor communication.

AB - Chip multiprocessors are gaining popularity as they are very suitable for data-intensive embedded and high-end processing. In particular, array-intensive embedded image and video applications can benefit a lot from these architectures due to coarse-grain parallelization they offer. However, if not optimized, interprocessor communication can be a major energy consumer. Focusing on a distributed memory chip multiprocessor architecture and array-intensive embedded applications, this paper proposes a compiler-based communication minimization strategy based on data replication. The proposed scheme replicates shared data items across the memories of the processors in a controlled fashion (i.e., under a memory limit), with the goal of eliminating the otherwise necessary interprocessor communication.

UR - http://www.scopus.com/inward/record.url?scp=77956195523&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956195523&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780387368

SN - 9780780387362

T3 - Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC

SP - 769

EP - 772

BT - Proceedings of the 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005

ER -

Kandemir M, Chen G, Li F, Demirkiran I. Using data replication to reduce communication energy on chip multiprocessors. In Proceedings of the 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005. 2005. p. 769-772. 1466454. (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC).