Exploiting shared scratch pad memory space in embedded multiprocessor systems

Mahmut Kandemir, J. Ramanujam, A. Choudhary

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

In this paper, we present a compiler strategy to optimize data accesses in regular array-intensive applications running on embedded multiprocessor environments. Specifically, we propose an optimization algorithm that targets the reduction of extra off-chip memory accesses caused by inter-processor communication. This is achieved by increasing the application-wide reuse of data that resides in the scratch-pad memories of processors. Our experimental results obtained on four array-intensive image processing applications indicate that exploiting inter-processor data sharing can reduce the energy-delay product by as much as 33.8% (and 24.3% on average) on a four-processor embedded system. The results also show that the proposed strategy is robust in the sense that it gives consistently good results over a wide range of several architectural parameters.

Original languageEnglish (US)
Pages (from-to)219-224
Number of pages6
JournalProceedings - Design Automation Conference
DOIs
StatePublished - Jan 1 2002

Fingerprint

Data storage equipment
Embedded systems
Image processing
Communication

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

@article{96b3482e6fdd433cabcc9fbf177aae83,
title = "Exploiting shared scratch pad memory space in embedded multiprocessor systems",
abstract = "In this paper, we present a compiler strategy to optimize data accesses in regular array-intensive applications running on embedded multiprocessor environments. Specifically, we propose an optimization algorithm that targets the reduction of extra off-chip memory accesses caused by inter-processor communication. This is achieved by increasing the application-wide reuse of data that resides in the scratch-pad memories of processors. Our experimental results obtained on four array-intensive image processing applications indicate that exploiting inter-processor data sharing can reduce the energy-delay product by as much as 33.8{\%} (and 24.3{\%} on average) on a four-processor embedded system. The results also show that the proposed strategy is robust in the sense that it gives consistently good results over a wide range of several architectural parameters.",
author = "Mahmut Kandemir and J. Ramanujam and A. Choudhary",
year = "2002",
month = "1",
day = "1",
doi = "10.1109/DAC.2002.1012623",
language = "English (US)",
pages = "219--224",
journal = "Proceedings - Design Automation Conference",
issn = "0738-100X",

}

Exploiting shared scratch pad memory space in embedded multiprocessor systems. / Kandemir, Mahmut; Ramanujam, J.; Choudhary, A.

In: Proceedings - Design Automation Conference, 01.01.2002, p. 219-224.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Exploiting shared scratch pad memory space in embedded multiprocessor systems

AU - Kandemir, Mahmut

AU - Ramanujam, J.

AU - Choudhary, A.

PY - 2002/1/1

Y1 - 2002/1/1

N2 - In this paper, we present a compiler strategy to optimize data accesses in regular array-intensive applications running on embedded multiprocessor environments. Specifically, we propose an optimization algorithm that targets the reduction of extra off-chip memory accesses caused by inter-processor communication. This is achieved by increasing the application-wide reuse of data that resides in the scratch-pad memories of processors. Our experimental results obtained on four array-intensive image processing applications indicate that exploiting inter-processor data sharing can reduce the energy-delay product by as much as 33.8% (and 24.3% on average) on a four-processor embedded system. The results also show that the proposed strategy is robust in the sense that it gives consistently good results over a wide range of several architectural parameters.

AB - In this paper, we present a compiler strategy to optimize data accesses in regular array-intensive applications running on embedded multiprocessor environments. Specifically, we propose an optimization algorithm that targets the reduction of extra off-chip memory accesses caused by inter-processor communication. This is achieved by increasing the application-wide reuse of data that resides in the scratch-pad memories of processors. Our experimental results obtained on four array-intensive image processing applications indicate that exploiting inter-processor data sharing can reduce the energy-delay product by as much as 33.8% (and 24.3% on average) on a four-processor embedded system. The results also show that the proposed strategy is robust in the sense that it gives consistently good results over a wide range of several architectural parameters.

UR - http://www.scopus.com/inward/record.url?scp=0036058776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036058776&partnerID=8YFLogxK

U2 - 10.1109/DAC.2002.1012623

DO - 10.1109/DAC.2002.1012623

M3 - Article

SP - 219

EP - 224

JO - Proceedings - Design Automation Conference

JF - Proceedings - Design Automation Conference

SN - 0738-100X

ER -