article · 1995

Modeling the Benefits of Mixed Data and Task Parallelism

Soumen Chakrabarti James, James Demmel, Katherine Yelick

Cited by 0Abstract and details only

Abstract

Mixed task and data parallelism exists naturally in many applications, but utilizing it may require sophisticated scheduling algorithms and software support. Recently, significant research effort has been applied to exploiting mixed parallelism in both theory and systems communities. In this paper, we ask how much mixed parallelism will improve performance in practice, and how architectural evolution impacts these estimates. First, we build and validate a performance model for a class of mixed task and data parallel problems based on machine and problem parameters. Second, we use this model to estimate the gains from mixed parallelism for some scientific applications on current machines. This quantifies our intuition that mixed parallelism is best when either communication is slow or the number of processors is large. Third, we show that, for balanced divide and conquer trees, a simple one-time switch between data and task parallelism gets most of the benefit of general mixed paralleli...

Cite this paper

APA 7

James, S. C., Demmel, J., & Yelick, K. (1995). Modeling the Benefits of Mixed Data and Task Parallelism.

MLA 9

James, Soumen Chakrabarti, et al. “Modeling the Benefits of Mixed Data and Task Parallelism.” 1995.

Chicago

James, Soumen Chakrabarti, James Demmel, and Katherine Yelick. 1995. “Modeling the Benefits of Mixed Data and Task Parallelism.”

Harvard

James, S.C., Demmel, J. and Yelick, K. (1995) ‘Modeling the Benefits of Mixed Data and Task Parallelism’.

BibTeX

@article{james1995modeling,
  title = {{Modeling the Benefits of Mixed Data and Task Parallelism}},
  author = {James, Soumen Chakrabarti and Demmel, James and Yelick, Katherine},
  year = {1995}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.