A Method for the On-Line Use of Off-Line Derived Remappings ofIterative Automatic Target Recognition Tasks onto a Particular Class ofHeterogeneous Parallel Platforms

Authors:
John R. Budenske;Ranga S. Ramanujan;Howard Jay Siegel
Affiliations:
-;Architecture Technology Corporation, P.O. Box 24344, Minneapolis, MN 55424, USA, {budenske, ranga}@atcorp.com;Parallel Processing Laboratory, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907-1285, USA, hj@purdue.edu
Venue:
The Journal of Supercomputing
Year:
1998

Citing 15
Cited 2

A model for an intelligent operating system for executing image understanding tasks on a reconfigurable parallel architecture

Journal of Parallel and Distributed Computing
Allocating Modules to Processors in a Distributed System

IEEE Transactions on Software Engineering
Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Mapping Computer-Vision-Related Tasks onto Reconfigurable Parallel-Processing Systems

Computer
Genetic algorithms: A Survey

Computer
Genetic-Algorithm Programming Environments

Computer
Software support for heterogeneous computing

ACM Computing Surveys (CSUR)
Task matching and scheduling in heterogeneous computing environments using a genetic-algorithm-based approach

Journal of Parallel and Distributed Computing - Special issue on parallel evolutionary computing
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Heterogeneous Computing: Challenges and Opportunities

Computer
A Distributed Heterogeneous Supercomputing Management System

Computer
Implementations of a Feature-Based Visual Tracking Algorithm on Two MIMD Machines Mark Bernd

ICPP '97 Proceedings of the international Conference on Parallel Processing
Mercury Computer Systems' modular heterogeneous RACE(R) multicomputer

HCW '97 Proceedings of the 6th Heterogeneous Computing Workshop (HCW '97)
SmartNet: a scheduling framework for heterogeneous computing

ISPAN '96 Proceedings of the 1996 International Symposium on Parallel Architectures, Algorithms and Networks
Theory and practice in system-level design of application-specific heterogeneous multiprocessors

Theory and practice in system-level design of application-specific heterogeneous multiprocessors

An Overview of MSHN: The Management System for Heterogeneous Networks

HCW '99 Proceedings of the Eighth Heterogeneous Computing Workshop
A semi-static approach to mapping dynamic iterative tasks onto heterogeneous computing systems

Journal of Parallel and Distributed Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study focuses on a particular application domain (iterativeautomatic target recognition tasks) and an associated specific class ofdedicated heterogeneous parallel hardware platforms. For thecomputational environment considered, a methodology is presented forthe on-line operating system to decide heuristically whether to performa remapping of the application onto the platform based on informationgenerated from input data by the application during execution. If thedecision is to remap, the operating system will be able to select amapping, which is appropriate for the given state of the application,from a stored set of mappings that were previously derived with anoff-line heuristic.