NXP taps Kinara to be the ‘CUDA of automotive AI‘
NXP is aiming to use its acquisition of Kinara to create an automotive AI software ecosystem in automotive similar to that Nvidia’s CUDA.
The initial target for the Kinara Ara-2 generative AI chip is in the vehicle cabin for driver monitoring or infotainment copilots to query a manual or monitor the cabin and respond to conditions, says Rutger Vrijen, senior vice president and head of strategy for the connected edge at NXP.
The $307m deal announced yesterday is set to complete in the next few months.
“There’s tremendous opportunities to help Kinara scale in combination with the broader portfolio. But the longer term vision is to make it really easy for our customers to adopt this across all our devices,” he said, “We are not at CUDA level yet but the software and toolchain first strategy is something that will enable us to do that. Kinara is not just a provider of silicon but focussed on making the silicon usable.”
The integration of the toolchain and model zoo into NXP’s eIQ tool will be shown at the Embedded World exhibition next month, and it has already been tested with the NXP Linux and FreeRTOS distributions.
“The programmabilility and the ability to use the compiler suite and model zoo was a very important consideration for NXP. It came down to the use cases that we see as important which is what pointed us to Kinara.”
Kinara is working on a pipeline of devices beyond the Ara-2 that will combine LLM, CNNs and vision language models (VLM) that use the same transformer models for computer vision.
“Future chips for other use cases are under development for our current customers but also target the customers we will get to with NXP. There are products in the pipeline and LLMs and VLMs are very important work loads and these will work with CNNs,” said Wajahat Qadeer, chief architect at Kinara.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
