Grant: Strategic Projects Supplemental Competition
École de technologie supérieure
$84,750.00
Multi level partitioning of signal processing algorithms for multiprocessor SoC
FY 2008-09
Summary
The growing demand for connectivity induces the wireless communication research community to constantly
innovate. The novel techniques which are currently being explored allow to significantly increase spectral
efficiency. However, a larger number of users and greater amounts of information on the same bandwidth
require increased signal processing capacities. In this context, the computing power of programmable platforms
has considerably increased, thereby requiring designers to deal with the exponential rise of their complexity.
Due to the very intense competition in this market, the industry and designers try to get the most out of all the
techniques that are likely to speed up their design process and to optimize the performances. The current
research project conducted by Professors Thibeault and Gagnon in collaboration with Octasic since May 2006
has allowed to demonstrate the importance of partitioning and that this crucial stage constitutes a bottleneck
during the design process.
This research proposal aims to explore various ways to optimize partitioning. These approaches are compared
for a multiprocessor platform with signal processing systems in order to achieve a judicious allocation of
available resources. The specific needs of the final application will also be considered. Constrained and
unconstrained partitioning scenarios will be compared. The aim of the unconstrained scenario is to manage the
partitioning problem at a high level of abstraction with a minimum of initial constraints. It is based on a
metaheuristic evolutionary algorithm which has the capacity to solve such complex problems. It will be
combined to two other constrained partitioning scenarios in order to evaluate its full potential. The novelty of
this project resides in the exploration of several partitioning techniques for a reduced set of criteria. They are
specifically evaluated for Software-Defined Radio applications with multi-user transmission and reception.
These applications are available and continuously evaluated in our laboratories.
Program
Strategic Projects Supplemental Competition
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
356885-2007
Name nom
Gagnon, François
Department département
Génie électrique
Organization id
53
Institution établissement
École de technologie supérieure
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2008
Competition year année de concours
2007
Award amount
84750
Program id
STPSC
Program nane en
Strategic Projects Supplemental Competition
Program name fr
Projets stratégiques compétition supplémentaire
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1067
Committee name en
Strategic Advanced Communications and Management of Information 2
Committee name fr
Stratégique -Technologies avancées de communication et de gestion de l'information 2
Area of application code
805
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Communications technologies (satellites, radar, etc.)
Area of application fr
Technologie des télécommunications (satellites, radar,etc.)
Research subject code
2519
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Microelectronics
Research subject fr
Microélectronique
Partie
2
Nb partie
2
Application title
Multi level partitioning of signal processing algorithms for multiprocessor SoC
Keyword
NA
Application summary
The growing demand for connectivity induces the wireless communication research community to constantly
innovate. The novel techniques which are currently being explored allow to significantly increase spectral
efficiency. However, a larger number of users and greater amounts of information on the same bandwidth
require increased signal processing capacities. In this context, the computing power of programmable platforms
has considerably increased, thereby requiring designers to deal with the exponential rise of their complexity.
Due to the very intense competition in this market, the industry and designers try to get the most out of all the
techniques that are likely to speed up their design process and to optimize the performances. The current
research project conducted by Professors Thibeault and Gagnon in collaboration with Octasic since May 2006
has allowed to demonstrate the importance of partitioning and that this crucial stage constitutes a bottleneck
during the design process.
This research proposal aims to explore various ways to optimize partitioning. These approaches are compared
for a multiprocessor platform with signal processing systems in order to achieve a judicious allocation of
available resources. The specific needs of the final application will also be considered. Constrained and
unconstrained partitioning scenarios will be compared. The aim of the unconstrained scenario is to manage the
partitioning problem at a high level of abstraction with a minimum of initial constraints. It is based on a
metaheuristic evolutionary algorithm which has the capacity to solve such complex problems. It will be
combined to two other constrained partitioning scenarios in order to evaluate its full potential. The novelty of
this project resides in the exploration of several partitioning techniques for a reduced set of criteria. They are
specifically evaluated for Software-Defined Radio applications with multi-user transmission and reception.
These applications are available and continuously evaluated in our laboratories.
