NVIDIA has launched two servers designed to bring real-time edge AI to manufacturing and other industrial applications. Both servers, one designed for larger industrial premises, the other a micro-edge server for smaller industrial applications, are supported by AI-optimised, cloud-native software designed for 5G and industrial robotics applications.

Both part of NVIDIA’s EGX Edge AI platform, the EGX A100 is designed for larger commercial off-the-shelf servers, while the tiny EGX Jetson Xavier NX is for micro-edge servers.

The NVIDIA EGX Edge AI platform provides farms and factories with real-time processing and protection for massive amounts of data streaming from trillions of edge sensors. The platform makes it possible to deploy, manage and update fleets of servers securely and remotely.

The EGX A100 converged accelerator and EGX Jetson Xavier NX micro-edge server are created to serve different size, cost and performance needs. Servers powered by the EGX A100 can manage hundreds of cameras in airports, for example, while the EGX Jetson Xavier NX is built to manage a handful of cameras in convenience stores. Cloud-native support ensures the entire EGX lineup can use the same optimised AI software to easily build and deploy AI applications.

“The fusion of IoT and AI has launched the ‘smart everything’ revolution,” said Jensen Huang, founder and CEO of NVIDIA. “Large industries can now offer intelligent connected products and services like the phone industry has with the smartphone. NVIDIA’s EGX Edge AI platform transforms a standard server into a mini, cloud-native, secure, AI data centre. With our AI application frameworks, companies can build AI services ranging from smart retail to robotic factories to automated call centres.”

The EGX A100 is the first edge AI product based on the NVIDIA Ampere architecture.  It combines the groundbreaking computing performance of the NVIDIA Ampere architecture with the accelerated networking and critical security capabilities of the NVIDIA Mellanox ConnectX-6 Dx SmartNIC to transform standard and purpose-built edge servers into secure, cloud-native AI supercomputers.

NVIDIA says that its Ampere architecture — the company’s eighth-generation GPU architecture — provides the largest-ever generational leap in performance for a range of compute-intensive workloads, including AI inference and 5G applications running at the edge. This allows the EGX A100 to process high-volume streaming data in real time from cameras and other IoT sensors to drive faster insights and higher business efficiency.

“Data, AI and intelligent cloud-native applications are transforming the enterprise edge in every industry,” said Chris Wright, senior vice president and chief technology officer at Red Hat. “NVIDIA’s new EGX A100 converged accelerators combined with precompiled drivers for Red Hat Enterprise Linux and certified operators for Red Hat OpenShift simplify deployment and management of the hardware and help our joint customers address some of the most demanding AI, edge and 5G workloads.”

With an NVIDIA Mellanox ConnectX-6 Dx network card, the EGX A100 can receive up to 200 Gbps of data and send it directly to the GPU memory for AI or 5G signal processing. With the introduction of NVIDIA Mellanox’s time-triggered transport technology for telco (5T for 5G), EGX A100 is a cloud-native, software-defined accelerator that can handle the most latency-sensitive use cases for 5G. This provides the ultimate AI and 5G platform for making intelligent real-time decisions at the points of action — stores, hospitals and factory floors.

“We’ve been collaborating with NVIDIA to build Mavenir’s high-performance virtualised 5G radio access network and accelerated 5G packet core network,” said Pardeep Kohli, president and CEO of Mavenir. “This will enable us to deliver a wide range of new GPU-accelerated 5G services from AI/ML to AR/VR applications.”

NVIDIA describes the EGX Jetson Xavier NX as “the world’s smallest, most powerful AI supercomputer for microservers and edge AIoT boxes”. It has more than 20 solutions now available from ecosystem partners. 

The EGX Jetson Xavier NX has the power of an NVIDIA Xavier SoC in a credit card-size module, and running the EGX cloud-native software stack, can process streaming data from multiple high-resolution sensors.  The module provides up to 21 TOPS at 15W, or 14 TOPS at 10W. 

NVIDIA says that the EGX Jetson Xavier NX “opens the door for embedded edge-computing devices that demand increased performance to support AI workloads but are constrained by size, weight, power budget or cost”.

The EGX Edge AI platform’s cloud-native architecture allows it to run containerised software to support a range of GPU-accelerated workloads.

NVIDIA application frameworks include Clara for healthcare, Aerial for telcos, Jarvis for conversational AI, Isaac for robotics, and Metropolis for smart cities, retail, transportation and more. They can be used together or individually and open new possibilities for a variety of edge use cases.

With support for cloud-native technologies now available across the entire NVIDIA EGX lineup, manufacturers of intelligent machines and developers of AI applications can build and deploy high-quality, software-defined features on embedded and edge devices targeting robotics, smart cities, healthcare, industrial IoT and more.

Existing edge servers enabled with NVIDIA EGX software are available from global enterprise computing providers Atos, Dell Technologies, Fujitsu, GIGABYTE, Hewlett Packard Enterprise, IBM, Inspur, Lenovo, Quanta/QCT and Supermicro. They are also available from major server and IoT system makers such as ADLINK and Advantech.

These servers along with optimised application frameworks can be used by software vendors such as Whiteboard Coordinator, Deep Vision AI, IronYun, Malong and SAFR by RealNetworks to build and deploy healthcare, retail, manufacturing and smart cities solutions.