Basic HTML version of Foils prepared April 7,1995

Foil 10 What Issues should High Performance Fortran (HPF) Address!

From Programming Paradigms B CRPC/MCNC Workshop -- April 10-13 1995. by Geoffrey C. Fox


1 Should not solve ALL Problems
2 Goal: Express in a high level portable scalable fashion those aspects of problems one would like to use Fortran for
  • Need not solve all issues Roughly express all data parallelism and needed task parallelism
  • Integrate other programming paradigms to address remaining issues (see PCRC - Parallel Compiler Runtime Consortium)
3 Lessons from study of
  • CMFORTRAN experience
  • Some initial HPF experience
  • Fortran + Message Passing Experience
4 Particle Dynamics and Parallel Differential Equation Solving have been studied in detail (for HPF). Other fields less completely understood.

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 Feb 22 1998