Basic HTML version of Foils prepared August 29 98

Foil 56 Jacobi Iteration: OpenMP Mapping

From Designing and Building Parallel Programs 2: openMP Shared Memory Programming Language DoD Modernization Tutorial -- 1995-1998. by Ian Foster, Gina Goff, Ehtesham Hayder, Chuck Koelbel(Some foils prepared by Kuck & Associates, Inc.)
1 Minimize forking and synchronization overhead
  • One parallel region at highest possible level
  • Mark outermost possible loop for work sharing
2 Keep each processor working on the same data
  • Consistent schedule for DO loops
  • Trust underlying system not to migrate threads for no reason
3 Lay out data to be contiguous
  • Column-major ordering in Fortran
  • Therefore, make dimension of outermost work-shared loop the column
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