News for hackers. Stuff that matters.
Re:New Compute Engine A2 VMs–First Nvidia Ampere A100 GPUs i... by zetazzed on Tuesday July 07, 2020 @12:58PM (#23761193)
I think this is the most in-depth article on Ampere: https://developer.nvidia.com/blog/nvidia-ampere-architecture...

Lots of architectural changes like MIG, new floating point formats, etc. Great to see GCP getting VMs out pretty soon after launch so people can start kicking the tires.

Re:New Compute Engine A2 VMs–First Nvidia Ampere A100 GPUs i... by g_airborne on Tuesday July 07, 2020 @06:06PM (#23764655)
Very cool! Does anyone know how is software support for all these features? It seems that TF doesn’t support the TP32/16 types as of yet. Is this something only CUDA engineers can use right now?

It does seem a little fishy to me that NVIDIA often boasts with figures like 10x performance upgrade whilst in practice those are only possible if you use one of their non-default float types which are hardly supported in most deep learning libraries :(

Re:New Compute Engine A2 VMs–First Nvidia Ampere A100 GPUs i... by zetazzed on Tuesday July 07, 2020 @09:49PM (#23766178)
Both PyTorch and Tensorflow teams have announced they'll support TF32. By design, it interoperates well with existing code, since calling code can just treat it as a regular FP32 value.