Executing Task Graphs Using Work-Stealing
Name
Leiserson_Executing task.pdf
Size
1.03 MB
Format
Adobe PDF
Checksum (MD5)
f14465277dc004b4ea649c32b2ba60e0
Author(s)
Agrawal, Kunal
Leiserson, Charles E.
Sukha, Jim
Date Issued
May 2010
Journal
Proceedings of the IEEE International Symposium on Parallel & Distributed Processing (IPDPS), 2010
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Agrawal, Kunal, Charles E. Leiserson, and Jim Sukha. “Executing Task Graphs Using Work-stealing.” Proceedings of the IEEE International Symposium on Parallel & Distributed Processing (IPDPS), 2010. 1–12. © Copyright 2010 IEEE
Version
Final published version
Abstract
NABBIT is a work-stealing library for execution of task graphs with arbitrary dependencies which is implemented as a library for the multithreaded programming language Cilk++. We prove that Nabbit executes static task graphs in parallel in time which is asymptotically optimal for graphs whose nodes have constant in-degree and out-degree. To evaluate the performance of Nabbit, we implemented a dynamic program representing the Smith-Waterman algorithm, an irregular dynamic program on a two-dimensional grid. Our experiments indicate that when task-graph nodes are mapped to reasonably sized blocks, Nabbit exhibits low overhead and scales as well as or better than other scheduling strategies. The Nabbit implementation that solves the dynamic program using a task graph even manages in some cases to outperform a divide-and-conquer implementation for directly solving the same dynamic program. Finally, we extend both the Nabbit implementation and the completion-time bounds to handle dynamic task graphs, that is, graphs whose nodes and edges are created on the fly at runtime.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/IPDPS.2010.5470403
