|
Abstract : |
Abstract: Directory-based distributed shared memory (DSM) systems have drawn high interests in parallel computing research and industry in recent years. Current generation systems are limited to using point-to-point messages for cache invalidation requests and associated acknowledgments. Such an approach incurs a large number of control messages, heavy network traffic, and high occupancy at home nodes. In this paper we present a new approach to reduce cache invalidation overheads. We introduce a set of multidestination-based reservation and gather worms to distribute invalidation requests and collect acknowledgments. Six different grouping schemes are investigated in generating such multidestination worms in order to implement fully-mapped directory-based cache coherence on networks using deterministic (e-cube) or adaptive (turn-model) wormhole routing. These schemes are evaluated for different applications and 2D mesh configurations through execution-driven simulation. The interplay among overall execution time, the number of invalidation messages, total network traffic, routing adaptivity is studied. The results indicate that up to 15 % reduction in overall execution time can be achieved by using multidestination messages. It is observed that turn-model routing with a density-dependent column grouping leads to maximum benefits. The results demonstrate, |
