Publications of Torsten Hoefler

P. Kambadur, A. Gupta, Torsten Hoefler and Andrew Lumsdaine:

Demand-driven Execution of Static Directed Acyclic Graphs Using Task Parallelism

(presented in Kochi, India, pages 284-293, ISBN: 978-1-4244-4922-4, Dec. 2009)

Abstract

The dataflow model allows natural expression of parallelism in an application. Applications expressed in the dataflow model can be executed either using the data-driven or the demand-driven schemes. Although both these schemes have their utility in different scenarios, the realization of the demand-driven scheme is not adequately supported in the existing solutions for task parallelism. In this paper, we examine some of the requirements placed by the demand-driven execution scheme on task parallelism. We present PFunc, a new library-based solution for task parallelism that fully supports the demand-driven execution scheme. We compare the runtimes and peak memory consumption of an unsymmetric sparse LU factorization emulation parallelized using both the data- and demand-driven execution schemes. This comparison shows that the demand-driven model provides benefits that necessitate its full support in task parallelism.

Documents

BibTeX

@inproceedings{kambadur-pfunc,
  author={P. Kambadur and A. Gupta and Torsten Hoefler and Andrew Lumsdaine},
  title={{Demand-driven Execution of Static Directed Acyclic Graphs Using Task Parallelism}},
  year={2009},
  month={Dec.},
  pages={284-293},
  location={Kochi, India},
  isbn={978-1-4244-4922-4},
  source={http://www.unixer.de/~htor/publications/},
}


serving: 216.73.216.189:3320	© Torsten Hoefler