Bangalore: At the Computex 2017 Trade Show in Taiwan, Nvidia launched an alliance partner program with some of the world’s original design manufacturers (ODM) such as Foxconn, Inventec, Quanta and Wistron.
The strategy behind the new program is to get ahead of the anticipated customer demand for artificial intelligence (AI) cloud computing.
This new program will also be part of Nvidia’s HGX Partner Program, the company said in a statement. The program works to provide each ODM with early access to the Nvidia HGX reference architecture, Nvidia GPU computing technologies and design guidelines.
HGX is the same data centre design used in Microsoft’s Project Olympus initiative, Facebook’s Big Basin systems and Nvidia DGX-1 AI supercomputers.
Foxconn and Quanta can use HGX as a starter “recipe,” ODM partners can work with Nvidia to design and bring to market a wide range of qualified GPU-accelerated systems for hyperscale data centres.
According to the graphic chip maker, the overall demand for AI computing resources has risen sharply over the past year, so has the market adoption and performance. Today, 10 of the world’s top 10 hyperscale businesses are using Nvidia GPU accelerators in their data centres.
The program will also support the release of Nvidia’s Volta architecture-based GPUs. Ian Buck, general manager of Accelerated Computing at Nvidia, said, “Accelerated computing is evolving rapidly — in just one year the company has tripled the deep learning performance of its Tesla GPUs, as an example — and this is having a significant impact on the way systems are designed.”
The standard HGX design architecture includes eight Nvidia Tesla GPU accelerators in the SXM2 form factor and connected in a cube mesh using Nvidia NVLink high-speed interconnects and optimized PCIe topologies.
With a modular design, HGX enclosures are suited for deployment in existing data centre racks, using hyperscale CPU nodes as needed. Both Nvidia Tesla P100 and V100 GPU accelerators are compatible with HGX. This allows for immediate upgrades of all HGX-based products once V100 GPUs become available later this year.