Tesla Reveals Specs of its New AI-Powered Full Self-Driving Computer
【Summary】At the Hot Chips conference in San Francisco on Tuesday, Tesla engineers revealed of the details of the chip that will power Tesla’s future Autopilot, Full Self-Driving (FSD) system. Tesla's VP of hardware engineering Pete Bannon said that the new AI-powered chip is 21 times faster that the Nvidia chip it’s replacing and only 80% of the cost.
In April, at a special event at Tesla's Palo Alto, California headquarters called Tesla Autonomy Investor Day, Tesla CEO Elon Musk announced that Tesla vehicles are using a new custom-designed processor to power its Autopilot full self-driving (FSD) system.
At the time Musk said that no chip was available that had the processing power and power constraints that Tesla required, so the automaker built its own from scratch. Now the technical details of the new chip have been revealed for the first time.
At the Hot Chips conference in San Francisco on Tuesday, Tesla's VP of hardware engineering Pete Bannon revealed of the details of the chipset that will power Tesla's future Autopilot, full self-driving (FSD) system. Bannon said that the new AI-powered chip is 21 times faster that the Nvidia chip it's replacing and only 80% of the cost.
Tesla said it needed more robust hardware to achieve its 2019 goal of "full self-driving" which includes not only driving on highways, but extends to driving on local roads with traffic lights and road signs to obey.
The new AI processor has 6 billion transistors.
"It was clear to us, in order to meet our performance levels at the power constraints and the form factor constraints we had, we had to design something of our own," said Ganesh Venkataramanan, Senior Director Autopilot Hardware at Tesla, who also spoke at Tuesday's event. Venkataramanan previously worked for AMD and is one of the chip's designers.
The new chips is already being installed in Tesla models. All Tesla model produced after March 2019 have been shipping the new FSD chip, including the Model 3.
Tesla Had Specific Performance Targets for the New Chip
Tesla has specific performance targets for its new chip. First, it had to consume less than 100 watts of power, it needed to be retrofitted into existing Tesla models, have built-in security, and it had to have full redundancy, so if any part of the chip failed the chip would still be able to power the Autopilot FSD system. In addition, it also needed a redundant power supply and overlapping camera field with redundant paths.
Each Tesla computer has two independant AI chips which allow for redundancy for an extra layer of safety. This redundancy even extends to the power supply further guarding against a power interruption. For the vehicle's forward facing cameras each on has its own power supply to guard against failures.
Tesla designed the new chip to offer more than 50 TeraOPS (tera operations per second) of performance for its AI-powered deep neural nets used for autonomous driving.
"There are a lot of redundancy features, which makes sure nothing untoward happens to the system" said Venkataramanan.
Each of the AI chips can perform 36 trillion operations per second, giving the entire processor 72 TFLOPS of processing capability at 2GHz. The chip also has its own dual neural network accelerators (NNA). Each one is 96x96 MACs and can perform 36.8 TOPs per NNA.
The hardware is designed for redundancy, so that each chip makes its own assessment of what the car should do next. The computer compares the two independent assessments and the car only takes the action and if the chips agree. If the chips disagree, the car just discards the frame of video data and tries again, Venkataramanan explained.
Venkataramanan said that even if the two chips do not agree, the framerate is so high that if one frame is discarded, the overall system performance is not affected.
Tesla vehicles do not rely on lidar, so the cameras are a necessary component for self-driving. That's one of the reasons Tesla wanted powerful AI chips that could handle such a high frame rate for video.
Tesla said the chip took 14 months to design, and the processor being manufactured by Samsung.
resource from: anandtech.com
Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.
Tesla Rival XPeng Inc. to Start Deliveries of its New Flagship G9 Electric SUV in September, CEO Confirms After Sharing New Details
Valeo Signs Major Deal with BMW to Supply Advanced Driver Assist Hardware for the Automaker's Forthcoming 'Neue Klasse' EV Platform
EV Charging Provider Electrify America Raises $450 Million, Siemens to Become a Minority Shareholder
Electric Truck Maker Rivian Opens the First Fast Chargers in Colorado for its Nationwide ‘Adventure Network’
Volkswagen Unveils the 385-Mile Range ID Aero Concept, a Preview of its First Electric Sedan that Will Be Sold in the U.S., Europe and China
Qualcomm and its Industry Partners Demonstrate C-V2X Technology in Georgia That Ensures School Buses and Fire Trucks Never Get Stuck at Red Lights
Tesla's Battery Supplier CATL Unveils its New ‘Qilin’ Battery That Can Deliver 600+ Miles of Range to EVs
Shares of Volvo’s EV Brand Polestar to Begin Trading on the NASDAQ After Closing on its SPAC Deal With Gores Guggenheim
- EV Startup Fisker Inc to Produce its Second Vehicle in Ohio at Foxconn’s Newly Acquired Factory
- Tesla's Battery Supplier CATL Unveils its New ‘Qilin’ Battery That Can Deliver 600+ Miles of Range to EVs
- Polestar is Offering New Android R Infotainment Software as an OTA Update With Enhanced Features for the Polestar 2 EV
- Ford Motor Co Selects its Plant in Spain to Build 'Breakthrough' EVs for the European Market on a Next-Gen Architecture
- Tesla’s Battery Supplier CATL Launches its ‘EVOGO’ EV Battery Swapping Service in China
- Autonomous Truck Developer Embark Trucks Adds Freight Carrier U.S. Xpress to its Partner Development Program
- Nissan’s First EV With Solid-State Batteries Coming in 2028
- Tesla is ‘Virtually Recalling’ Roughly 64,500 Model 3 Performance Sedans in the U.S. and China for a Missing Speedometer Display While in Track Mode
- StoreDot Successfully Demonstrates its Rapid EV Battery Charging Technology That Could Deliver 100 Miles of Range in 5 Minutes
- The NIO ET7 Will Come Standard With an Advanced Dolby Atmos-Powered Sound System Co-Developed With Audio Pioneer Dirac