You are required to read and agree to the below before accessing a full-text version of an article in the IDE article repository.

The full-text document you are about to access is subject to national and international copyright laws. In most cases (but not necessarily all) the consequence is that personal use is allowed given that the copyright owner is duly acknowledged and respected. All other use (typically) require an explicit permission (often in writing) by the copyright owner.

For the reports in this repository we specifically note that

  • the use of articles under IEEE copyright is governed by the IEEE copyright policy (available at http://www.ieee.org/web/publications/rights/copyrightpolicy.html)
  • the use of articles under ACM copyright is governed by the ACM copyright policy (available at http://www.acm.org/pubs/copyright_policy/)
  • technical reports and other articles issued by M‰lardalen University is free for personal use. For other use, the explicit consent of the authors is required
  • in other cases, please contact the copyright owner for detailed information

By accepting I agree to acknowledge and respect the rights of the copyright owner of the document I am about to access.

If you are in doubt, feel free to contact webmaster@ide.mdh.se

Measuring Cache Related Pre-emption Delay on a Multiprocessor Real-Time System

Fulltext:


Authors:

Filip Sebek

Note:

<PRE> @InProceedings{RTES01Sebek, author = {Filip Sebek}, title = {Measuring Cache Related Pre-emption Delay on a Multiprocessor Real-Time System}, booktitle = {Proceedings of {IEEE} Workshop on Real-Time Embedded Systems (RTES01)}, year = {2001}, address = {London}, month = dec # "3", } </PRE>

Publication Type:

Conference/Workshop Paper

Venue:

IEEE Workshop on Real-Time Embedded Systems (RTES01)

Abstract

Cache memories in real-time systems can increase performance, but to the cost of unpredictable behavior which gives loose bounds on the worst case execution time analysis. Task pre-emption cause a swap of cache contents with an initial performance dip that is considered as a delay. This delay is necessary in execution time analysis and must be added to each task-switch to determine if the task sets are schedulable.Cache performance and costs have traditionally been estimated through trace-driven simulations, but since representative traces and a true simulation models are hard to accomplish, a physical measurement at the system might be the only way to get the status of the system.This paper suggests two methods to measure the cache related pre-emption delay on a Power PC750 multiprocessor system by using the processors built-in performance monitor. One method is completely hardware-based and the other has a minimal software support. Both methods pass information to an external monitor system that stores data with timestamps in a database for further analysis.

Bibtex

@inproceedings{Sebek284,
author = {Filip Sebek},
title = {Measuring Cache Related Pre-emption Delay on a Multiprocessor Real-Time System},
note = {\textlessPRE\textgreater @InProceedings\textbraceleftRTES01Sebek, author = \textbraceleftFilip Sebek\textbraceright, title = \textbraceleftMeasuring Cache Related Pre-emption Delay on a Multiprocessor Real-Time System\textbraceright, booktitle = \textbraceleftProceedings of \textbraceleftIEEE\textbraceright Workshop on Real-Time Embedded Systems (RTES01)\textbraceright, year = \textbraceleft2001\textbraceright, address = \textbraceleftLondon\textbraceright, month = dec {\#} {"}3{"}, \textbraceright \textless/PRE\textgreater},
month = {December},
year = {2001},
booktitle = {IEEE Workshop on Real-Time Embedded Systems (RTES01)},
url = {http://www.es.mdu.se/publications/284-}
}