Abstract
Massively parallel processing (MPP) computer systems use high-speed interconnection networks to link hundreds or thousands of RISC microprocessors. With each microprocessor having a peak performance of 100 or more megaflops per second, there is at least the possibility of achieving very high performance. However, the question of exactly how to achieve this performance remains unanswered. MPP systems and vector multi-processors require very different coding styles. Different MPP systems have widely varying architectures and performance characteristics. For most problems, a range of different parallel implementations is possible, again with varying performance characteristics. In this paper, we provide a detailed evaluation of MPP performance for a spectral transform kernel as used in weather and climate modeling applications. Using a specially designed spectral transform code, the authors study performance on three different MPP systems: Intel Paragon, IBM SP2, and Cray T3D. Great care is taken to tune the implementation for efficient execution on each platform. The results yield insights into MPP performance characteristics, parallel spectral transform algorithms, and coding style for MPP systems. The authors conclude that it is possible to construct parallel models that achieve multigigaflops-per-second performance on a range of MPPS, if the models are constructed to allow compile- or run-time selection of some parallel implementation options.
