Re: DIY FPGA Mining rig for any algorithm with fast ROI

Can you give anymore details on what exactly you are going to try to get going with Intel? Are you talking Stratix10 HBM? Or some form of prototype?

Yes, the Stratix 10 parts are equivalent to the Ultrascale+ parts. I believe we'll be able to get the same or better performance for a much lower price point. If FPGA are really going to be viable in the long term to displace GPUs the cost has to be reduced in a significant way. $3995 is ok, right now, while margins are high... But if we really wanted to displace GPUs completely both the cost / perf and power / perf will need to be better than GPUs. I'm hoping that we'll eventually (6-12 months) be able to sell a $1000-2000 board with a stratix 10 or ultrascale+ part that has HBM.

What about this very critical point of view about Intel Stratix 10 HBM ?
https://www.semiaccurate.com/2017/12/19/intels-claims-fpgas-hbm-dont-hold-water/

Both Xilinx and Intel are failing to sample or ship HBM chips announced more than six months ago. I dont think that HBM is coming at mainstream prices in FPGAs anytime soon - even AMD and Nvidia are moving away from it in consumer products.

As far as I'm aware they are at least in some limited fashion shipping the stratix 10 mx series. I'll confirm next week for sure.

I think youre right in that Intel is farther along. Theyve already implemented HBM (or rather MCDRAM) in KNL and have the interposer experience.

I should clarify I dont think HBM is being abandoned, but it is being relegated to higher cost cards and GDDR6 is taking over in the mass production end. I remember buying 100 Fury Xs in 2015 and having the serial numbers be hand written and I think they incremented maybe a few thousand over the year I accumulated mine.