Microsoft have been using them in Bing and other projects for a while:
https://www.microsoft.com/en-us/research/project/project-cat...
Word on the street is that this was a vanity project of a VP, and never resulted in performance levels that couldn't be achieved with a little bit of focused optimization of boring old CPU work (threading + SIMD).
There's been a recent trend to increasingly move more compute capabilities into NICs. This has been going on for a while, but has gained a new dimension with cloud providers. For example, with their "Nitro" system, AWS can more or less run their Hypervisor entirely on the NIC and completely offload the network and storage virtualization from their servers. This development is likely to continue. FPGAs are going to play a significant part in that because they allow the customers to reconfigure this hardware according to their needs.
Aren’t they already widely used as NICs? And I many places are beginning to offer them for ML workloads and such.
I don't think "widely", maybe in a few niches? "SmartNICs" are becoming a bit of a thing again, but those are mostly not FPGA-based as far as I know.
Virtual machines are very much a thing now, and virtualisation has made it into network cards reasonably well ... but pretty well nothing else.
In our future datacentre we want to say how many cores, connected to how much ram, how much GPU resource, some NVME etc. etc. and there's going to be a whole lot of very specialised switching and tunnelling going on. This needs to be as close to the cores/cache as possible, a good order of magnitude faster than we run our present networking stuff, and probably an area where there will be a significant pace of development ie a software defined solution would be nice.
So, a software defined north bridge, in essence. And an FPGA is pretty much the only thing we have right now that could do the job.
Because an FPGA lets you optimize your "hardware" solution to a computing problem without the hassle of fabricating a chip of your own (although the performance with an FPGA is much lower than with a custom chip).
What in the world FPGAs have to do in a datacentre?