Data parallel visual reconstruction and partitioning algorithms and the associated code are developed for a vector random access machine (V-RAM). Finite element algorithms are constructed for solving the one-dimension...
详细信息
Data parallel visual reconstruction and partitioning algorithms and the associated code are developed for a vector random access machine (V-RAM). Finite element algorithms are constructed for solving the one-dimensional visualreconstruction problem with the input data consisting of a symmetrical top hat loading for the modeling of interacting step discontinuities. The advantage of the V-RAM implementation is the general code applicability to a variety of architectures. A specific implementation is performed on a Distributed Array Processor (DAP) simulator on the VAX 6000–420. Execution times on the DAP simulator are obtained and are found to be in agreement with the algorithmic complexities of the V-RAM code.
暂无评论