At Google I/O this May, Google announced a custom asic for machine learning. And that they have been using it in the data center for about a year and for well known applications including Search, Maps and also the celebrated win over Lee Sedol at GO. Turns out that it is likely 8 bit doing fixed point arithmetic that gives it much better performance per watt.
Looking forward to see what Nervana comes out with, and what Intel has up it’s sleeve or Qualcomm!
gamesmachinesplay 