Title :
Application of user-defined floating-point formats
Author_Institution :
Dept. of Radio Electron., Brno Univ. of Technol., Brno, Czech Republic
Abstract :
The contribution deals with a binary representation of real numbers. In domain of digital signal processing the number representation is either in fixed-point or floating-point form. There are many processors with fixed or floating-point representation and there are also several blocks used for arithmetical operations in FPGA using fixed or floating point. But generally these blocks do not have a large variability in terms of bit width in consequence of using standardized number formats. The goal of the contribution is mainly to present a simple floating-point unit for FPGAs with user defined formats. In the text the algorithm for multiplication for floating-point representation is presented as well.
Keywords :
field programmable gate arrays; floating point arithmetic; signal processing; FPGA; arithmetical operations; binary representation; digital signal processing; floating point form; standardized number formats; user defined floating point formats; Computers; Convolution; Digital signal processing; Field programmable gate arrays; Image resolution; Logic gates; Program processors;
Conference_Titel :
Signal Processing Algorithms, Architectures, Arrangements, and Applications Conference Proceedings (SPA), 2009
Conference_Location :
Poznan
Print_ISBN :
978-1-4577-1477-1
Electronic_ISBN :
978-83-62065-06-6