The year is 2035; humanoid robots serve humanity, which is protected by the Three Laws of Robotics. Every robot and machine created has a positronic brain. This brain is a fictional technological device, it functions as a central processing unit for robots and in some unspecified way, provides them with a form of consciousness and artificial intelligence.
Those positronic brains are connected to a main central positronic brain (much like a data center) that gathers data, controls, trains and over the air updates the smaller positronic brains that are embedded on the fictional robots and machines.
This scenario is obviously lifted from the pages of Isaac Asimov’s classic novel “I, Robot.” Nvidia is beginning to blend fiction with fact.
NVIDIA and Jensen Huang today announced two products for EGX AI Edge platform, the EGX A100 for larger commercial off-the-shelf servers and the tiny EGX Jetson Xavier NX for micro-edge servers, delivering high performance, secure AI processing at the edge.
With the NVIDIA EGX AI Edge platform, factories, hospitals, stores and farms can carry out real time processing and protection of the amounts of data streaming from trillions of edge sensors. The platform makes it possible to securely deploy, manage and update fleets of servers 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 optimized 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 have with the smartphone. NVIDIA’s EGX AI Edge platform transforms a standard server into a mini cloud-native, secure, AI data center. With our AI application frameworks, companies can build AI services ranging from smart retail, robotic factories, to automated call centers.”
EGX A100 Powered by NVIDIA Ampere Architecture
The EGX A100 is the first edge AI product based on the NVIDIA Ampere architecture. NVIDIA believes that as AI moves increasingly to the edge; organizations can include EGX A100 in their servers to carry out real-time processing and protection of the massive amounts of streaming data from edge sensors.
It combines the 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.
The NVIDIA Ampere architecture, the company’s eighth-generation GPU architecture, delivers the largest-ever generational leap in performance for a wide 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.
With an NVIDIA Mellanox ConnectX-6 Dx network card onboard, 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 platforms for making intelligent real-time decisions at the points of action, stores, hospitals and factory floors.
The EGX Jetson Xavier NX
The EGX Jetson Xavier NX is the smallest, powerful AI supercomputer for microservers and edge AIoT boxes, with more than 20 solutions now available from ecosystem partners. It packs the power of an NVIDIA Xavier SoC into a credit-card sized module. EGX Jetson Xavier NX, running the EGX cloud-native software stack, can quickly process streaming data from multiple high-resolution sensors.
The energy-efficient module delivers up to 21 TOPS at 15W, or 14 TOPS at 10W. As a result, 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.
What about Autonomous Driving?
NVIDIA said that the company will keep on developing hardware and software for autonomous driving applications and the next NVIDIA Drive platforms will be based on the Orin and Ampere programmable architecture.
Different Levels of autonomy will require different platforms and horsepower, which will be dependent of the power that each platform consumes within the vehicle while in autonomous driving mode.
Xpeng Motors announced a rollout of their P7 vehicles powered by NVIDIA Drive and will be available for purchase next month.
The Xpeng P7 features the NVIDIA DRIVE AGX Xavier platform for its XPILOT3.0. Signaling the EV maker’s confidence in NVIDIA’s AI compute platform, Xpeng also announced it will leverage the DRIVE platform for its next production model.
Xpeng Motors is programming applications for autonomous driving and automated features on top of NVIDIA’s DRIVE OS software platform.
The Xpeng P7 is the company’s first intelligent EV to be powered by the NVIDIA DRIVE AGX platform, which features the high-performance, energy-efficient Xavier system-on-a-chip (SoC). It is equipped with 12 ultrasonic sensors, five high-precision millimeter-wave radars, 13 autonomous driving cameras, plus one in-car camera with HD map and high-precision positioning. The smart electric sedan will bring several autonomous driving feature-firsts to Chinese customers, including SAE Level 3 -ready full-scenario autonomous driving functions for highways, urban roads and valet parking.
Delivering 30 TOPS (trillions of operations per second) of performance while consuming only 30 watts of power, Xavier is the first production-level SoC dedicated to automated and autonomous driving that meets today’s rigorous safety standards and regulatory requirements. Architected for safety, Xavier offers the redundancy and diversity necessary to process data from a variety of sensors, and is the path to production for highly automated and autonomous driving systems.
Faraday Future also announced that it is deploying the NVIDIA DRIVE AGX Xavier platform in its flagship luxury FF 91 electric vehicle.
Implications
Getting into the data center business is hard and NVIDIA knows that, but there is a high potential for NVIDIA’s technology and CUDA software development to be more widely available to developers and everyday users.
The automotive announcements this time were mostly focused on scaling to ADAS platforms, SAE L2+ and through fully autonomous Level 5 systems. The announcements were also focused on the development of new software applications, algorithms and deep neural networks in collaboration with Edge and AI applications for inference and training on the server.
NVIDIA continues to strive to build the ecosystem that it envisions, in which it plays a key role in everything from the chip and system architecture through the software stack to the simulation software in the data center and the very architecture of that data center itself.