Tesla is reportedly working on a chip to handle all the tasks needed to power the fleet of fully self-driving cars that its CEO Elon Musk promised would be road-ready by 2019. According to CNBC, the electric carmaker is working with AMD to develop the autonomous driving chip. It’s a move that would clearly be in line with the recent hiring of ex-AMD executive Jim Keller to replace Chris Lattner as head of Tesla’s Autopilot hardware engineering effort.
Neither Tesla nor AMD responded to requests for comment, but the CNBC report was seemingly bolstered by comments made by Sanjay Jha, CEO of AMD spinoff GlobalFoundries, a semiconductor foundry, during a conference today that it is working directly with Tesla on producing a chip.
Furthermore, Tesla has already received back samples of the first implementation of its processor and is now running tests on it, a source told CNBC.
The news that Tesla is laboring on its own autonomous driving chip follows the revelation that the company is also developing a new hardware suite with more computing power to help achieve its goal of full automation.
Full autonomy will require vast amounts of computing power to process all the telemetry and data produced by the car’s various cameras and sensors. As such, many of the world’s big chipmakers are staking out positions on autonomous driving. Intel just announced that it was partnering with Alphabet’s Waymo on its autonomous driving project.
Meanwhile, Nvidia is working with Toyota, Audi, Volvo, and several others on its own efforts. Previously, Tesla was working with Nvidia on its latest versions of Autopilot.