Slash Boxes

SoylentNews is people

posted by Fnord666 on Friday September 22 2017, @11:39PM   Printer-friendly
from the cars-aren't-intelligent,-they-only-*think*-they-are dept.

According to CNBC, Tesla is teaming up with AMD to develop a custom chip optimized for AI, to be used for self-driving features in Tesla cars. The head of Tesla's "Autopilot" team is Jim Keller, formerly of AMD and Apple, who helped design the A4 and A5 chips while working at Apple and was lead architect on the Athlon 64 at AMD.

Also at Engadget, TechCrunch, and Business Insider

GlobalFoundries, which fabricates chips for Advanced Micro Devices Inc, said on Thursday that Tesla had not committed to working with it on any autonomous driving technology or product, contradicting an earlier media report. [...] The spokesperson for GlobalFoundries said that Jha’s comments at the GlobalFoundries Technology Conference were not reported accurately.

Original Submission

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 1) by khallow on Saturday September 23 2017, @10:48AM (1 child)

    by khallow (3766) Subscriber Badge on Saturday September 23 2017, @10:48AM (#572068) Journal
    Ok, so this is a fake news story. Let's try to recover something from the exercise. If hypothetically one were to develop a CPU, GPU, or whatnot for supporting an self-driving application, what sort of stuff would be good to stick in there? Massive I/O bandwidth? Image processing support?
  • (Score: 0) by Anonymous Coward on Saturday September 23 2017, @12:22PM

    by Anonymous Coward on Saturday September 23 2017, @12:22PM (#572082)

    Here's what Nvidia is pitching, []

    But this market is a fast moving target (like pedestrians??), with new sensors and new algorithms all the time.