Grant: Collaborative Research and Development Grants
University of Toronto
$42,500.00
A self-accelerating adaptive processor
EF 2011-12
Résumé
High current density in sub-100 nm ICs has created a ""power wall"", limiting the rate of clock speed scaling in general purpose microprocessors. Attaining higher speed performance and improved energy efficiency motivates the need to develop processors that are customized to specific applications. Performing computations in custom hardware can deliver orders of magnitude improvement in energy efficiency and throughput. However, custom processor design, as with any hardware design, is difficult and time-consuming compared to software design. Moreover, hardware design in VHDL or Verilog lies outside the skill set of most software programmers. A further challenge is in identifying what custom hardware would be of benefit to the speed and/or power of an application, as this depends on the run-time and power profile of the application under specific datasets. There is a need, then, for the rapid and automated design of processors tailored for particular applications.
We are building a self-accelerating adaptive processor by modifying the architecture of a standard processor to create the ability to profile the execution of its own code. Using this profiling ability, our unique processor will be able to identify sections of its code that require optimization. Specifically, the profiling results will drive the selection of program code segments to be re-targeted to custom hardware from their original high-level language implementation. C-to-RTL synthesis will be used, with the RTL subsequently compiled by standard back-end tools. Once the hardware ""compute accelerators"" are available, the program binary will be modified to access the accelerators accordingly. Programmable logic devices, such as field-programmable gate arrays (FPGAs), are an ideal implementation platform for such adaptive processors, as FPGAs can be configured in milliseconds to implement any digital circuit. The reconfigurability of FPGAs also permits functionality to evolve over time, based on application needs.
Programme
Collaborative Research and Development Grants
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
417430-2011
Name nom
Anderson, Jason
Department département
Electrical and Computer Engineering, Edward S. Rogers Sr. Department of
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2011
Award amount
42500
Program id
CRDPJ
Program nane en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2701
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Computer hardware
Research subject fr
Matériel informatique
Partie
1
Nb partie
3
Application title
A self-accelerating adaptive processor
Keyword
NSERC
Application summary
High current density in sub-100 nm ICs has created a ""power wall"", limiting the rate of clock speed scaling in general purpose microprocessors. Attaining higher speed performance and improved energy efficiency motivates the need to develop processors that are customized to specific applications. Performing computations in custom hardware can deliver orders of magnitude improvement in energy efficiency and throughput. However, custom processor design, as with any hardware design, is difficult and time-consuming compared to software design. Moreover, hardware design in VHDL or Verilog lies outside the skill set of most software programmers. A further challenge is in identifying what custom hardware would be of benefit to the speed and/or power of an application, as this depends on the run-time and power profile of the application under specific datasets. There is a need, then, for the rapid and automated design of processors tailored for particular applications.
We are building a self-accelerating adaptive processor by modifying the architecture of a standard processor to create the ability to profile the execution of its own code. Using this profiling ability, our unique processor will be able to identify sections of its code that require optimization. Specifically, the profiling results will drive the selection of program code segments to be re-targeted to custom hardware from their original high-level language implementation. C-to-RTL synthesis will be used, with the RTL subsequently compiled by standard back-end tools. Once the hardware ""compute accelerators"" are available, the program binary will be modified to access the accelerators accordingly. Programmable logic devices, such as field-programmable gate arrays (FPGAs), are an ideal implementation platform for such adaptive processors, as FPGAs can be configured in milliseconds to implement any digital circuit. The reconfigurability of FPGAs also permits functionality to evolve over time, based on application needs.