Software DSMs have been a research topic for over a decade. While good performance has been achieved in some cases, consistent performance has continued to elude researchers. This paper investigates the performance of DSM protocols running highly regular scientific applications. Such applications should be ideal targets for DSM research because past behavior gives complete, or nearly complete, information about future behavior. We show that a modified home-based protocol can significantly outperform more general protocols in this application domain because of reduced protocol complexity. Nonetheless, such protocols still do not perform as well as expected. We show that the one of the major factors limiting performance is interaction with the operating system on page faults and page protection changes. We further optimize our protocol by completely eliminating such memory manipulation calls from the steady-state execution. Our resulting protocol improves average application performance...
Peter J. Keleher