Abstract. This paper presents a new data representation known as Dual FiXedpoint (DFX), which employs a single bit exponent to select two different fixedpoint scalings. DFX provides a compromise between conventional fixed-point and floating-point representations. It has the implementation complexity similar to that of a fixed-point system together with the improved dynamic range offered by a floating-point system. The benefit of using DFX over both fixed-point and floating-point is demonstrated with an IIR filter implementation on a XilinxVirtex II FPGA.
Chun Te Ewe, Peter Y. K. Cheung, George A. Constan