Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Toronto

$35,000.00

Programming FPGAs using Software via Overlay Processing Engines

FY 2014-15

Summary
Powerful and cheap computing drives innovation and leads to new technologies in many fields that improve lives around the world. However, if we want to continue the rate of improvement in computing performance seen by the last decades, then we must now innovate ways to reduce the power consumption of computers while improving their performance---and Field-Programmable Gate Arrays (FPGAs) are one of the most promising ways we might overcome this challenge. FPGAs are integrated circuits that are organized such that they can be programmed and reprogrammed to emulate a hardware design that exactly matches the requirements of an application, and hence can have much better performance-per-watt than alternatives. This has led to growing commercial interest in using FPGAs for general-purpose and scientific computing---however, those communities mainly employ software programmers that use high-level programming languages such as C, C++, and Fortran, and that normally wait only minutes to compile a program. In contrast FPGAs currently require expert hardware designers to program and debug them, and a large FPGA design can take up to a day to compile. A potential solution to this roadblock to the adoption of FPGAs in general purpose computing is overlay processing engines: application-specific processor designs that can be placed on an FPGA but are themselves programmable by high-level programming languages, allowing software programmers to more easily and quickly capitalize on the potential of FPGAs. The proposed research program will study and develop the worlds most powerful overlay processing engines for FPGAs by creating novel and aggressive FPGA-centric processor architectures, and by leveraging compiler support to increase parallelism and performance while keeping hardware simple. Processing engines of the proposed calibre have yet to be designed and proven for FPGAs, but if successful will allow FPGAs to be adopted by a much broader range of companies, application developers, and scientists.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
262057-2013
Name nom
Steffan, John
Department département
Electrical & Computer Engineering
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2013
Award amount
35000
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
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
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
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
2
Nb partie
2
Application title
Programming FPGAs using Software via Overlay Processing Engines
Keyword
NSERC
Application summary
Powerful and cheap computing drives innovation and leads to new technologies in many fields that improve lives around the world. However, if we want to continue the rate of improvement in computing performance seen by the last decades, then we must now innovate ways to reduce the power consumption of computers while improving their performance---and Field-Programmable Gate Arrays (FPGAs) are one of the most promising ways we might overcome this challenge. FPGAs are integrated circuits that are organized such that they can be programmed and reprogrammed to emulate a hardware design that exactly matches the requirements of an application, and hence can have much better performance-per-watt than alternatives. This has led to growing commercial interest in using FPGAs for general-purpose and scientific computing---however, those communities mainly employ software programmers that use high-level programming languages such as C, C++, and Fortran, and that normally wait only minutes to compile a program. In contrast FPGAs currently require expert hardware designers to program and debug them, and a large FPGA design can take up to a day to compile. A potential solution to this roadblock to the adoption of FPGAs in general purpose computing is overlay processing engines: application-specific processor designs that can be placed on an FPGA but are themselves programmable by high-level programming languages, allowing software programmers to more easily and quickly capitalize on the potential of FPGAs. The proposed research program will study and develop the worlds most powerful overlay processing engines for FPGAs by creating novel and aggressive FPGA-centric processor architectures, and by leveraging compiler support to increase parallelism and performance while keeping hardware simple. Processing engines of the proposed calibre have yet to be designed and proven for FPGAs, but if successful will allow FPGAs to be adopted by a much broader range of companies, application developers, and scientists.