This chapter focuses on the workload balance of MPI applications running in heterogeneous cluster environment consisting of Intel Xeon processors and Intel Xeon Phi coprocessors in a financial industry application that calculates Asian option payoffs. Three cases are considered: unbalanced symmetric MPI code, manual balancing with pre-calculated performances of the cluster components, and dynamic workload balancing, implemented with Boss‐Workers model, also known as master/slave communication model.

Performance results for tree load balancing techniques presented in this chapter. (Courtesy Morgan Kaufmann)

MPI communication scheme of dynamically balanced Boss-Workers model of load distribution. (Courtesy Morgan Kaufmann)
Chapter Author
Vadim Karpusenko, PhD, is a Principal HPC Research Engineer at Colfax International. His research interests are in the area of physical modeling with HPC clusters, highly parallel architectures, and code optimization. Vadim holds a PhD in Physics from North Carolina State University for his computational research of the free energy and stability of helical secondary structures of proteins.
Click to see the overview article “Teaching The World About Intel Xeon Phi” that contains a list of TechEnablement links about why each chapter is considered a “Parallelism Pearl” plus information about James Reinders and Jim Jeffers, the editors of High Performance Parallelism Pearls.
Leave a Reply