NVIDIA seems to have scored a fairly large customer lately, as Google has just added Tesla P100 GPUs to their cloud infrastructure. Effective immediately, you can attach up to four of these GPUs to your rented servers on an hourly or monthly basis. According to their pricing calculator, each GPU adds $2.30 per hour to your server’s fee in Oregon and South Carolina, which isn’t a lot if you only use them for short periods of time.
If you need to use them long-term, though, Google has also announced “sustained use discounts” with this blog post, too.
While NVIDIA has technically launched a successor to the P100, the Volta-based V100, the Pascal-based part is still quite interesting. The main focus of the GPU design, GP100, was bringing FP64 performance up to its theoretical maximum of 1/2 FP32. It also has very high memory bandwidth, due to its HBM 2.0 stacks, which is often a huge bottleneck for GPU-based applications.
For NVIDIA, selling high-end GPUs is obviously good. The enterprise market is lucrative, and it validates their push into the really large die sizes. For Google, it gives a huge reason for interested parties to consider them over just defaulting to Amazon. AWS has GPU instances, but they’re currently limited to Kepler and Maxwell (and they offer FPGA-based acceleration, too). They can always catch up, but they haven’t yet, and that's good for Google.