Nvidia

How NIO Develops Intelligent Vehicles on NVIDIA HGX

How NIO Develops Intelligent Vehicles on NVIDIA HGX

Building next-generation smart vehicles requires state-of-the-art AI infrastructure.

The electric vehicle manufacturer NIO uses NVIDIA HGX to build a comprehensive data center infrastructure to develop software-defined and AI-powered vehicles. Using high-performance computing, the automaker can continuously iterate on sophisticated deep learning models, creating robust autonomous driving algorithms in a closed-loop environment.

“The complex scenarios faced by mass-produced cars and the massive amount of data generated by these fleets are the cornerstones of NIO’s autonomous driving capabilities,” said Bai Yuli, Head of AI Platforms at NIO. “By using NVIDIA’s high-performance computing solutions, NIO can accelerate the path to autonomous driving.”

NIO has already launched intelligent vehicles built on this infrastructure, such as its all-electric and intelligent flagship sedan, the ET7. Its midsize performance sedan, the ET5, is expected to debut in September.

Besides developing high-performance data centers, both models are built on the Adam supercomputer, powered by four NVIDIA DRIVE Orin SoCs. These vehicles feature self-driving and intelligent cockpit capabilities that are continuously iterated and improved in the data center for a revolutionary customer experience.

Build High-Performance AI Infrastructure with NVIDIA GPUs and Networking

The role of the data center is to ingest, hold, and label massive amounts of data for training large-scale AI models.

Data collection fleets generate hundreds of petabytes of data and billions of images every year. This data is then used to optimize the deep neural networks (DNN) that will operate in vehicles.

NIO’s scalable AI infrastructure is powered by NVIDIA HGX with eight A100 Tensor Core GPUs and NVIDIA ConnectX-6 InfiniBand adapters. This scalable supercomputer cluster consists of NVME SSD servers and interconnects through the high-speed NVIDIA Quantum InfiniBand networking platform.

This powerful infrastructure makes it possible to transfer large amounts of deep learning data to supercomputer memory or NVIDIA A100 video memory at ultra-high speeds of up to 200 Gbps.

NVIDIA HGX A100 is a high-performance server platform designed for AI scenarios, including large datasets and complex models like those powering autonomous vehicles. It integrates a fully optimized NVIDIA AI software stack into NGC.

The platform sets a new benchmark for compute density, condensing 5 petaflops of AI performance and replacing siled infrastructures with a single platform for a wide range of complex AI applications.

With the HGX A100, NIO is able to flexibly develop and deploy scalable AI systems. It also allows the company to increase model development efficiency 20-fold, allowing it to launch autonomous vehicles earlier and scale to newer, faster architectures.

Go forward

NIO is already off to the races with its software-defined lineup, announcing plans to double capacity at its plant in Hefei, China, to 240,000 vehicles per year, with a facility capable of producing up to 300,000. .

As NIO scales its manufacturing capabilities and continues to expand into global markets, NVIDIA HGX scales with them, enabling the deployment of one of the most advanced AI platforms in the automotive industry.