Tesla to make its own custom SoC (System on Chip) for self-driving cars built by Samsung, report says

Tesla has been rumored to be working on its own SoC (System on Chip) optimized for self-driving cars since we reported that the company quietly hired legendary chip architect Jim Keller from AMD as new “Vice-President of Autopilot Hardware Engineering” earlier this year. While Keller’s hardware engineer experience could be useful for other projects at Tesla, the fact that the automaker poached a team of chip architects and executives from AMD following Keller’s hire fueled the rumor.

In what could now possibly be a confirmation of the rumor, a report from South Korea suggests that Samsung Electronics signed a contract with Tesla to build an ASIC (Application-Specific Integrated Circuit) system – meaning to build its System on Chip with Samsung semiconductors.

Apple used to have a similar ASIC contract with Samsung until it decided to design its own semiconductors following the acquisition of  PA Semi, a company formerly led by Keller and Peter Bannon, who also followed Keller at Tesla just a few weeks later.

The report comes from the Electronic Times in South Korea, which cites an unnamed industry source:

“This is a long-term project that requires about 3 years for design, production of prototype, and mass-production. Working with a leading company like Tesla will provide an opportunity to greatly increase capability of Samsung Electronics’ automotive field.”

We asked Tesla to comment on the report and we will update if we get an answer.

Tesla recently changed its main chip supplier for its Autopilot/self-driving programs. The company was using the EyeQ3 chip from Mobileye since the implementation of the Autopilot program in 2014, but in introducing the second generation of the program that the company hopes will lead to a fully self-driving system, Tesla started equipping every car with a small NVIDIA supercomputer, DrivePX2.

The move allowed the automaker to implement Tesla Vision, its own end-to-end image processing system with machine learning. If the report is true, now the automaker is going a step further and looking to get more involved in the design of this critical hardware for self-driving technology, which needs to be reliable, powerful, and energy-efficient.