Hardware support for floating point map function generation

Abstract

An algorithm suited for hardware implementation assists in evaluating two-variable floating-point map functions. A map function F(X,Z) is an arbitrary function found in jet engine simulations and other scientific applications. The hardware oriented algorithm involves two stages of processing: preprocessing and run time processing. During preprocessing, breakpoints are analyzed to generate data tables and constants used at run time. At run time, the breakpoint region containing an arbitrary input argument (X/spl nu/,Z/spl nu/), is identified in a small number of steps. The algorithm replaces the general search needed in software routines to identify the breakpoint region. An example describes a straightforward implementation of a map function generator that uses bilinear interpolation.