News for hackers. Stuff that matters.

A comment on Accelerating TensorFlow Performance on Mac. Parent comment

Re:Accelerating TensorFlow Performance on Mac by skwb on Wednesday November 18, 2020 @07:35PM (#25144747)
My gut instincts (based off of nothing but pure speculation and being a ML developer for several years) says no.

For one, the M1 engine has 16 cores, vs over 1,500 for a 1660 series NVIDA card. I know it may not be apples to apples, but I have a very hard time believing it would be able to keep up with even the most marginal card for training.

[ Parent | on HN ]
Re:Accelerating TensorFlow Performance on Mac by wffurr on Wednesday November 18, 2020 @08:31PM (#25145192)
I don’t know about the neural engine, but the GPU on the M1 has 128 EUs in each of the 8 cores, making for 1024 EUs total. It’s not quite in the same league as a 1660 Ti but it’s close: https://www.anandtech.com/show/16252/mac-mini-apple-m1-teste...
[ Parent | on HN ]