This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

DSP Vs. DSP core on FPGA



Hi,

We work with a TI microcontroller, and for one application must use FPGA (will not be licenced if not) . There was a suggestion to use a DSP core on the FPGA. What are the advantages of a DSP Vs. DSP core on FPGA? What problems will we face? time? power consumption? any input is welcome

Thanks

  • This is rather a question for a DSP forum than for the MSP430 microcontroller forum. Most people here are working wtih MSPs and not with DSPs. :)

    However, an advantage of DSPs in FPGA is that you only need to license those parts of the DSP that you need for your application. The less features you need, the lower the license cost and the more of the FPGA is available for other parts, e.g. for much of the circuitry that would be needed around a separate DSP. Also, changes in the circuitry as well as in the DSP configuraiton (includign upgrades of capabilities,a s long as teh FPGA is large enough) can be done 'on-the-fly' with an update of the FPGA configuraitohn. This includes pin reassignments and much more.

    However, it is a job for rather large numbers of devices. For small count projects, a dedicated DSP is easier to implement and maybe even cheaper (if you get a DSP IP license for a low count at all)

**Attention** This is a public forum