Executing Dynamic Task Graphs Using Work-Stealing
@inproceedings{Agrawal2010ExecutingDT, title={Executing Dynamic Task Graphs Using Work-Stealing}, author={Kunal Agrawal and Charles E. Leiserson and Jim Sukha}, year={2010} }
Nabbit is a work-stealing library for executing dynamic task graphs with arbitrary dependencies. We prove that Nabbit achieves asymptotically optimal performance for task graphs whose nodes have constant in-degree and out-degree. We have implemented Nabbit in the multithreaded programming language Cilk++. Since the implementation of Nabbit required no modification to the Cilk++ runtime system, it should not be hard to port it to other fork-join languages and libraries. In order to evaluate the… CONTINUE READING
Citations
Publications citing this paper.
SHOWING 1-8 OF 8 CITATIONS
Fault-tolerant programming models and computing frameworks
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED
Analysis of dependence tracking algorithms for task dataflow execution
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED
Elastic Tasks: Unifying Task Parallelism and SPMD Parallelism with an Adaptive Runtime
VIEW 1 EXCERPT
CITES BACKGROUND
Bounds on Multithreaded Computations by Work Stealing by Warut Suksompong
VIEW 1 EXCERPT
CITES BACKGROUND
On task tree executor architectures based on intel parallel building blocks
VIEW 1 EXCERPT
CITES METHODS
Using stream rewriting for mapping and scheduling data flow graphs onto many-core architectures
VIEW 1 EXCERPT
CITES BACKGROUND
A Methodology for Optimizing Multithreaded System Scalability on Multi-cores
VIEW 2 EXCERPTS
CITES BACKGROUND
Scheduling Macro-DataFlow Programs on Task-Parallel Runtime Systems
VIEW 1 EXCERPT
CITES METHODS
References
Publications referenced by this paper.
SHOWING 1-10 OF 18 REFERENCES
Cilk: an efficient multithreaded runtime system
VIEW 17 EXCERPTS
Scheduling multithreaded computations by work stealing
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL
Converting to and from Dilated Integers
VIEW 1 EXCERPT
The Fortress Language Specification Version 1.0
VIEW 1 EXCERPT
Cache-Oblivious Algorithms
VIEW 1 EXCERPT