FPGAs are an amazing product that almost shouldn't exist if you think about the business and marketing concerns. They are a product that is too expensive at scale. If an application takes off, it is eventually cheaper and more performant to switch to ASICs, which is obvious when you see the 4-digit prices of the most sophisticated FPGAs.
Given how ruinously expensive silicon products are to bring to market, it's amazing that there are multiple companies competing (albeit in distinct segments).
FPGAs also seem like a largely untapped domain in general purpose computing, a bit like GPUs used to be. The ability to reprogram an FPGA to implement a new digital circuit in milliseconds would be a game changer for many workloads, except that current CPUs and GPUs are already very capable.
I love FPGAs.
For me, the promise of computation is not in the current CPU (or now GPU) world, but one in which the hardware can dynamically run the most optimized logic for a given operation.
Sadly, this has yet to materialize (with some exceptions[0][1][2]).
Hopefully in an LLM-first world, we can start to utilize FPGAs more effectively at (small) scale :)
[0]https://www.microsoft.com/en-us/research/wp-content/uploads/...
[2]https://www.alibabacloud.com/blog/deep-dive-into-alibaba-clo...
If you look at the XC2064 datasheet[1], you'll see there are 12,038 configuration bits, only 1024 of those bits actually program the LUTs, and 90% are for routing. For general purpose logic replacement, that offers great flexibility.
If you want to do general purpose computing, it's my strong (and minority) opinion that routing fabrics are a premature optimization. The trend has been in the wrong direction.
If you were to go the other way, and just build a systolic array of look up tables, as I have hypothesized for years with my BitGrid, you could save 90% of the silicon, and still get almost all of the compute. It gets better when you consider the active logic would only be between neighboring cells, thus capacitive power would be much lower, and speeds could be higher.
[1] https://downloads.reactivemicro.com/Electronics/FPGA/Xilinx%...
40 years and the industry still doesn't understand that they should embrace open source for tooling.
I'm reminded of Ken Sheriff's reverse engineering of the original FPGA, the Xilinx XC2064.
https://www.righto.com/2020/09/reverse-engineering-first-fpg...
National Instruments made programming FPGAs accessible to engineers who are not EEs like me via LabVIEW. It was really cool to have loops running at tens of kHz up to 100MHz speeds
It's really too bad that it was locked to NI products and they've kind faded away.
I sometimes like to think of what could have been, if the ability to program FPGAs so easily would have become more popular.
On the 40th anniversary I will confess that for most of my career I thought the “field” in FPGA meant like a field of gates.
I'm surprised there's still an (now AMD) Xilinx campus at Union Ave & Hwy 85.
And pour one out for Altera that was actually founded a year before but took 5 years to arrive at something similar. It was eventually acqui-crushed by Intel.
fpgas are underrated. insane control, hard realtime, tweak logic without touching hardware. and still holding grounds in hft, telecom basebands, satellite payloads, broadcast gear, lab instruments, even some cloud accelerators like aws f1. anywhere latency's tight but logic keeps changing. most move to asic when design's stable but if your workload evolves or margins depend on latency, fpga's the only sane option
Just a note: At the bottom of the page they mention a book on Embedded System Design that they contributed to but there's no link. It took a little digging but I found the book they're talking about: https://us.artechhouse.com/A-Hands-On-Guide-to-Designing-Emb...
Recently posted:
The FPGA turns 40. Where does it go from here? (11.06.2025)
My naive take is they will have some use in dynamic code for AGI
After years of reverse engineering, work ongoing, https://github.com/openxc7
https://f4pga.org & https://news.ycombinator.com/item?id=32861075 (umbrella project) https://www.bunniestudios.com/blog/2017/litex-vs-vivado-firs...> There’s already IP cores for DRAM, PCI express, ethernet, video, a softcore CPU (your choice of or1k or lm32) and more.. LiteX produces a design that uses about 20% of an XC7A50 FPGA with a runtime of about 10 minutes, whereas Vivado produces a design that consumes 85% of the same FPGA with a runtime of about 30-45 minutes.
https://news.ycombinator.com/item?id=39836745#39922534
> you can.. get [FPGA] parts for significant discounts in 1-off quantities through legit Chinese distributors like LCSC. For example, a XC7A35T-2FGG484I is 90$ on Digikey and 20$ at LCSC. I think a personalized deal for that part would be cheaper than 20$ though...