Nvidia Announces New Edge Platform for 'Real-Time' AI, IoT Projects
This week Nvidia announced Nvidia EGX, a new platform that lets enterprises program computing functions on the edge -- i.e., as close to the data as possible.
Nvidia EGX has been architected to provide as much low-latency performance as possible, the company said, offering "real-time" "continuous streaming" ability for factories, warehouses, retailers, enterprises and others, and is designed to work with both microservers and servers.
On the microserver side, the platform can be powered by the Nvidia Jetson Nano, which allows 500 billion operations per second of processor tasks via just "a few watts," meeting the low-power requirements that edge and Internet of Things (IoT) computing projects generally require. On the server side, the power can then be ramped all the way up to be supported by Nvidia T4 servers, which offer support for accelerated workloads with over 10,000 TOPS for intensive real-time AI and other compute-heavy tasks.
"Enterprises demand more powerful computing at the edge to process their oceans of raw data...to make rapid, AI-enhanced decisions that can drive their business," commented Bob Pette, vice president and general manager of Enterprise and Edge Computing at Nvidia, in a prepared statement provided in the company's announcement of EGX. "Nvidia EGX allows them to easily deploy systems to meet their needs on premises, in the cloud or both."
Nvidia also announced that it is partnering with Red Hat to optimize Nvidia EGX with Red Hat's Kubernetes container platform. The company points out that the Nvidia Edge Stack works with the CUDA Kubernetes plug-in and runtimes (and in fact is integrated with CUDA-X), TensorRT and DeepStream. Downloads are available here.
For IoT interconnectivity, the stack works with Microsoft Azure IoT Edge and AWS IoT Greengrass.
A release date for the stack was not provided, but a number of companies are listed on the product page as early adopters.
Becky Nagel is the vice president of Web & Digital Strategy for 1105's Converge360 Group, where she oversees the front-end Web team and deals with all aspects of digital strategy. She also serves as executive editor of the group's media Web sites, and you'll even find her byline on PureAI.com, the group's newest site for enterprise developers working with AI. She recently gave a talk at a leading technical publishers conference about how changes in Web technology may impact publishers' bottom lines. Follow her on twitter @beckynagel.