News for hackers. Stuff that matters.
Re:Build a fast deep learning machine for under $1K by nl on Thursday February 09, 2017 @05:44AM (#13605990)
There's a reason AMD is selling deep learning cards with Flash drives built in.

For those not familiar with them, this is the Radeon Pro SSG[1]

This has a built in M2 drive, but this is used as video card memory, NOT main storage. It could possibly allow big (HUGE) models or batches, but doesn't prove fast IO is often a bottleneck.

Practically no one[2] is using these for deep learning. They are marketed to the oil and gas modelling and visualization market and notably the product page (linked above) makes no mention of neural networks or deep learning, and it has never been mentioned in AMD's publicity.

Yes, it might be good for deep learning. And yet, modern deep models do want more memory. But there is a lot that needs to happen for this to be useful: AMD needs to release something like CuDNN and they need to make sure OpenCL is supported as well as CUDA is.

[1] https://arstechnica.com/gadgets/2016/07/amd-radeon-pro-ssg-g..., http://www.amd.com/en-us/press-releases/Pages/amd-radeon-pro...

[2] I'm sure you'll find someone. But show me a published paper or any kind, or even benchmarks showing the use of the extra memory somewhere.

Re:Build a fast deep learning machine for under $1K by gcp on Thursday February 09, 2017 @06:51AM (#13606259)
doesn't prove fast IO is often a bottleneck.

It's not often a bottleneck. In fact it usually isn't. But when it is, you're left wondering why you didn't get an SSD. They're cheap enough now.

Re:Build a fast deep learning machine for under $1K by deepnotderp on Thursday February 09, 2017 @01:03PM (#13609178)
MIOpen is AMD's cuDNN alternative.
Re:Build a fast deep learning machine for under $1K by rockdoe on Thursday February 09, 2017 @01:45PM (#13609613)
Which does not actually exist. It's announced but unreleased.