As for SOPC solution implemented with FPGA, Altera's SOPC solution is based on Nios/NiosII soft-core embedded MCU, Xilinx's SOPC solution is based on PowerPC Hard-core MCU.
In fact, FPGA programming is to design and debug hardware circuit with software development tools, it includes bottom level hardware design. However, DSP & MCU programming is merely software design. The difficulty and complexity of FPGA programming is much worse than that of DSP & MCU programming .
In my experience having complete control and understanding of the physical aspects of the a design, make it easier to produce a more architecturally sound product.
The benefits being a lack or redundancy, simplicity, easier debugging and the ability to react to changing conditions through fast iterations, not just in software but in the actual hardware architecture.
The FPGA supports these requirements and allows you to build your own intellectual property whilst not becoming reliant on the architectural constraints, whims and foibles of the supplier of your MCU or DSP.
You can pay for this, literally, in the cost of the devices in comparison to a similar function in an MCU or DSP solution, but I have found that what you may lose in margin is more than made up for in versatility and the ability to build intrinsic value in your business.
I don't believe that there is or ever will be a simple answer to this as each approach is optimised for a different application.
FPGAs give massive flexibility both in terms of their capabilities and the option to redesing at a hardware level if the specification changes. However due to the fine grained approach every implementation is wastefull of silicon resource and so will have higher cost and higher power dissipation.
DSP win where pure performance on complex algorithms is the key requirement, especially where floating point arithmetic is needed.
DSCs win when you are looking for a jack of all trades, some low level control, real world I/O and data processing but at low cost and low power.
One other emerging area is massively parallel processing (see Ambric or Picochip). These offer programming in a high level software language and performance comparable to top of the range DSPs of FPGA.
Pete I agree with you, but the point of my post was to try to make engineers realise that the choice of a component cannot be made for purely engineering reasons.
Designers need to assess the impact of their decisions on a business as a whole.
Pete I agree with you, but the point of my post was to try to make engineers realise that the choice of a component cannot be made for purely engineering reasons.
Designers need to assess the impact of their decisions on a business as a whole.
