Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Alliance Grants

University of Toronto

$155,980.00

Large-Scale Heterogeneous Computing with FPGAs: Infrastructure, Architecture and Tools

FY 2024-25

Summary
Data centres are large facilities hosting up to hundreds of thousands of compute servers that are used for high-performance computing and for providing cloud-computing services. As the demand for ever more computing capability increases, the classic compute servers powered by microprocessors cannot keep up. At the same time, the vast numbers of servers consume tremendous amounts of power. More specialized computing devices are now being deployed, especially for applications in artificial intelligence. These devices can provide increased performance and better power efficiency, but only for specific types of computations. One such device is the field-programmable gate array (FPGA), which is a programmable chip that can implement computations as hardware circuits instead of using software programs. Building computations as circuits usually results in better performance and power efficiency. In this proposal, we are investigating the benefits of harnessing large clusters of FPGAs for implementing large-scale artificial intelligence applications. We are implementing applications on state-of-the art FPGA hardware to measure their effectiveness and using these results to motivate the exploration of better ways to design, program and compile for FPGAs to make them even more efficient for implementing artificial intelligence and other data centre applications. The outcomes of this work will lead to more efficient computation in high-performance computing and the cloud. Most people will be directly affected by better cloud performance because the cloud is what supports many of the services found on smart phones and smart devices, such as language translation and voice recognition. There is also an environmental impact of more power efficient data centres. The industrial partner of this proposal, AMD, is a manufacturer of FPGAs and will be able to leverage the results of our research in their planning for future products.
Program
Alliance Grants
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
587125-2023
Name nom
Chow, Paul P
Department département
Electrical & 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
2024
Competition year année de concours
2023
Award amount
155980
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
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
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Large-Scale Heterogeneous Computing with FPGAs: Infrastructure, Architecture and Tools
Keywords
computer-aided design; distributed computing; field-programmable gate arrays; hardware acceleration; heterogeneous computing; high-level synthesis; machine learning (ml); multi-fpga applications; multiprocessing; reconfigurable computing
Application summary
Data centres are large facilities hosting up to hundreds of thousands of compute servers that are used for high-performance computing and for providing cloud-computing services. As the demand for ever more computing capability increases, the classic compute servers powered by microprocessors cannot keep up. At the same time, the vast numbers of servers consume tremendous amounts of power. More specialized computing devices are now being deployed, especially for applications in artificial intelligence. These devices can provide increased performance and better power efficiency, but only for specific types of computations. One such device is the field-programmable gate array (FPGA), which is a programmable chip that can implement computations as hardware circuits instead of using software programs. Building computations as circuits usually results in better performance and power efficiency. In this proposal, we are investigating the benefits of harnessing large clusters of FPGAs for implementing large-scale artificial intelligence applications. We are implementing applications on state-of-the art FPGA hardware to measure their effectiveness and using these results to motivate the exploration of better ways to design, program and compile for FPGAs to make them even more efficient for implementing artificial intelligence and other data centre applications. The outcomes of this work will lead to more efficient computation in high-performance computing and the cloud. Most people will be directly affected by better cloud performance because the cloud is what supports many of the services found on smart phones and smart devices, such as language translation and voice recognition. There is also an environmental impact of more power efficient data centres. The industrial partner of this proposal, AMD, is a manufacturer of FPGAs and will be able to leverage the results of our research in their planning for future products.