FPGA-based Implementation of Signal Processing Systems, 2nd Edition

8 Architecture Derivation for FPGA-based DSP Systems

8.1 Introduction

The technology review in Chapter 4 and the detailed circuit implementation material in Chapter 5 clearly demonstrated the need to develop a circuit architecture when implementing DSP algorithms in FPGA technology. The circuit architecture allows the performance needs of the application to be captured effectively. One optimization is to implement the high levels of parallelism available in FIR filters directly in hardware, thereby allowing a performance increase to be achieved by replicating the functionality in FPGA hardware. In addition, it is possible to pipeline the SFG or DFG heavily to exploit the plethora of available registers in FPGA; this assumes that the increased latency in terms of clock cycles, incurred as a result of the pipelining (admittedly at a smaller clock period), can be tolerated. It is clear that optimizations made at the hardware level can have direct cost implications for the resulting design. Both of these aspects can be captured in the circuit architecture.

In Chapter 5 it was shown how this trade-off is much easier to explore in “fixed architectural” platforms such as microprocessors, DSP processors or even reconfigurable processors, as appropriate tools can be or have been developed to map the algorithmic requirements efficiently onto the available hardware. As already discussed, the main attraction of using FPGAs is that the available hardware can be developed to meet the specific ...