Distributed shared memoy (DSM) systems have attracted considembie research efforts recently, since they combine the advantages of two different computer classes: shared memory multiprocessors and distn’buted systems. The most important one is the use of shared memory programming pamdigm on physically distributed memon.es. In the first part of this paper, one possible classiJication taxonomy, wh...

Reconfigurable optical interconnects can revive large-scale shared-memory processing.

In this paper, an unified lightweight error recovery scheme based on coordinated checkpointing and rollback for distributed shared memory clusters is proposed. The new scheme maintains multiple globally consistent checkpoints of the state of a distributed shared memory cluster and recovers to a pre-fault checkpoint of the system. It also describes and evaluates the coordinated checkpointing. Th...