Basic HTML version of Foils prepared 2 September 1997

Foil 39 Load Imbalance and Speed-Up for Laplace Example -- II

From CPS615 Laplace Example -- Programming Models and Performance CPS615 Basic Simulation Track for Computational Science -- Fall Semester 97. by Geoffrey C. Fox
Processors doing 9 or 12 updates must wait for those doing 16 to finish
T1 = 196 tcalc T16 = 16 tcalc as all that counts is maximum amount of work done by any one processor
Speed up degraded by load imbalance is: Sload = 196/16 = 12.25 This is speed up ignoring degradation due to communications

© 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 Mon Apr 12 1999