Design issues of prefetching strategies for heterogeneous software dsm
This presentation is the property of its rightful owner.
Sponsored Links
1 / 26

Design Issues of Prefetching Strategies for Heterogeneous Software DSM PowerPoint PPT Presentation


  • 82 Views
  • Uploaded on
  • Presentation posted in: General

Design Issues of Prefetching Strategies for Heterogeneous Software DSM. Author :Ssu-Hsuan Lu, Chien-Lung Chou, Kuang-Jui Wang, Hsiao-Hsi Wang, and Kuan-Ching Li Speaker :Chien-Lung Chou Date :2006/05/18. Outline. Introduction Motivation Related Work Proposed Method

Download Presentation

Design Issues of Prefetching Strategies for Heterogeneous Software DSM

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Design issues of prefetching strategies for heterogeneous software dsm

Design Issues of Prefetching Strategies for Heterogeneous Software DSM

Author :Ssu-Hsuan Lu, Chien-Lung Chou, Kuang-Jui Wang, Hsiao-Hsi Wang, and Kuan-Ching Li

Speaker :Chien-Lung Chou

Date :2006/05/18


Outline

Outline

  • Introduction

  • Motivation

  • Related Work

  • Proposed Method

  • Performance Evaluation

  • Conclusions and Future Work


Introduction

Introduction

  • In Distributed Shared Memory (DSM) systems, it induces:

    • large number of page faults.

    • large number of communication time.


Introduction cont

Introduction (cont.)

  • Page faults and communication time are major overheads in DSM systems.

  • We need additional strategies to reduce page faults and communication time are:

    • Home migration

    • Write vector

    • Prefetching


Introduction cont1

Introduction (cont.)

  • Most traditional prefetching strategies can provide good performance in homogeneous cluster platforms.

  • However, the performance of such strategies may be worse in heterogeneous environment.


Motivation

Motivation

Homogeneous cluster platform.


Motivation cont

Motivation (cont.)

Heterogeneous cluster platform


Motivation cont1

Motivation (cont.)

  • We need to concern about heterogeneous environment.

    • More and more personal computers will be perform computations collectively.

    • Large number of advanced techniques will be develop in this environment.

    • We will usually meet this environment in future.


Related work

Related Work

  • History Prefetching Strategy.

    • It permits home nodes sending data to remote nodes in advance.

  • It has some disadvantages:

    • Accumulated Waiting Phenomenon.

    • Waiting Synchronization Phenomenon.

    • Misprefetch.

    • Home nodes have too much work.


Related work cont

Related Work (cont.)

  • Effective Prefetch Strategy

    • Filtering Unnecessary Prefetches.

    • Distributing Prefetch Overhead.

    • Load Balancing with Barrier Synchronization.

  • Agent Home of prefetching strategy

    • It will find a node that will help home nodes to transfer prefetching data.

    • Thus, it reduces overhead of home nodes.


Proposed method

Proposed Method

Prefetching Strategy in Heterogeneous Environments


Proposed method cont

Proposed Method (cont.)

  • According to above disadvantages, we propose the method that allows

    • home nodes are adjusted to suitable place.

    • high speed processors to execute prefetch in advance.

    • low speed processors to leave the barrier early.


Proposed method cont1

Proposed Method (cont.)

  • First, we distribute home pages to nodes that have better resources.

  • These nodes are suitable to be home nodes because they have better performance.


Proposed method cont2

Proposed Method (cont.)

  • Second, we observe that hosts that have worse resources finish work later, so we adjust policy of prefetching strategy.

  • Originally, all hosts leave barrier at the same time.


Proposed method cont3

Proposed Method (cont.)

  • In our method, the hosts that have worse resources leave barrier after requesting prefetching data.

  • The hosts that have better resources leave barrier after sending prefetching pages to hosts that have worse resources.


Proposed method cont4

Proposed Method (cont.)

  • Third, we also observe that hosts that have better resources spend large amount of idle time during barrier in heterogeneous environment.

  • It raises execution time and barrier time.


Proposed method cont5

Proposed Method (cont.)

  • We utilize idle time in barrier of hosts that have better resources to perform prefetching to each other.


Proposed method cont6

Proposed Method (cont.)

Our Proposed Method


Performance evaluation

Performance Evaluation

  • Experimental Platform - Hardware


Performance evaluation cont

Performance Evaluation (cont.)

  • Experimental Platform - Software

    • Linux Fedora Core 3.

    • Kernel 2.6.9.

    • JIAJIA DSM software.


Performance evaluation cont1

Performance Evaluation (cont.)

The Idle Time in Barrier for IS Application


Performance evaluation cont2

Performance Evaluation (cont.)

The Idle Time in Barrier for Merge Application


Performance evaluation cont3

Performance Evaluation (cont.)

Performance Benefits


Conclusions and future work

Conclusions and Future Work

  • In heterogeneous environment, benefits of original prefetching strategies are limited.

  • In this paper, we utilized idle time to improve overall performance.

  • In the best situation, our proposed method could reduce idle time in barrier of about 60%.


Conclusions and future work cont

Conclusions and Future Work (cont.)

  • In the future, we will make effort to find a method to optimize the use of idle time in barrier.

  • In addition, we will also investigate the parallel program execution with issues about dynamic CPU loads include in our next development stage.


Design issues of prefetching strategies for heterogeneous software dsm

Thank You!!


  • Login