News for hackers. Stuff that matters.
Re:A Cloud-Scale Acceleration Architecture: FPGAs in Microso... by webaholic on Friday October 21, 2016 @10:27PM (#12766734)
And how is any of that different from providing GPUs in the cloud? I am not saying that they provide them for free. They can charge for all of that support and tools.

We haven't reached a stage where fpgas make economical sense for small customers. GPUs were in the same stage 5 years ago. I hope Microsoft becomes a trail blazer in bringing fpgas on par with GPUs. They have one of the best tool-chain teams working for them, so it is doable.

Re:A Cloud-Scale Acceleration Architecture: FPGAs in Microso... by tw04 on Friday October 21, 2016 @11:33PM (#12766997)
A GPU doesn't have custom (potentially proprietary) logic programmed into it. It's the same reason we have shared CPUs but not FPGAs.
Re:A Cloud-Scale Acceleration Architecture: FPGAs in Microso... by monocasa on Saturday October 22, 2016 @05:20PM (#12770616)
GPUs had their own MMUs five years ago for running user shaders.