A DISTRIBUTED SHARED-MEMORY SYSTEM WITH SELF-ADJUSTING COHERENCE SCHEME

Abstract

The performance of distributed shared memory depends on the memory coherence algorithms and the access characteristics of shared data. In this paper, we propose an efficient coherence scheme using multiple coherence algorithms with self-adjusting feature. Our method can dynamically choose a more adaptive coherence algorithm for each variable class and the incorrect classification of shared variables will not affect the performance. We show that for each fixed classification, application programs suffer 5.1%, 4.6%, and 48.9% increases in the average execution time, when compared against the performance of a self-adjusting scheme. Experiments have shown our approach achieving good performance.