Open AccessPSO based optimization of worst-case execution time for ASIP application
Author(s) -
Mood Venkanna,
Rameshwar Rao,
P. Chandra Sekhar
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i2.33.14162
Subject(s) - computer science , scheduling (production processes) , execution time , worst case execution time , automotive industry , particle swarm optimization , set (abstract data type) , upper and lower bounds , task (project management) , critical path method , host (biology) , embedded system , distributed computing , mathematical optimization , algorithm , programming language , ecology , biology , mathematical analysis , mathematics , management , systems engineering , engineering , economics , aerospace engineering
Industrial requires hard real-time systems for safety and critical applications like automotive, Aeronautics, manufacturing control and train industries. Hard Real-Time Systems’ embedded controllers are with expectation of complete the tasks within a certain time bounds reliably including task scheduling. The estimation of upper bound limits corresponding to the execution times is often termed as the Worst-Case Execution Times (WCETs). It is an essential step in developing and validating the hard real-time systems. Particularly, the upper bounds need to satisfy these constraints related to the execution times. However, it is often not feasible many times to set upper bounds on execution times for programs. In present work, the problem of choosing reconfigurable Custom Instructions (CIs) is accomplished by optimizing the WCET corresponding to an application. This issue is designed using Particle Swarm Optimization (PSO) based program for a path analysis. The work emphasizes on the effectiveness of optimizing the WCET when applied to a reconfigurable processor. It evaluates a compound application of multimedia with a host of reconfigurable CIs corresponding to a number of hardware parameters.