NVIDIA GTC: NXP and NVIDIA Partner to Accelerate AI Deployment

By Ken Briodagh

Senior Technology Editor

Embedded Computing Design

March 19, 2024


NVIDIA GTC: NXP and NVIDIA Partner to Accelerate AI Deployment

At NVIDIA GTC, NXP Semiconductors and NVIDIA announced a new collaboration to enable NVIDIA’s trained AI models to be deployed on NXP’s portfolio of edge processing devices through the eIQ machine learning development environment.

According to the release, the partnership gives developers the ability to accelerate AI development through this integration of the NVIDIA TAO Toolkit into the NXP eIQ machine learning development environment. NXP reportedly is the first semiconductor vendor to integrate the NVIDIA TAO APIs directly within an AI enablement offering.

“AI innovation will define the future of the smart connected world,” said Charles Dachs, Senior Vice President and General Manager, Industrial and IoT Edge, NXP. “Combining NVIDIA’s expertise in training and testing AI models with NXP’s long history of industrial and IoT edge innovation creates a synergy that allows our customers to bring their AI models to market quickly and easily.”

The NVIDIA TAO low-code AI framework is designed to make it easier to leverage trained AI models and fine tune them for specific uses with transfer learning, while NXP’s eIQ development environment makes it easier for developers to deploy AI models to the edge through a combination of software, inference engines, neural network compilers and optimized libraries.

“NVIDIA TAO greatly simplifies the creation and deployment of AI models, including state-of-the-art generative AI models,” said Deepu Talla, Vice President of Robotics and Edge Computing at NVIDIA. “This collaboration brings highly accurate, optimized AI models tuned with NVIDIA TAO and plugged seamlessly into NXP’s eIQ development environment to accelerate edge AI deployments.”

The NXP eIQ machine learning software development environment enables the use of AI algorithms on NXP’s broad portfolio of microcontrollers and microprocessors. It is fully integrated into NXP’s MCUXpresso SDK and Yocto Project Linux development environments, allowing developers to develop complete system-level applications with ease. The eIQ machine learning development environment will directly integrate NVIDIA TAO APIs, delivering a single platform for model AI training, optimization and deployment. NVIDIA TAO provides an API-driven workflow that leverages a collection of pre-trained models and transfer learning to enable users to build custom AI models. NVIDIA TAO provides several optimizations, such as model pruning, that increase the inference throughput.

Ken Briodagh is a writer and editor with two decades of experience under his belt. He is in love with technology and if he had his druthers, he would beta test everything from shoe phones to flying cars. In previous lives, he’s been a short order cook, telemarketer, medical supply technician, mover of the bodies at a funeral home, pirate, poet, partial alliterist, parent, partner and pretender to various thrones. Most of his exploits are either exaggerated or blatantly false.

More from Ken