Abstract
Transactional memory (TM) promises to simplify construction of parallel applications by allowing programmers to reason about interactions between concurrently executing code fragments in terms of high-level properties they should possess. However, all currently existing TM systems deliver on this promise only partially by disallowing parallel execution of computations performed inside transactions. This paper fills in that gap by introducing NePaLTM (Nested PAralleLism for Transactional Memory), the first TM system supporting nested parallelism inside transactions. We describe a programming model where TM constructs (atomic blocks) are integrated with OpenMP constructs enabling nested parallelism. We also discuss the design and implementation of a working prototype where atomic blocks can be used for concurrency control at an arbitrary level of nested parallelism. Finally, we present a performance evaluation of our system by comparing transactions-based concurrency control mechanism for nested parallel computations with a mechanism already provided by OpenMP based on mutual exclusion.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.