The Residue Number System (RNS) as an alternative to binary representation in digital systems has been studied extensively in the last decades [1,26]. The attractive feature of the RNS is that for operations such as addition and multiplication, a large dynamic range (bit-width) can be divided into sub-ranges of reduced bit-width by splitting the datapath in independent parallel channels where the operations can be executed faster (shorter carry propagation) [26].The main drawback is that converters are required to interface an RNS datapath to the conventional systems based on binary representation, so the use of RNS is justified when the number of operations to be performed in RNS, without conversions, is significant.Over the years, several applications in Digital Signal Processing (DSP), such as digital filters, have benefit from the RNS implementation, e.g., [8,11,15,24].Here, we describe the RNS implementation of a number of DSP algorithms by comparing their performance (clock rate, area, and power dissipation) to the same algorithms implemented in the traditional two's complement number system (TCS), and discussing some trade-offs.In Sect. 8.2, we recall the main RNS concepts to introduce the notation used in the chapter.In Sect. 8.3, we explain the main criteria to choose the RNS base and discuss same trade-offs in choosing the right base for a given application.