Basic HTML version of Foils prepared 24 August 98

Foil 31 Data Parallelism in Algorithms

From Master Foilset for CPS615 Introduction -- Material from Culler and Koelbel Computational Science for Simulations -- Fall Semester 1998. by Geoffrey C. Fox, Nancy McCracken
1 Data-parallel algorithms exploit the parallelism inherent in many large data structures.
  • A problem is an (identical) algorithm applied to multiple points in data "array"
  • Usually iterate over such "updates"
  • Example: Red-Black Relaxation
    • All "red" points can be updated in parallel; then all the "black"
2 Analysis:
  • Scalable parallelism -- can usually get million or more way parallelism
  • Hard to express when "geometry" irregular or dynamic
in Table To:

© Northeast Parallel Architectures Center, Syracuse University, npac@npac.syr.edu

If you have any comments about this server, send e-mail to webmaster@npac.syr.edu.

Page produced by wwwfoil on Sun Apr 11 1999