A method for capturing state data on dynamically reconfigurable processors

Vu Manh Tuan, Hideharu Amano

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

1 Citation (Scopus)

Abstract

In a preemptive multitasking environment, when a task is preempted, necessary state information must be correctly preserved in order for the task to be resumed later. For hardware tasks executing on a coarse-grained dynamically reconfigurable processing array (DRPA), a greate amount of state data are usually distributed on many different storage elements. Besides, DRPAs have different architectures using a variety of development tools. This paper addresses such problems and propose a method for capturing the state data of hardware tasks. Based on resource usage analysis, algorithms for identifying preemption points and inserting preemption states subject to user-specified preemption latency are proposed. Also, the integaration of the proposed steps into the system design flow is discussed. The performance degradation caused by preemption is minimized by allowing preemption only at predefined points where demanded resources are small. The evaluation result using a model based on NEC Electronics DRP-1 shows that the proposed method could allow preemption for a certain task satisfying a given preemption latency with reasonable hardware overhead (from 6% to 15%).

Original languageEnglish
Title of host publicationProceedings of the 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008
Pages208-214
Number of pages7
Publication statusPublished - 2008
Event2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008 - Las Vegas, NV, United States
Duration: 2008 Jul 142008 Jul 17

Other

Other2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008
CountryUnited States
CityLas Vegas, NV
Period08/7/1408/7/17

Fingerprint

Hardware
Array processing
Multitasking
Electronic equipment
Systems analysis
Degradation

Keywords

  • Dynamically reconfigurable processor
  • Hardware overhead
  • Preemption algorithm
  • Preemption latency

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Tuan, V. M., & Amano, H. (2008). A method for capturing state data on dynamically reconfigurable processors. In Proceedings of the 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008 (pp. 208-214)

A method for capturing state data on dynamically reconfigurable processors. / Tuan, Vu Manh; Amano, Hideharu.

Proceedings of the 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008. 2008. p. 208-214.

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

Tuan, VM & Amano, H 2008, A method for capturing state data on dynamically reconfigurable processors. in Proceedings of the 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008. pp. 208-214, 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008, Las Vegas, NV, United States, 08/7/14.
Tuan VM, Amano H. A method for capturing state data on dynamically reconfigurable processors. In Proceedings of the 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008. 2008. p. 208-214
Tuan, Vu Manh ; Amano, Hideharu. / A method for capturing state data on dynamically reconfigurable processors. Proceedings of the 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008. 2008. pp. 208-214
@inproceedings{8087688f144d4079ae0a31ae41c40283,
title = "A method for capturing state data on dynamically reconfigurable processors",
abstract = "In a preemptive multitasking environment, when a task is preempted, necessary state information must be correctly preserved in order for the task to be resumed later. For hardware tasks executing on a coarse-grained dynamically reconfigurable processing array (DRPA), a greate amount of state data are usually distributed on many different storage elements. Besides, DRPAs have different architectures using a variety of development tools. This paper addresses such problems and propose a method for capturing the state data of hardware tasks. Based on resource usage analysis, algorithms for identifying preemption points and inserting preemption states subject to user-specified preemption latency are proposed. Also, the integaration of the proposed steps into the system design flow is discussed. The performance degradation caused by preemption is minimized by allowing preemption only at predefined points where demanded resources are small. The evaluation result using a model based on NEC Electronics DRP-1 shows that the proposed method could allow preemption for a certain task satisfying a given preemption latency with reasonable hardware overhead (from 6{\%} to 15{\%}).",
keywords = "Dynamically reconfigurable processor, Hardware overhead, Preemption algorithm, Preemption latency",
author = "Tuan, {Vu Manh} and Hideharu Amano",
year = "2008",
language = "English",
isbn = "1601320647",
pages = "208--214",
booktitle = "Proceedings of the 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008",

}

TY - GEN

T1 - A method for capturing state data on dynamically reconfigurable processors

AU - Tuan, Vu Manh

AU - Amano, Hideharu

PY - 2008

Y1 - 2008

N2 - In a preemptive multitasking environment, when a task is preempted, necessary state information must be correctly preserved in order for the task to be resumed later. For hardware tasks executing on a coarse-grained dynamically reconfigurable processing array (DRPA), a greate amount of state data are usually distributed on many different storage elements. Besides, DRPAs have different architectures using a variety of development tools. This paper addresses such problems and propose a method for capturing the state data of hardware tasks. Based on resource usage analysis, algorithms for identifying preemption points and inserting preemption states subject to user-specified preemption latency are proposed. Also, the integaration of the proposed steps into the system design flow is discussed. The performance degradation caused by preemption is minimized by allowing preemption only at predefined points where demanded resources are small. The evaluation result using a model based on NEC Electronics DRP-1 shows that the proposed method could allow preemption for a certain task satisfying a given preemption latency with reasonable hardware overhead (from 6% to 15%).

AB - In a preemptive multitasking environment, when a task is preempted, necessary state information must be correctly preserved in order for the task to be resumed later. For hardware tasks executing on a coarse-grained dynamically reconfigurable processing array (DRPA), a greate amount of state data are usually distributed on many different storage elements. Besides, DRPAs have different architectures using a variety of development tools. This paper addresses such problems and propose a method for capturing the state data of hardware tasks. Based on resource usage analysis, algorithms for identifying preemption points and inserting preemption states subject to user-specified preemption latency are proposed. Also, the integaration of the proposed steps into the system design flow is discussed. The performance degradation caused by preemption is minimized by allowing preemption only at predefined points where demanded resources are small. The evaluation result using a model based on NEC Electronics DRP-1 shows that the proposed method could allow preemption for a certain task satisfying a given preemption latency with reasonable hardware overhead (from 6% to 15%).

KW - Dynamically reconfigurable processor

KW - Hardware overhead

KW - Preemption algorithm

KW - Preemption latency

UR - http://www.scopus.com/inward/record.url?scp=62649129709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62649129709&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:62649129709

SN - 1601320647

SN - 9781601320643

SP - 208

EP - 214

BT - Proceedings of the 2008 International Conference on Engineering of Reconfigurable Systems and Algorithms, ERSA 2008

ER -