This article describes a parallel implementation of an algorithm for simulating mixed convective flow over a three-dimensional backward-facing step. A FORTRAN90 code was developed and parallelized using OpenMP directives for distributed shared memory (DSM) multiprocessors. Numerical experiments conducted on an IBM p5-575 multiprocessor show that the code achieves significant speed-up on up to 16 processors. Superlinear speed-up was also observed in some cases as a result of efficient cache utilization on the multiprocessor. © Taylor & Francis Group, LLC.