3
$\begingroup$

What is the difference between a normal processor and a processor designed for AI?

Improve this question
$\endgroup$
1
  • $\begingroup$ There have indeed been very recent reports of AI-oriented processors being integrated into smartphones, such as this Forbes article from 9/28/17. $\endgroup$
    – DukeZhou
    Commented Oct 2, 2017 at 21:37

2 Answers 2

Reset to default
2
$\begingroup$

Parallel processing is very important when computing ANNs. Though they are not designed for AIs, GPUs are widely used in machine learning because of their higher capability of paralel processing and it is due to their higher number of cores comparing CPUs.

All in all, the dedicated hardware should have GPU-like architecture.

Improve this answer
$\endgroup$
2
$\begingroup$

Specialized AI hardware takes advantage of highly parallelizable nature of many neural network designs. GPUs are designed for pixel crunching - coincidentally very paralelisable too. This is why they often offer orders of magnitude better performance (in NN tasks) than CPUs. That being said, GPUs have shortcomings to. First, many of GPU's built in features are not utilized in neural network applications- in many cases accurate floating point operations are not necessary, data for simple calculations involved in NNs. If you remove all the unused features from GPUs and use that extra space for more compute units, you get something like Googles' https://cloud.google.com/blog/big-data/2017/05/an-in-depth-look-at-googles-first-tensor-processing-unit-tpu TPU.

Improve this answer
$\endgroup$
1
  • 1
    $\begingroup$ Some of the newer Nvidia GPUs have half precision operations(fp16) supported also, which allows code to use less memory, and less compute time, but as you mentioned, googles TPU still does have more compute cores because it does not need to support full precision or double precision. $\endgroup$
    – Aiden Grossman
    Commented Oct 1, 2017 at 23:28

You must log in to answer this question.