News for hackers. Stuff that matters.
Re:Can FPGAs Beat GPUs in Accelerating Next-Generation Deep ... by jsheard on Tuesday March 21, 2017 @07:27PM (#13927234)
You're thinking of Nvidia's GP100 chip, which does run FP16 twice as fast as FP32. GP100 is only used on the Tesla P100 and Quadro GP100 cards though.

The Titan X Pascal (and 1080ti) uses the smaller GP102 chip, which as znfi pointed out is practically useless for FP16.

There are no comments on this comment yet.