Grant: Discovery Grants Program - Individual
University of British Columbia
$19,491.00
Processor and memory configurability for multiprocessor systems-on-chip
EF 2010-11
Résumé
In recent years, the cost of designing integrated circuits has dramatically increased due to exponentially larger circuits, an increase in circuit-level design challenges due to smaller transistors, and increased time-to-market pressures. If it were not for the computer-aided design (CAD) innovations developed to date, the average design cost would be significantly higher than its current value. In spite these CAD innovations, the demand for design complexity continues to outpace the ability of engineers to meaningfully design them. A continuous pipeline of CAD innovations must continue otherwise design costs will quickly become prohibitive for most semiconductor companies.
One approach to reducing development costs is to add configurability to the embedded processors, memory, and communications that make up a System-on-Chip (SoC). Configurability provides SoCs with performance, energy-efficiency, and area-efficiency characteristics closer to that of expensive custom circuitry. At the same time, the flexibility of processor-based architectures is maintained resulting in better reuse, reduced risk, and faster time-to-market.
This research will investigate methods for augmenting Multiprocessor Systems-on-Chip (MPSoCs) with processor and memory configurability. The current trend towards multiprocessor SoCs has many advantages in terms of energy-efficiency and performance; however, the design tools necessary for MPSoC design are far from mature. Adding configurability to MPSoCs greatly improves performance while minimizing cost; however, it adds many additional challenges to design-tool methodologies. This research will tackle these challenges thus improving the CAD tools available to designers. This will make MPSoCs more accessible to the average semiconductor company. The implications of this work to the average consumer are faster, cheaper, and more energy-efficient products.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
355618-2008
Name nom
Hallschmid, Peter
Department département
Okanagan - Engineering, School of
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
2010
Competition year année de concours
2008
Award amount
19491
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
334
Committee name en
Commun.,Computers & Components
Committee name fr
Communic.,ordin. et composants
Area of application code
513
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Electrical and electronic machinery and equipment (including computer hardware)
Area of application fr
Machinerie et équipement électriques et électroniques (y compris matériel informatique)
Research subject code
2504
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Integrated circuits
Research subject fr
Circuits intégrés
Partie
3
Nb partie
5
Application title
Processor and memory configurability for multiprocessor systems-on-chip
Keyword
NSERC
Application summary
In recent years, the cost of designing integrated circuits has dramatically increased due to exponentially larger circuits, an increase in circuit-level design challenges due to smaller transistors, and increased time-to-market pressures. If it were not for the computer-aided design (CAD) innovations developed to date, the average design cost would be significantly higher than its current value. In spite these CAD innovations, the demand for design complexity continues to outpace the ability of engineers to meaningfully design them. A continuous pipeline of CAD innovations must continue otherwise design costs will quickly become prohibitive for most semiconductor companies.
One approach to reducing development costs is to add configurability to the embedded processors, memory, and communications that make up a System-on-Chip (SoC). Configurability provides SoCs with performance, energy-efficiency, and area-efficiency characteristics closer to that of expensive custom circuitry. At the same time, the flexibility of processor-based architectures is maintained resulting in better reuse, reduced risk, and faster time-to-market.
This research will investigate methods for augmenting Multiprocessor Systems-on-Chip (MPSoCs) with processor and memory configurability. The current trend towards multiprocessor SoCs has many advantages in terms of energy-efficiency and performance; however, the design tools necessary for MPSoC design are far from mature. Adding configurability to MPSoCs greatly improves performance while minimizing cost; however, it adds many additional challenges to design-tool methodologies. This research will tackle these challenges thus improving the CAD tools available to designers. This will make MPSoCs more accessible to the average semiconductor company. The implications of this work to the average consumer are faster, cheaper, and more energy-efficient products.