Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of British Columbia

$29,000.00

Low-cost, high-performance with FPGAs, structured ASICs, and processor arrays

EF 2009-10

Résumé
Field-programmable gate arrays (FPGA) are a vital technology invented 25 years ago to build digital hardware. The key strengths of the technology are instant manufacturing, no up-front manufacturing costs, and the ability to to fix hardware bugs or add features at no cost. These strengths are obtained by prefabricating a generic logic circuit that is configured by the customer using computer-aided design tools. Despite their advantages, FPGAs are estimated to be 40x less dense, 4x slower, and use 12x more power than ASICs. Improvements and alternatives to FPGAs are needed to overcome these disadvantages. FPGA interconnect dominates the area, power, and delay of the device. FPGA tools cannot easily map parallel software into FPGAs. Structured ASICs are a promising alternative to FPGAs; they vastly improve density, power, and delay by premanufacturing most (but not all) of the semiconductor masks. Single-chip massively parallel processor arrays are a promising alternative to run parallel software, but they can also used to implement high-performance and high-density computaitonal circuits with much faster mapping runtimes and higher capacity limits. Together, these three devices provide very low-cost accessibility to the latest semiconductor technology for implementing digital hardware and highly parallel systems. The goals of this research are to realize advances in three areas: improved FPGA processing speed through interconnect optimization and vector processing, improved structured ASICs with easier design tools, and demonstrate the ability to efficiently map circuits to massively parallel processor arrays. Combining hardware performance with software cost and ease-of-use leads to dramatic improvements in cost/performance ratio. Achieving this convergence is a key enabler for new applications that will benefit society in important areas such as health care, communications, and scientific computing.
Programme
Discovery Grants Program - Individual
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
293263-2009
Name nom
Lemieux, Guy
Department département
Electrical and Computer Engineering
Organization id
2
Institution établissement
University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2009
Competition year année de concours
2009
Award amount
29000
Program id
RGPIN
Program nane 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
1079
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et de l'informatique
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
2722
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Vlsi systems
Research subject fr
Systèmes intégrés à très grande échelle (VLSI)
Partie
1
Nb partie
5
Application title
Low-cost, high-performance with FPGAs, structured ASICs, and processor arrays
Keyword
NA
Application summary
Field-programmable gate arrays (FPGA) are a vital technology invented 25 years ago to build digital hardware. The key strengths of the technology are instant manufacturing, no up-front manufacturing costs, and the ability to to fix hardware bugs or add features at no cost. These strengths are obtained by prefabricating a generic logic circuit that is configured by the customer using computer-aided design tools. Despite their advantages, FPGAs are estimated to be 40x less dense, 4x slower, and use 12x more power than ASICs. Improvements and alternatives to FPGAs are needed to overcome these disadvantages. FPGA interconnect dominates the area, power, and delay of the device. FPGA tools cannot easily map parallel software into FPGAs. Structured ASICs are a promising alternative to FPGAs; they vastly improve density, power, and delay by premanufacturing most (but not all) of the semiconductor masks. Single-chip massively parallel processor arrays are a promising alternative to run parallel software, but they can also used to implement high-performance and high-density computaitonal circuits with much faster mapping runtimes and higher capacity limits. Together, these three devices provide very low-cost accessibility to the latest semiconductor technology for implementing digital hardware and highly parallel systems. The goals of this research are to realize advances in three areas: improved FPGA processing speed through interconnect optimization and vector processing, improved structured ASICs with easier design tools, and demonstrate the ability to efficiently map circuits to massively parallel processor arrays. Combining hardware performance with software cost and ease-of-use leads to dramatic improvements in cost/performance ratio. Achieving this convergence is a key enabler for new applications that will benefit society in important areas such as health care, communications, and scientific computing.