News for hackers. Stuff that matters.
Re:A new GPU backend for the TVM stack by make3 on Monday October 30, 2017 @02:24PM (#15587564)
they don't need to target the frameworks themselves, just give optimized binaries/kernels for the operations. That's what Nvidia does with cudnn. the people building the frameworks will then wrap these building blocks.

the real preoccupation is that these building blocks need to be as fast or faster than Nvidia's

Re:A new GPU backend for the TVM stack by DannyBee on Monday October 30, 2017 @10:00PM (#15590616)
More likely, you do that, and won't bother. This is the difference between being #1 and #2 in a space.

If what they have works for them, precisely none of these people will bother.

Re:A new GPU backend for the TVM stack by make3 on Tuesday October 31, 2017 @11:54AM (#15594141)
I'm not sure. Cloud compute providers (Google, Amazon & MS) might write the wrappers just to try to give Nvidia competition in the gpu market and force them to let their prices.

they have a huge incentive to go so

Re:A new GPU backend for the TVM stack by dharma1 on Monday October 30, 2017 @02:41PM (#15587733)
Exactly this. A handful of good AMD engineers should be able to squeeze everything out of their own hardware by tuning fast convolution, gemm and other ML related kernels optimised for Vega. That happens once, not for every framework.

AMD's management just doesn't seem to be that interested in ML.