Photo: Andrej Karpathy
Behind all the impressive superpowers of Tesla Full Self-Driving (FSD) are huge computers that process billions of miles of data using machine learning through neural networks. Although Tesla computers are already the leading computers in the world, the company’s new supercomputer—dubbed “Dojo”—will be the best driver training computer ever created and possibly the fastest ever built. Nevertheless, on the way to its creation, Tesla created another one, less powerful than Dojo, but already the fifth most powerful computer in the world.
The director of artificial intelligence and Autopilot Vision at Tesla, Andrej Karpathy, took part in the 2021 Conference on Computer Vision and Pattern Recognition. During his speech, he presented the latest supercomputer, which became Dojo’s predecessor. He showed a photo of one of its three clusters.
Karpathy also spoke about the characteristics of the new supercomputer, pointing out that Dojo will be next:
- 720 nodes of 8x A100 80GB. (5760 GPUs total)
- 1.8 EFLOPS (720 nodes * 312 TFLOPS-FP16-A100 * 8 gpu / nodes)
- 10 PB of “hot tier” NVME storage @ 1.6 TBps
- 640 Tbps of total switching capacity
“We have a neural net architecture network and we have a data set, a 1.5 petabytes data set that requires a huge amount of computing. So I wanted to give a plug to this insane supercomputer that we are building and using now. For us, computer vision is the bread and butter of what we do and what enables Autopilot. And for that to work really well, we need to master the data from the fleet, and train massive neural nets and experiment a lot. So we invested a lot into the computer. In this case, we have a cluster that we built with 720 nodes of 8x A100 of the 80GB version. So this is a massive supercomputer. I actually think that in terms of flops, it's roughly the number 5 supercomputer in the world,” said the director of artificial intelligence and Autopilot Vision at Tesla.
The goal of Tesla's supercomputer is to increase the speed and accuracy of learning by at least 10 times compared to the current computer. The new supercomputer is developed by the company to increase the learning rate of neural networks on the server-side, which will further bring Tesla closer to achieving full self-driving autonomy.
© 2021, Eva Fox. All rights reserved.
We appreciate your readership! Please share your thoughts in the comment section below.
About the Author
Eva Fox joined Tesmanian in 2019 to cover breaking news as an automotive journalist. The main topics that she covers are clean energy and electric vehicles. As a journalist, Eva is specialized in Tesla and topics related to the work and development of the company.