Google is the latest cloud provider to announce the availability of Nvidia Tesla V100 GPUs on Compute Engine and Kubernetes Engine in beta.
The Nvidia Tesla V100 GPUs were launched in the first half of 2017. It is a data centre GPU build to accelerate artificial intelligence (AI), high performance computing (HPC) and graphics.
It is powered by Nvidia's Volta, the Tesla V100 is the flagship product of Tesla data centre computing platform for deep learning, HPC and graphics. The Tesla platform accelerates over 500 HPC applications and every major deep learning framework.
According to Google product managers Chris Kleban and Ari Liberman, users can now select as many as eight Nvidia Tesla V100 GPUs, 96 vCPU and 624GB of system memory in a single VM (virtual machine), receiving up to one petaflop of mixed precision hardware acceleration performance.
"The next generation of NVLink interconnects deliver up to 300GB/s of GPU-to-GPU bandwidth, 9X over PCIe, boosting performance on deep learning and HPC workloads by up to 40 per cent," they wrote in a blog post.
Currently, the Nvidia Tesla V100 GPUs are available in the following regions: us-west1, us-central1 and europe-west4.
Google has also announced that the NVidia Tesla P100 GPUs are now generally available for those seeking a "balance between price and performance". This option is available in europe-west4 (Netherlands) in addition to us-west1, us-central1, us-east1, europe-west1 and asia-east1 (Taiwan).
According to Kleban and Liberman, users can select up to four P100 GPUs, 96 vCPUs and 624GB of memory per virtual machine.
"This announcement provides more choice and flexibility for Australian businesses using Google Cloud, helping to support demanding workloads such as machine learning and high-performance computing," Google Cloud country director A/NZ Colin Timm said.
Google is not the first to offer the NVidia Tesla V100 GPUs; in fact the company is the last of the top cloud providers to make it available.
Amazon Web Services (AWS) announced in October 2017 that it was making available the GPUs in four regions. In November, Microsoft announced it was kicking off a beta of NCv3, an Azure VM.
IBM soon followed in January 2018, saying it was the first to offer a comprehensive suite of GPUs including the P100, K80 and M60 on IBM Cloud bare metal and virtual servers and it was now introducing the Tesla V100.