Grant: Discovery Grants Program - Individual
University of Toronto
$42,000.00
Scalable and Accelerated Data Processing and Storage in the Cloud
EF 2024-25
Résumé
This research will focus on designing scalable big data processing and storage systems and accelerating their performance using graphics processors. We will target three types of systems, transaction, stream and graph processing systems, with distinct designs and requirements. Transaction processing systems serve interactive user requests, stream processing systems run long computations on data streams for real-time analytics, and graph processing systems perform computations and analytics on graph data. Modern cloud services depend on these core systems for highly scalable operation. However, with the ever-growing volume of data generated by users, these services are subject to unpredictable demand and significant variability.
In this proposal, our first research objective is to design systems that support highly unpredictable cloud workloads. I am interested in exploring the challenges raised when designing such systems, including dynamically scaling performance while meeting service level objectives, and providing high availability and strong data consistency.
Our second research objective is to accelerate these systems using graphics processors. These processors offer a powerful approach for accelerating data-parallel workloads but they raise challenges for transactional and graph workloads that generate random accesses. To accelerate these workloads, we plan to explore novel designs that enable extracting data parallelism from these workloads, enabling both CPUs and GPUs to be used efficiently.
We expect that the proposed research will enable high-performance scalable web applications that can efficiently meet the throughput and latency demands of large-scale cloud services. With the growing demand for high-performance data processing, GPUs are likely to become widely available on all computing devices in the future. As a result, we expect that a successful outcome from our research on GPU-accelerated systems will have high impact.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
RGPIN-2024-05760
Name nom
Goel, Ashvin
Department département
Department of Electrical and 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
2024
Competition year année de concours
2024
Award amount
42000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2720
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Computer systems software
Research subject fr
Logiciel de systèmes informatiques
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
Scalable and Accelerated Data Processing and Storage in the Cloud
Keywords
cloud and big-data infrastructure; data processing and analytics; storage systems; gpu processing; caching and replication; operating systems; distributed systems
Application summary
This research will focus on designing scalable big data processing and storage systems and accelerating their performance using graphics processors. We will target three types of systems, transaction, stream and graph processing systems, with distinct designs and requirements. Transaction processing systems serve interactive user requests, stream processing systems run long computations on data streams for real-time analytics, and graph processing systems perform computations and analytics on graph data. Modern cloud services depend on these core systems for highly scalable operation. However, with the ever-growing volume of data generated by users, these services are subject to unpredictable demand and significant variability.
In this proposal, our first research objective is to design systems that support highly unpredictable cloud workloads. I am interested in exploring the challenges raised when designing such systems, including dynamically scaling performance while meeting service level objectives, and providing high availability and strong data consistency.
Our second research objective is to accelerate these systems using graphics processors. These processors offer a powerful approach for accelerating data-parallel workloads but they raise challenges for transactional and graph workloads that generate random accesses. To accelerate these workloads, we plan to explore novel designs that enable extracting data parallelism from these workloads, enabling both CPUs and GPUs to be used efficiently.
We expect that the proposed research will enable high-performance scalable web applications that can efficiently meet the throughput and latency demands of large-scale cloud services. With the growing demand for high-performance data processing, GPUs are likely to become widely available on all computing devices in the future. As a result, we expect that a successful outcome from our research on GPU-accelerated systems will have high impact.