Reconfigurable Computing: The Theory and Practice of FPGA-Based Computation
Reconfigurable Computing: The Theory and Practice of FPGA-Based Computation
Implementation of a neuro-fuzzy network with on-chip learning and its applications
Expert Systems with Applications: An International Journal
| Hi-index | 0.09 |
The rapid expansion of the market in applications of the digital signal processor has unloosed a flood of diverse chips. Design engineers are being inundated with altogether too much information to absorb. Still, the problem does become more manageable once it is decided whether a fixed-point or a floating point math unit should be basic to the digital signal processor (DSP) to be used. Several factors should be taken into account. An important first step is to gain an understanding of how the hardware representations differ and how they affect precision and range. Also needed is a grasp of the types of applications to which particular chips are best suited and which hardware vendors provide these chips. Another consideration is the availability of good development tools and the programming paradigms they support. And finally, since performance is a driving factor behind the use of DSPs, cost, speed and power consumption are key ingredients