From ElectroDragon
Jump to: navigation, search

What do FPGA can do?

This is all refer from book The design warrior's guide of FPGA. you can download it from here.

To be just a tad more specific, FPGAs are currently eating into four major market segments: ASIC and custom silicon, DSP, embedded microcontroller applications, and physical layer communication chips. Furthermore, FPGAs have created a new market in their own right: reconfigurable computing (RC).

ASIC and custom silicon: As was discussed in the previous section, today’s FPGAs are increasingly being used to implement a variety of designs that could previously have been realized using only ASICs and custom silicon.

Digital signal processing: High-speed DSP has traditionally been implemented using specially tailored microprocessors called digital signal processors (DSPs). However, today’s FPGAs can contain embedded multipliers, dedicated arithmetic routing, and large amounts of on-chip RAM, all of which facilitate DSP operations. When these features are coupled with the massive parallelism provided by FPGAs, the result is to outperform the fastest DSP chips by a factor of 500 or more.

Embedded microcontrollers: Small control functions have traditionally been handled by special-purpose embedded processors called microcontrollers. These low cost devices contain on-chip program and instruction memories, timers, and I/O peripherals wrapped around a processor core. FPGA prices are falling, however, and even the smallest devices now have more than enough
capability to implement a soft processor core combined with a selection of custom I/O functions. The end result is that FPGAs are becoming increasingly attractive for embedded control applications.

Physical layer communications: FPGAs have long been used to implement the glue logic that interfaces between physical layer communication chips and high-level networking protocol layers. The fact that today’s high-end FPGAs can contain multiple high-speed transceivers means that communications and networking functions can be consolidated into a single device.

Reconfigurable computing: This refers to exploiting the inherent parallelism and reconfigurability provided by FPGAs to “hardware accelerate” software algorithms. Various companies are currently building huge FPGA-based reconfigurable computing engines for tasks ranging from hardware simulation to cryptography analysis to discovering new drugs.