News for hackers. Stuff that matters.

A comment on Linode GPU Instances. Parent comment

Re:Linode GPU Instances by danieldk on Thursday June 20, 2019 @01:56AM (#20230293)
If you really want low cost to compute for Deep Learning and you needs lots of compute and don't want to pay for V100s, then the AMD Vega R7 is the card for you. 700 dollars, 16GB Ram, 1TB of GPU bandwidth (higher than the V100!), works with Tensorflow (pip install tensorflow-rocm), and about 60% of the performance on resnet-50.FP64 is not fully gimped (it is halved, i think - so still quite good).

Two of my colleagues use high-end AMD GPUs to train RNNs and transformers with tensorflow-rocm. There are still some nasty bugs (e.g. [1]), so it is currently not for everyone. However, given how far they have come compared to 1-2 years ago, it is very likely that in a year or so, they are a real competitor to NVIDIA for compute. That competition was long needed.

[1] https://github.com/ROCmSoftwarePlatform/tensorflow-upstream/...

[ Parent | on HN ]
Re:Linode GPU Instances by jamesblonde on Thursday June 20, 2019 @03:27AM (#20230686)
Agreed, it is not quite prime-time yet. They are trying to upstream all the ROCm stuff in TensorFlow, and when it gets into mainline and stabilizes, i agree that it has great potential for take-off - particularly from price-sensitive researchers and large companies who need huge GPU farms.
[ Parent | on HN ]
Re:Linode GPU Instances by ksec on Thursday June 20, 2019 @05:01AM (#20231086)
Two Questions.

I wonder if Google is in any way helping AMD in the TensorFlow and ROCm?

What happen when Intel join the GPU race in 2020. Making their own ROCm again?

[ Parent | on HN ]