Assessing Programming Costs of Explicit Memory Localization on a Large Scale Shared Memory Multiprocessor

We present detailed experimental work involving a commercially available large scale shared memory multiple instruction stream-multiple data stream (MIMD) parallel computer having a software controlled cache coherence mechanism. To make effective use of such an architecture, the programmer is responsible for designing the program′s structure to match the underlying multiprocessors capabilities. We describe the techniques used to exploit our multiprocessor (the BBN TC2000) on a network simulation program, showing the resulting performance gains and the associated programming costs. We show that an efficient implementation relies heavily on the user′s ability to explicitly manage the memory system.