Grant: Engage Grants Program
Concordia University
$25,000.00
Automatic generation of application models for embedded systems
EF 2010-11
Résumé
Consumer interest in high-end smart phones is pushing manufacturers to include more and more features and capabilities seen in PC desktops. As the complexity of the designed System-on-Chip increases, pre-silicon performance investigations are difficult to do without appropriate tools and methodologies. Application models for embedded systems are needed for early performance analysis before availability of either hardware or software. Current practice based on traffic generators is not sufficiently accurate to model various realistic use cases. A better option is to replace some of the traffic generators by a more precise representation of the application running on the CPUs. However, development of such representations is a manual and time consuming job. The primary objective of this project is to understand which code structures must be implemented in the application model and which details may be abstracted away so that the application model can be automatically generated.
The experiment will rely on source code targeted for the QNX real-time operating system (RTOS). Two use cases will be developed: the first an MP3 music playback and the second an MP3 playback running concurrently to a voice call, implemented as a Vocoder (voice codec) application. The idea is to model the software architecture including OS communication (thread, IPC, ISR, etc.) in OSCI SystemC. Once the application is modeled, it will be mapped to target MicroBlaze processor for performance validation.
The proposed research will benefit RIM by enabling early optimization of embedded systems and rapid design space exploration, thereby alleviating the problems of current ad-hoc manual modeling methodologies. The success of our research project would engender technologies that can produce more efficient and innovative embedded systems in a cost-effective manner, thereby making RIM's products and services more competitive in the global marketplace.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
412120-2010
Name nom
Abdi, Samar
Department département
Electrical and Computer Engineering
Organization id
70
Institution établissement
Concordia University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2010
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2500
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Electrical and electronic engineering
Research subject fr
Génie électrique et électronique
Partie
1
Nb partie
1
Application title
Automatic generation of application models for embedded systems
Keyword
NSERC
Application summary
Consumer interest in high-end smart phones is pushing manufacturers to include more and more features and capabilities seen in PC desktops. As the complexity of the designed System-on-Chip increases, pre-silicon performance investigations are difficult to do without appropriate tools and methodologies. Application models for embedded systems are needed for early performance analysis before availability of either hardware or software. Current practice based on traffic generators is not sufficiently accurate to model various realistic use cases. A better option is to replace some of the traffic generators by a more precise representation of the application running on the CPUs. However, development of such representations is a manual and time consuming job. The primary objective of this project is to understand which code structures must be implemented in the application model and which details may be abstracted away so that the application model can be automatically generated.
The experiment will rely on source code targeted for the QNX real-time operating system (RTOS). Two use cases will be developed: the first an MP3 music playback and the second an MP3 playback running concurrently to a voice call, implemented as a Vocoder (voice codec) application. The idea is to model the software architecture including OS communication (thread, IPC, ISR, etc.) in OSCI SystemC. Once the application is modeled, it will be mapped to target MicroBlaze processor for performance validation.
The proposed research will benefit RIM by enabling early optimization of embedded systems and rapid design space exploration, thereby alleviating the problems of current ad-hoc manual modeling methodologies. The success of our research project would engender technologies that can produce more efficient and innovative embedded systems in a cost-effective manner, thereby making RIM's products and services more competitive in the global marketplace.