Telecom News

Nvidia EGX platform delivers real-time AI in GPU edge servers

LinkedIn Google+ Pinterest Tumblr

The American chipset manufacturer Nvidia is rolling out its EGX platform to bring real-time artificial intelligence (AI) to the edge of the network. Nvidia EGX is an accelerated computing platform, which boasts low-latency AI that enables companies to perceive, understand and act in real time on continuous streaming data between 5G base stations, warehouses, retail stores, factories and beyond. AI computing will occur at the edge of the network, where sensors collect data before it is sent to cloud-connected data centers.


This platform is expected to satisfy the increasing demand for AI applications to assist numerous devices streaming continuous raw sensor data and is designed for high-throughput AI at the edge where data is primarily sourced to achieve instantaneous and guaranteed response times while reducing bandwidth to the cloud. According to the company, by 2025, there could be up to 150 billion machine sensors and the Internet of Things (IoT) devices streaming continuous data that will need to be processed.


“Enterprises demand more powerful computing at the edge to process their oceans of raw data – streaming in from countless interactions with customers and facilities – to make rapid, AI-enhanced decisions that can drive their business,” said Bob Pette, Vice president and general manager of Enterprise and Edge Computing at Nvidia.” A scalable platform like Nvidia EGX allows them to easily deploy systems to meet their needs on premises, in the cloud or both.”


According to Nvidia, their new scalable EGX platform starts with the tiny Nvidia Jetson Nano, which in a few watts can provide one-half trillion operations per second (TOPS) of processing for tasks such as image recognition. The platform can be further extended to a full rack of Nvidia T4 servers and deliver more than 10,000 TOPS for real-time speech recognition and other real-time AI tasks.


Furthermore, Nvidia EGX is optimized for running enterprise-grade Kubernetes container platforms such as Red Hat Openshift. Tested with Nvidia Edge Stack, an optimized software suite, these container platforms will simplify the setup, provisioning and management of GPU accelerated infrastructure. To enable hybrid cloud computing, Nvidia EGX-powered systems and devices can connect to cloud IoT services. Customers can remotely manage their services from AWS IoT Greengrass and Microsoft Azure IoT Edge.


Nvidia and its customers will offer a new class of servers for instantaneous AI on real-time streaming data in markets such as telecommunications, medicine, manufacturing, retail and transportation. Early adopters of this solution include more than 40 industry-leading companies and organizations, from BMW Group Logistics to Foxconn D Group.

Write A Comment