Rapid prototyping of FPGA based floating point DSP systems

A system for the rapid prototyping of floating point hardware designs is presented. This system, called Float, consists of a floating point class for the simulation of quantization effects associated with low precision floating point operators; an optimizer which can automatically determine the minimal number of exponent and fraction bits required for a specified degree of accuracy; and a parameterized floating point library which can generate floating point operators with arbitrary precision. A digital sine-cosine generator is used as an example.