June 18, 2013 AT 12:00 am

How FPGAs work, and why you’ll buy one

Fpga-Tree

How FPGAs work, and why you’ll buy one.

Today, pretty much everyone has a CPU, a DSP and a GPU, buried somewhere in their PC, phone, car, etc. Most don’t know or care that they bought any of these, but they did.

Will everyone, at some future point, also buy an FPGA? The market size of FPGAs today is about 1% of the annual global semiconductor sales (~$3B vs ~$300B). Will FPGA eventually become a must-have, or will its volume remain relatively low?

We’ll try to answer this question below. In order to see how popular FPGAs could become, we’ll need to discuss what FPGAs are. FPGAs are a programmable platform, but one designed by EEs for EEs rather than for programmers. So for many programmers, FPGAs are exciting yet mysterious; I hope our discussion will help demystify them.

We’ll start with a common explanation of FPGAs’ relatively low popularity. We’ll see why that explanation is wrong – and why, if we take a closer look, we actually come to expect FPGAs to blow the competition out of the water!

This will conclude today’s installment, “Why you’ll buy an FPGA”. A sequel is in the making, titled “Why you won’t buy an FPGA”. There, we’ll see some of the major obstacles standing between FPGAs and world domination.

Related

3 Comments

  1. They sound fun but it adds an unnecessary level of learning and it adds cost and a burden to young programmers who don’t have the funds necessary to build something.

    I’ve seen accomplished engineers work on an FPGA’s for eight years and then quit.

    The other problem is that your average FPGA costs more to turn into an ASIC which teams of people don’t have. Make sure you get a quote before you build!

    The last problem is finding an FPGA large enough and they certainly won’t be fast enough to be competitive against other computers right now.

  2. How much does it cost to build an ASIC? It is a once in a lifetime opportunity for some because of the cost and there is no guarantee it will work because there is a lot of testing and debugging between going from FPGA to ASIC. Sorry to get everyone’s hopes up.

    “A minimum HardCopy order would be to manufacture at least 10000 chips according to Altera. ASIC construction and 10000 chips would come down to around half a million USD or so. So this is the range of the investment needed for an ASIC. And that is without taking into consideration the component and production costs of the rest of the board.”

  3. There are many reasons why I won’t use FPGA’s. Development systems are too expensive for personal tinkering. I have had products in production which used FPGA’s (I inherited them). We always designed out the FPGA because the market life of our product was much longer than the product life of the FPGA. We typically replaced the funtionality with a uP because the models of uP we used had long product life and had sufficient capability to do the job. Plus we had a software team which didn’t know hardware description language and neither did our hardware team.

Sorry, the comment form is closed at this time.