Grant: Discovery Grants Program - Individual
University of New Brunswick
$21,000.00
Software tools for reconfigurable platforms
EF 2010-11
Résumé
One route to achieving better computer performance is to attach peripheral boards with reconfigurable hardware units. By configuring the chip appropriately, one can provide a complete System-on-Chip solution that is optimal for a given set of factors. (i.e. cost and time to market). To improve performance, the most CPU-intensive parts of the program can be compiled into a custom hardware solution for a programmable device. If communication overhead is kept under control, the result should be a speed improvement as well as a reduction in development time.
However, the challenges for anyone attempting to implement such a mixed software-hardware solution are enormous. The programming languages, the compilers, the simulation tools and the run-time monitoring tools all provide woefully inadequate assistance. In general, the tools rely heavily on an expert system designer to guide and direct the process. The payoffs would be enormous if development tools could guide the process and make effective use of a hybrid microporcessor - configurable unit platform.
I propose to work on the following aspects of the problem:
1) Decomposing a program into those components which are best suited to be sped up by a configurable hardware implementation, and those remaining components which are best handled by traditional software.
2) Developing programming language constructs and techniques which facilitate #1.
3) Enhancing existing compilers to support the new programming language constructs.
4) Developing simulation tools which wil enable program decompositions to be tested and evaluated.
Assorted applications available from my previous work relating to computational biology, co-designed virtual machines, and logic synthesis will be used to validate the proposed research.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
New Brunswick, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
262177-2007
Name nom
Kent, Kenneth
Department département
Computer Science, Faculty of
Organization id
75
Institution établissement
University of New Brunswick
Province en
New Brunswick
Province fr
Nouveau-Brunswick
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2007
Award amount
21000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
330
Committee name en
Computing and Information Sciences - A
Committee name fr
Informatique - A
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2719
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Computer architecture and design
Research subject fr
Architecture d'ordinateur et conception
Partie
4
Nb partie
5
Application title
Software tools for reconfigurable platforms
Keyword
NSERC
Application summary
One route to achieving better computer performance is to attach peripheral boards with reconfigurable hardware units. By configuring the chip appropriately, one can provide a complete System-on-Chip solution that is optimal for a given set of factors. (i.e. cost and time to market). To improve performance, the most CPU-intensive parts of the program can be compiled into a custom hardware solution for a programmable device. If communication overhead is kept under control, the result should be a speed improvement as well as a reduction in development time.
However, the challenges for anyone attempting to implement such a mixed software-hardware solution are enormous. The programming languages, the compilers, the simulation tools and the run-time monitoring tools all provide woefully inadequate assistance. In general, the tools rely heavily on an expert system designer to guide and direct the process. The payoffs would be enormous if development tools could guide the process and make effective use of a hybrid microporcessor - configurable unit platform.
I propose to work on the following aspects of the problem:
1) Decomposing a program into those components which are best suited to be sped up by a configurable hardware implementation, and those remaining components which are best handled by traditional software.
2) Developing programming language constructs and techniques which facilitate #1.
3) Enhancing existing compilers to support the new programming language constructs.
4) Developing simulation tools which wil enable program decompositions to be tested and evaluated.
Assorted applications available from my previous work relating to computational biology, co-designed virtual machines, and logic synthesis will be used to validate the proposed research.