Basic HTML version of Foils prepared 15 March 1996

Foil 40 Computer Languages and Space - Time Properties

From Complex Systems and Parallel Computing CPSP713 Case studies in Computational Science -- Spring Semester 1996. by Geoffrey C. Fox
1 High Performance Fortran
    • Dimension A,B (10000)
    • A=A+B
2 Space (elements of arrays A,B) in problem is mapped into space (i.e. arrays preserved) in Virtual Problem
3 ---> Compiler can recognize data parallelism
4 ---> Good parallel performance on all machines
5 Fortran77 Do 1 I = 1, 10000
    • 1 A(I) = A(I) + B(I)
6 Space in problem is mapped into time (successive iterations of DO loop) in Virtual Problem
7 ---> Compiler has to "undo" this to recognize parallelism and generally fails
8 ---> Good languages preserve problem architecture
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