S[formula omitted]: A Methodology for Programming High Performance Algorithms on Clusters of Symmetric Multiprocessors (SMPs)

We describe a methodology for developing high performance programs running on clusters of SMP nodes. The SMP cluster programming methodology is based on a small prototype kernel (Simple) of collective communication primitives that make efficient use of the hybrid shared and message-passing environment. We illustrate the power of our methodology by presenting experimental results for sorting integers, two-dimensional fast Fourier transforms (FFT), and constraint-satisfied searching. Our testbed is a cluster of DEC AlphaServer 2100 4/275 nodes interconnected by an ATM switch.