Project Trillium is Arm's machine learning platform for edge devices including mobile and embedded systems.
NVDLA is based on Nvidia Xavier, which was claimed to be the world's most powerful system on a chip when launched earlier this year. Xavier was designed to process sensor data for autonomous vehicles.
Benefits of NVDLA include forthcoming support in forthcoming versions of the TensorRT deep learning accelerator, and the frequent of new features through open source contributions from the research community.
"Today, we are one step closer to that vision by incorporating Nvidia into the Arm Project Trillion platform, as our entire ecosystem will immediately benefit from the expertise and capabilities our two companies bring in AI and IoT."
Nvidia vice-president and general manager of autonomous machines Deepu Talla said "Inferencing will become a core capability of every IoT device in the future.
"Our partnership with Arm will help drive this wave of adoption by making it easy for hundreds of chip companies to incorporate deep learning technology."
This, the partners hope, will put affordable intelligent devices into billions of consumers' hands around the world.
While ASICs can be a lower-cost option when designing an edge device, Nvidia vice-president and general manager of accelerated computing Ian Buck observed that the high level of innovation in this part of the industry means a programmable component is generally preferable.
Furthermore, the selection of Nvidia's platform provides an opportunity to take advantage of developments up and down the stack, he added. "That ecosytem is really important."
The arrangement will give rise to "a new category of chips" predicted Nvidia founder and chief executive Jensen Huang: the "IoT AI SoC."
AI is complicated, he said, but "we worked with Arm to make it simple [for IoT]".
Disclosure: The writer attended Nvidia's GPU Technology Conference as a guest of the company.