Implementation of floating-point operations for 3D graphics on a coarse-grained reconfigurable architecture

Abstract

With the increasing requirements for more flexibility and higher performance in embedded systems design, reconfigurable computing has become more popular. There have been many coarse-grained reconfigurable architectures proposed and/or commercialized. But most of the existing architectures cannot be used for applications that require floating-point operations, since they have only integer units. In this paper, we present how we can perform various floating-point operations on a coarse-grained reconfigurable array of integer processing elements. We demonstrate the effectiveness of our approach through the implementation of various floating-point operations for 3D graphics and their performance analysis.