Providing hyperscale data centers with a fast, flexible path for AI, the new HGX-1 hyperscale GPU accelerator is an open-source design released in conjunction with Microsoft's Project Olympus.

HGX-1 does for cloud-based AI workloads what ATX -- Advanced Technology eXtended -- did for PC motherboards when it was introduced more than two decades ago. The new architecture is designed to meet the demand for AI computing in the cloud -- in fields such as autonomous driving, personalised healthcare, superhuman voice recognition, data and video analytics, and molecular simulations.

Nvidia supreme dalek Jen-Hsun Huang said that AI is a new computing model that requires a new architecture and the HGX-1 hyperscale GPU accelerator will do for AI cloud computing what the ATX standard did to make PCs pervasive today. It will enable cloud-service providers to easily adopt NVIDIA GPUs to meet surging demand for AI computing.

Microsoft's Azure Hardware Infrastructure general manager Kushagra Vaid said: "The HGX-1 AI accelerator provides extreme performance scalability to meet the demanding requirements of fast-growing machine learning workloads, and its unique design allows it to be easily adopted into existing data centers around the world."

Writing in his bog, Vaid claimed that thousands of enterprises and startups worldwide that are investing in AI and adopting AI-based approaches and the HGX-1 architecture provides unprecedented configurability and performance in the cloud.

The system is based around eight Nvidia Tesla P100 GPUs in a single chassis and features a new switching design based around Nvidia's NVLink and the PCIe standard. This allows a CPU to dynamically connect to any number of GPUs.

It allows cloud service providers that standardize on the HGX-1 infrastructure to offer customers a range of CPU and GPU machine instance configurations. The modular design of the HGX-1 allows for optimal performance no matter the workload. It provides up to 100x faster deep learning performance compared with legacy CPU-based servers, and is estimated at one-fifth the cost for conducting AI training and one-tenth the cost for AI inferencing.

HGX-1 offers existing hyperscale data centers a quick, simple path to be ready for AI.

The companies are sharing the design widely as part of Microsoft's Project Olympus contribution to the Open Compute Project, Sharing the reference design with the broader Open Compute Project community means that enterprises can easily purchase and deploy the same design in their own data centers.