Lessons Learned when Comparing Shared Memory and Message Passing Codes on Three Modern Parallel Architectures

A serial Fortran 77 micromagnetics code, which simulates the behaviour of thin-lm media, was parallelised using both shared memory and message passing paradigms, and run on an SGI Challenge, a Cray T3D and an SGI Origin 2000. We report the observed performance of the code, noting some important eeects due to cache behaviour. We also demonstrate how certain commonly-used presentation methods can disguise the true performance proole of a code.