Login | Register

Early and Accurate Modeling of Streaming Embedded Applications

Title:

Early and Accurate Modeling of Streaming Embedded Applications

Lee, Richard (2013) Early and Accurate Modeling of Streaming Embedded Applications. Masters thesis, Concordia University.

[img]
Preview
Text (application/pdf)
Lee_MASc_F2013.pdf - Accepted Version
Available under License Spectrum Terms of Access.
2MB

Abstract

This thesis presents automatic generation of fast and accurate timed models of streaming embedded applications, before the complete software-hardware platform is available. We focus on streaming applications, because they tend to be the most compute-intensive applications on mobile devices. Therefore, it is critical to optimize the hardware-software platform for streaming applications, as early as possible in the design process. As such, fast, accurate and early models are essential for hardware-software optimization.
Our design methodology is as follows. First, a measurement model is generated and executed, on the target processor, to predict the computation delays in an application. Next, the delays are annotated in the application code to generate a host-compiled model of the application. Our experiments show that such models can be generated and simulated at very high speed and accurately predict the computation load offered by the application. Our results with large streaming media applications, such as music and voice codecs, show that the estimation errors are less than 3.3%, while providing very high simulation speed. Therefore, using our models, embedded system designers can perform early optimizations to the system architecture with high confidence.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Electrical and Computer Engineering
Item Type:Thesis (Masters)
Authors:Lee, Richard
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Electrical and Computer Engineering
Date:12 August 2013
Thesis Supervisor(s):Abdi, Samar
ID Code:977498
Deposited By: RICHARD LEE
Deposited On:18 Nov 2013 20:34
Last Modified:18 Jan 2018 17:44
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Back to top Back to top