This site may earn chapter commissions from the links on this page. Terms of use.

Nvidia DRIVE Xavier

It's been two years since Elon Musk said that Tesla would develop its own chips to facilitate autonomous driving and began hiring a squad of designers and executives to brand information technology happen. This week Musk went public with the results. Tesla has developed its own silicon for running the neural networks it uses to practice vision processing in its AutoPilot software. The company is building information technology into a computer that'south a plug-in replacement for the Nvidia Drive PX2 systems it currently uses for AutoPilot 2.5-equipped cars.

Musk touts Tesla'south homegrown processor as being 10 times faster than what they can buy from Nvidia or anyone else today, stating the flake can analyze up to 2,000 frames of video per second instead of the current 200. Industry insiders I've spoken with agree that this type of performance improvement over the current PX2 performance is needed to achieve Level iv or Level 5 autonomous driving. So far, so good. However, Nvidia is already shipping samples of a new car reckoner, Drive Xavier, that is an guild of magnitude faster than the PX2. It is congenital around Nvidia'south new, and AI-targeted, Volta architecture that features Tensor Cores rather than the much older and more full general purpose Pascal chips used in the PX2.

New Computer Pits Tesla's Focused Evolution vs. Nvidia's Massive Investment

Tesla's current AutoPilot system relies on the driver to be ready to take over at any timeMusk touted the fact that Tesla's ain chip has been optimized for Tesla's driving software, which certainly gives it a leg upwardly. Design lead Pete Bannon — best known for overseeing Apple's A5 CPU — stressed that by doing a bottom-up design from scratch they accept created something more efficient and more powerful than anything they could find in the market place.

However, Nvidia says Xavier is the culmination of four years of piece of work by ii,000 engineers and an investment of $2 billion — a complexity attested to by its nine billion transistors. My speculation is that power usage and economics are bigger drivers of Tesla's decision than pure functioning. It is certainly reasonable that by building a chip and calculator that only does exactly what information technology needs, Tesla can lower the power required — not a huge amount past server farm standards, but always a consideration in electric vehicles.

Tesla Stands to Save Billions by Developing Its Ain Car Computer

Economically, Tesla has ii price issues. First is the cost of computers for all its vehicles going forward, just it is also likely to need to retrofit — perhaps free of charge — existing cars with new computers. Musk has previously promised that recent cars equipped with AutoPilot would eventually be able to achieve full autonomous driving capability. That will almost certainly require a new computer, and customers who view it is a promise fabricated by Tesla volition be reluctant to pay for it. So by building his own computer, Musk can realize substantial cost savings.

Nvidia doesn't say what a PX2 costs, just it is speculated that early partners using it for autonomous vehicle testing paid upward to $15K per unit. Even if the volume version is much less expensive, say effectually $2K, retrofitting a couple hundred one thousand cars with it would come with a cost tag approaching a billion dollars. That number will continue to go upwards until Tesla can transport its new computer, which Tesla doesn't expect to happen until adjacent year.

At present Read: Nvidia Stuffs Volta Into Tiny Jetson Xavier, Nvidia's Bulldoze PX2 Detailed, and Tesla Hits 200,000 Sales, Countdown Starts for Lower Taxation Credits