Show simple item record

dc.contributor.authorKambadur, Prabhanjan
dc.contributor.authorGupta, Anshul
dc.contributor.authorGhoting, Amol
dc.contributor.authorAvron, Haim
dc.contributor.authorLumsdaine, Andrew
dc.date.accessioned2021-08-18T11:56:21Z
dc.date.available2021-08-18T11:56:21Z
dc.date.issued2009
dc.identifier.citationKambadur, P., Gupta, A., Ghoting, A., Avron, H., & Lumsdaine, A. (2009). PFunc. Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis - SC ’09. doi:10.1145/1654059.1654103
dc.identifier.doi10.1145/1654059.1654103
dc.identifier.urihttp://hdl.handle.net/10754/670666
dc.description.abstractHPC today faces new challenges due to paradigm shifts in both hardware and software. The ubiquity of multi-cores, many-cores, and GPGPUs is forcing traditional serial as well as distributed-memory parallel applications to be parallelized for these architectures. Emerging applications in areas such as informatics are placing unique requirements on parallel programming tools that have not yet been addressed. Although, of all the available parallel programming models, task parallelism appears to be the most promising in meeting these new challenges, current solutions for task parallelism are inadequate. In this paper, we introduce PFunc, a new library for task parallelism that extends the feature set of current solutions for task parallelism with custom task scheduling, task priorities, task affinities, multiple completion notifications and task groups. These features enable PFunc to naturally and efficiently parallelize a wide variety of modern HPC applications and to support the SPMD model of parallel programming. We present three case studies: demand-driven DAG execution, frequent pattern mining and iterative sparse solvers to demonstrate the utility of PFunc's new features.
dc.description.sponsorshipWe thank Joseph Cottam, Jeremiah Willcock, Torsten Hoefler and Nicholas Edmonds for valuable insights that improved the quality of this paper. This work was supported by IBM, King Abdullah University of Science and Technology (KAUST), National Science Foundation grants EIA-0202048 and CCF-0541335, and a grant from the Lilly Endowment.
dc.publisherACM Press
dc.relation.urlhttp://dl.acm.org/citation.cfm?doid=1654059.1654103
dc.rightsArchived with thanks to ACM Press
dc.titlePFunc: Modern Task Parallelism For Modern High Performance Computing
dc.typeConference Paper
dc.identifier.wosutWOS:000320136800014
dc.eprint.versionPost-print
dc.contributor.institutionIndiana University
dc.contributor.institutionIBM T J Watson Research Center
dc.contributor.institutionTel-Aviv University


This item appears in the following Collection(s)

Show simple item record