Re:Intel Introduces Neuromorphic Test Chip
by hedgehog on Monday September 25, 2017 @09:19PM
(#15335449)
GPUs are generally much more flexible and can run something resembling a normal C program. From the little public information available chips like Google TPU or NVIDIA's Tensor Core (a functional unit on the Volta architecture) are essentially hard-wired to do exactly low precision matrix multiplication. Less flexible but more efficient when you know that's what your workload is.
https://devblogs.nvidia.com/parallelforall/inside-volta/
https://www.nextplatform.com/2017/04/05/first-depth-look-goo...
Re:Intel Introduces Neuromorphic Test Chip
by rileyphone on Monday September 25, 2017 @09:17PM
(#15335439)
From what I can tell, Google's TPUs are boiling GPUs down to the essence of what they do in TensorFlow, namely a "higher volume of reduced precision computation" [1].
Re:Intel Introduces Neuromorphic Test Chip
by dnautics on Tuesday September 26, 2017 @02:41AM
(#15336669)
no, GPUs are vector math engines. To be fair, you can assemble a matrix multiply from vector math, but it is not quite the same. In spirit, GPUs are closer to matrix engines than neuromorphic chips.
Excuse my ignorance, but aren't GPUs exactly that?