Basic HTML version of Foils prepared 2 October 1995

Foil 38 Load Imbalance and Speed-Up for Laplace Example -- II

From New CPS615 Foils-- D 23 September 95 CPS615 Basic Simulation Track for Computational Science -- Fall Semester 95. 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

© on Tue Oct 7 1997