Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Collaborative Research and Development Grants

University of Toronto

$65,976.00

Software-based speculative parallelism for multicore processors

EF 2010-11

Résumé
Until recently, an average computer programmer could exploit the increasing hundreds of millions of transistors available on integrated circuit chips without any extra effort, since they were each organized as a single processor. However, technology limitations have recently forced industry to switch to multicore processors: parallel processors within a chip. To fully exploit this parallelism requires that all programs be transformed using skills which average programmers do not have---a significant challenge for the Canadian software industry. The goal of this project is to ease the extraction of parallelism from sequential programs so that non-expert programmers can exploit multicores. Methods for speculative parallelization such as Thread-Level Speculation (TLS) and Transactional Memory (TM) have been shown to be a promising way of easing the parallelization of sequential programs, but typically involve novel hardware support that does not yet exist. In this project we will support speculative parallelization for C programs, through a systems based entirely in software. Our approach will be to leverage compiler analyses and optimizations to reduce overheads and customize these two key mechanisms to match the behaviour of applications.
Programme
Collaborative Research and Development Grants
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
360660-2007
Name nom
Steffan, Gregory
Department département
Electrical and 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
2010
Competition year année de concours
2007
Award amount
65976
Program id
CRDPJ
Program name en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
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
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
Partie
3
Nb partie
3
Application title
Software-based speculative parallelism for multicore processors
Keyword
NSERC
Application summary
Until recently, an average computer programmer could exploit the increasing hundreds of millions of transistors available on integrated circuit chips without any extra effort, since they were each organized as a single processor. However, technology limitations have recently forced industry to switch to multicore processors: parallel processors within a chip. To fully exploit this parallelism requires that all programs be transformed using skills which average programmers do not have---a significant challenge for the Canadian software industry. The goal of this project is to ease the extraction of parallelism from sequential programs so that non-expert programmers can exploit multicores. Methods for speculative parallelization such as Thread-Level Speculation (TLS) and Transactional Memory (TM) have been shown to be a promising way of easing the parallelization of sequential programs, but typically involve novel hardware support that does not yet exist. In this project we will support speculative parallelization for C programs, through a systems based entirely in software. Our approach will be to leverage compiler analyses and optimizations to reduce overheads and customize these two key mechanisms to match the behaviour of applications.