IBM Cloud has announced that it is making available Nvidia V100 GPUs, the fastest graphics processing units on the market, available through its cloud computing services. To use the GPUs, customers will need to order up bare metal servers equipped with the processors, and they can utilize up to two GPUs per server.
The Nvidia V100 GPUs were created for the gaming market, but they also offer benefits for artificial intelligence (AI) workloads and cloud-native applications.
IBM Cloud will also offer bare metal and virtual services with the Nvidia Tesla P100, a GPU designed for AI and deep learning workloads. “The combination of IBM high-speed network connectivity and bare metal servers with the Tesla V100 GPUs provides the performance and speed that enterprises need. That means AI models that once needed weeks of computing resources can now be trained in just a few hours,” said IBM's John Considine.