NVIDIA has announced NVIDIA EGX, an accelerated computing platform that would enable companies to perform low-latency AI (artificial intelligence) at the edge – to perceive, understand and act in real time on continuous streaming data between 5G base stations, warehouses, retail stores, factories and beyond.
This NVIDIA EGX platform was created by NVIDIA to meet the growing demand to perform instantaneous, high-throughput AI at the edge – where data is created – with guaranteed response times, while reducing the amount of data that must be sent to the cloud.
Edge servers like those in the NVIDIA EGX platform will be distributed throughout the world to process data in real time from these sensors.
“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.”
By 2025, 150 billion machine sensors and IoT devices will stream continuous data that will need to be processed, according to NVIDIA.
Scalability, Enterprise Features
EGX 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. And it spans all the way to a full rack of NVIDIA T4 servers, delivering more than 10,000 TOPS for real-time speech recognition and other real-time AI tasks.
NVIDIA has partnered with Red Hat to integrate and optimize its NVIDIA Edge Stack with enterprise-grade Kubernetes container orchestration platform, OpenShift. NVIDIA Edge Stack is optimized software that includes NVIDIA drivers, a CUDA Kubernetes plugin, a CUDA container runtime, CUDA-X libraries and containerized AI frameworks and applications, including TensorRT, TensorRT Inference Server and DeepStream. NVIDIA Edge Stack is optimized for certified servers and downloadable from the NVIDIA NGC registry.
“Red Hat is committed to providing a consistent experience for any workload, footprint and location, from the hybrid cloud to the edge,” said Chris Wright, chief technology officer (CTO) at Red Hat. “By combining Red Hat OpenShift and NVIDIA EGX-enabled platforms, customers can better optimize their distributed operations with a consistent, high-performance, container-centric environment.”
An ‘On-Prem AI Cloud-in-a-Box’
EGX combines the full range of NVIDIA AI computing technologies with Red Hat OpenShift and NVIDIA Edge Stack together with Mellanox and Cisco security, networking and storage technologies. This would enable companies in the largest industries – telecom, manufacturing, retail, healthcare and transportation – to quickly set up secured, enterprise-grade AI infrastructures.
“Mellanox Smart NICs and switches provide the ideal I/O connectivity for data access that scale from the edge to hyperscale data centers,” said Michael Kagan, chief technology officer (CTO) at Mellanox Technologies. “The combination of high-performance, low-latency and accelerated networking provides a new infrastructure tier of computing that is critical to efficiently access and supply the data needed to fuel the next generation of advanced AI solutions on edge platforms such as NVIDIA EGX.”
Microsoft Azure, AWS
NVIDIA AI computing is offered by major clouds and is architecturally compatible with NVIDIA EGX. AI applications developed in the cloud can run on NVIDIA EGX and vice versa. NVIDIA Edge Stack connects to major cloud IoT services, and customers can remotely manage their service from AWS IoT Greengrass and Microsoft Azure IoT Edge.
“Azure IoT Edge helps customers deploy cloud service to their IoT devices quickly and securely,” said Sam George, director of Azure IoT Edge. “We look forward to supporting NVIDIA’s EGX edge platform on Azure IoT Edge devices so that customers can deploy AI workloads targeting EGX-compatible hardware.”
EGX servers are available from global enterprise computing providers ATOS, Cisco, Dell EMC, Fujitsu, Hewlett Packard Enterprise, Inspur and Lenovo. They are also available from major server and IoT system makers Abaco, Acer, ADLINK, Advantech, ASRock Rack, ASUS, AverMedia, Cloudian, Connect Tech, Curtiss-Wright, GIGABYTE, Leetop, MiiVii, Musashi Seimitsu, QCT, Sugon, Supermicro, Tyan, WiBase and Wiwynn.
NVIDIA EGX servers are tuned for NVIDIA Edge Stack and NGC-Ready validated for CUDA-accelerated containers.