摘要
Parallel graph reduction is a promising model for new generation computer because of its amenability to both programming and parallel computing. In this paper, an initial design for a parallel graph reduction model, PGR model, is presented, which employs eager evaluation strategy to exploit conservative parallelism and provides with primitives and associated tags of nodes to synchronize concurrent tasks .Moreover, a direct operational description of graph reduction in terms of high level instructions (primitives) is given to obtain a virtual machine, called PGRVM.
Parallel graph reduction is a promising model for new generation computer because of its amenability to both programming and parallel computing. In this paper, an initial design for a parallel graph reduction model, PGR model, is presented, which employs eager evaluation strategy to exploit conservative parallelism and provides with primitives and associated tags of nodes to synchronize concurrent tasks .Moreover, a direct operational description of graph reduction in terms of high level instructions (primitives) is given to obtain a virtual machine, called PGRVM.
