Microsoft today announced that its N-Series of virtual machine (VM) instances backed by graphics processing units (GPUs) are now available in preview for developers to use in the Azure public cloud. Microsoft first announced the N-Series in September.
There are two categories of these new instances: the NC series and the NV series. The former, which uses Nvidia Tesla K80 GPUs, is meant for compute-intensive processes, while the latter, relying on Nvidia Tesla M60 and Nvidia Grid GPUs, is oriented around visual workloads. They all work in association with Intel E5-2690v3 chips. The new instances are initially only available in Azure’s South Central US (Texas) region, Microsoft Azure director of program management Corey Sanders wrote in a blog post.
Sanders is especially bullish about the NC instances. “This SKU … offers the fastest computational GPU available in the public cloud,” he wrote. “Furthermore, unlike other providers, these new SKUs expose the GPUs through discreet device assignment (DDA) which results in close to bare-metal performance.”
Public cloud market leader Amazon Web Services has offered GPU-backed instances for years, and IBM SoftLayer introduced them last year. The Google public cloud has not launched them.
June 5th: The AI Audit in NYC
Join us next week in NYC to engage with top executive leaders, delving into strategies for auditing AI models to ensure fairness, optimal performance, and ethical compliance across diverse organizations. Secure your attendance for this exclusive invite-only event.
You can sign up for access to the GPU-backed instances here.
