Porting a global ocean model onto a shared-memory multiprocessor: Observations and guidelines

Abstract

A three-dimensional global ocean circulation model has been modified to run on the BBN TC2000 multiple instruction stream/multiple data stream (MIMD) parallel computer. Two shared-memory parallel programming models have been used to implement the global ocean model on the TC2000: the TCF (TC2000 Fortran) fork-join model and the PFP (Parallel Fortran Preprocessor) split-join model. The method chosen for the parallelization of this global ocean model on a shared-memory MIMD machine is discussed. The performance of each version of the code has been measured by varying the processor count for a fixed-resolution test case. The statically scheduled PFP version of the code achieves a higher parallel computing efficiency than does the dynamically scheduled TCF version of the code. The observed differences in the performance of the TCF and PFP versions of the code are discussed. The parallel computing performance of the shared-memory implementation of the global ocean model is limited by several factors, most notably load imbalance and network contention. The experience gained while porting this large, “real world” application onto a shared-memory multiprocessor is also presented to provide insight to the reader who may be contemplating such an undertaking.