Re:An In-Depth Look at Google's Tensor Processing Unit Archi...
by throwaway71958 on Thursday April 06, 2017 @02:19AM
(#14048361)
Note however, that on Intel it's actually slower than run off the mill float32 linear algebra library like Eigen or OpenBLAS. Its main forte seems to be ARM.
https://github.com/google/gemmlowp
(Used in tensorflow)