Tesla Will Have Its Own A.I. Chip for Self – Driving Cars
Tesla is very close to having its own chip for managing self – driving tasks in its vehicles.
The car manufacturer has received first concepts of the first application for its hardware and is now testing them. The aim of building its own chip is to decrease Tesla’s dependence on other companies. However, Tesla cannot handle its chip development vision alone, therefore it will build on top of AMD academic property. Currently, Tesla is using Nvidia’s processors for its self – driving cars.
AMD shares spiked after CNBC reported that the company is working with Tesla. Parts of the stock ended the day approximately 5% higher and continued to increase after several hours.
Sanjay Jha, CEO of AMD spin – off and chip fabricator GlobalFoundries, said at the company’s conference in Santa Clara, California, mentioned Tesla as an example of companies that were working with fabricators.
In a remark, GlobalFoundries said the company does not comment on customers or potential customers and denied. Jha said that the company was working directly with Tesla.
Tesla’s silicon project is bounding ahead under the leadership of longtime chip architect Jim Keller. He is the head of Autopilot hardware and software since the departure of Apple veteran, Chris Lattner in June. Keller joined Tesla in early 2016 following two duties at AMD and one at Apple.
Built chip by Tesla could help to get closer to delivering totally autonomous driving. Tesla CEO Elon Musk promised this year that capability will be available to consumers in 2019.
AMD declined to comment. Tesla said it would not leave a comment on rumors.
Long ago, Tesla was using chips from Mobileye, but the two companies parted ways last year after an accident involving a Mobileye – powered Tesla. Currently, Tesla vehicles use Nvidia graphics processing units as part of the Autopilot self – driving hardware. Earlier this year Intel acquired Mobileye for more than $15 billion.
Particularly, Tesla is not working with Intel, which had worked with Alphabet’s Waymo car manufacturing group.
As a rule, GPUs from the likes of Nvidia, which is widely used today for various types of AI workloads, can do many things but are not designed with just a few computing jobs in mind, hence the custom chip development. Plus, Tesla would be less impacted by pricing dictated by Nvidia if it switches to in-house hardware.
Microsoft is working on its own A.I. chip for the HoloLens. And Apple has incorporated an AI chip into its top – of – the – line iPhone X. Alphabet has already built two generations of an AI chip that can work as a GPU alternative.
