Near-Optimal Speedup of Graphics Algorithms Using Multigauge Parallel Computers

摘要

A multigauge computer can have its datapath split into independent datapaths that execute operations on small data concurrently. This paper explains how certain forms of multigauge processing can be implemented with little cost in hardware; we illustrate this low cost implementation by describing the multigauging of the Quarter Horse microprocessor; and the authors report on the practical applications from graphics for which 95% of the theoretically possible speedup is achieved with this low cost implementation. It is concluded that because multigauging can be used with other architectural structures it is a very low cost way of exploiting parallelism.