FPGA implementation of a faithful polynomial approximation for powering function computation

Abstract

A FPGA implementation of a method for the calculation of faithfully rounded single-precision floating-point powering (X/sup p/) is presented in this paper. A second-degree minimax polynomial approximation is used, together with the employment of table look-up, a specialized squaring unit and a fused accumulation tree. The FPGA implementation of an architecture with a latency of 3 cycles and a throughput of one result per cycle has been performed using a Xilinx XC4036XL device. The implemented unit has an operation frequency over 33 MHz.