Cuda 9 is comin !!
https://developer.nvidia.com/cuda-toolkit/whatsnewVolta
This beastly GPUboth in size and capabilitiesboasts a whopping 21 billion transistors and 5,120 CUDA cores humming along at 1,455MHz boost clock speeds, all built using a 12-nanometer manufacturing process more advanced than that of Nvidias current GPUs. By comparison, todays Pascal GPU flagship, the 14nm Tesla P100, offers 3,840 CUDA cores and 15 billion transistors. The GeForce GTX 1060 has a quarter as many CUDA cores as the Tesla V100, at 1,280.
The Tesla V100 utilizes 16GB of ultra-fast, 4096-bit high-bandwidth memory to process data quickly.