Nvidia Announces Tesla P40 and P4 - Neural Network Inference, Big and Small

Re:Nvidia Announces Tesla P40 and P4 - Neural Network Infere... by aab0 on Tuesday September 13, 2016 @02:03PM (#12490740)

For a 4x boost, I imagine Tensorflow and Torch will get support shortly after the GPUs start shipping in real quantities.

[ Parent | on HN ]

Re:Nvidia Announces Tesla P40 and P4 - Neural Network Infere... by Eridrus on Tuesday September 13, 2016 @04:55PM (#12492150)

It's a 2x boost for training since you can't use int8 for training and need fp16.

INT8 is a 4x for inference, but most people aren't using GPUs for inference atm.

[ Parent | on HN ]

Re:Nvidia Announces Tesla P40 and P4 - Neural Network Infere... by scottlegrand on Tuesday September 13, 2016 @07:42PM (#12493160)

Some of us are...

https://blogs.aws.amazon.com/bigdata/post/TxGEL8IJ0CAXTK/Gen...

[ Parent | on HN ]

Re:Nvidia Announces Tesla P40 and P4 - Neural Network Infere... by Eridrus on Wednesday September 14, 2016 @10:43AM (#12497350)

Fair enough; when I said most people I meant companies who are not AmaGooFaceSoft and their international equivalents. Though I can't quite tell if you're doing GPU batch predictions and storing them or doing them in realtime with Spark Streaming.

Unrelated question though: any chance you will do blog post/paper about how DSSTNE does automatic model parallelism and gets good sparse performance compared to cuSparse/etc?

[ Parent | on HN ]