Now showing items 11-12 of 12
Efficient runtime support for cluster-based distributed shared memory multiprocessors
Distributed shared memory (DSM) systems provide a shared memory programming paradigm on top of a physically distributed network of computers. The DSM system removes the necessity for programmers to move data explicitly ...
Improved software pipelining for superscalar architectures
Although instruction scheduling is an scNP-complete problem (27), many techniques have been developed to improve pipelining efficiency. Among them, several were proposed for scVLIW machines, and were shown to be efficient ...