Skip to main content

Nvidia is powering a mega Tesla supercomputer powered by 10,000 H100 GPUs

Tesla has revealed its investment into a massive compute cluster comprising 10,000 Nvidia H100 GPUs specifically designed to power AI workloads.

The system, which went online this week, is designed to process the mountains of data its fleet of vehicles collect with a view to accelerating the development of fully self-driving vehicles, according to its leader of AI infrastructure, Tim Zaman.

Tesla has been striving for years to reach the point at which its vehicles can be considered entirely autonomous and has invested more than a billion dollars into adopting the infrastructure to make this possible.

Tesla supercomputer

In July 2023, CEO Elon Musk revealed the firm would invest $1 billion into building out its Dojo supercomputer over the next year. Dojo, which is based on Tesla’s own tech, began with the D1 chip, fitted with 354 custom CPU cores. Each training tile module comprises 25 D1 chips, with the base Dojo V1 configuration including 53,100 D1 cores in total.

The firm also built a compute cluster fitted with 5,760 Nvidia A100 GPUs in June 2012. But the firm’s latest investment in 10,000 of the company’s H100 GPUs dwarfs the power of this supercomputer. 

This AI cluster, worth more than $300 million, will offer a peak performance of 340 FP64 PFLOPS for technical computing and 39.58 INT8 ExaFLOPS for AI applications, according to Tom’s Hardware. 

The power at Tesla’s disposal is actually more than that offered by the Lenoardo supercomputer, the publication pointed out, making it one of the most powerful computers on the planet.

Nvidia’s chips are the components that power many of the world’s leading generative AI platforms. These GPUs, which are fitted into servers, have several other use cases from medical imaging to generating weather models.

Tesla is hoping to use the power of these GPUs to more efficiently and effectively churn through the vast quantities of data it has to build a model that can successfully rival a human.

While many businesses would usually lean on infrastructure hosted by the likes of Google or Microsoft, Tesla’s supercomputing infrastructure is all on-prem, meanig the firm will also have to maintain all of it.

More from TechRadar Pro



Comments

Post a Comment

Popular posts from this blog

The latest Apple TV 4K test lets you watch four sports streams at once

Apple is trying something new with the latest beta version of tvOS 16.5: the option to watch up to four simultaneous streams at once. Right now it's limited to live sports streamed through the Apple TV app on the Apple TV 4K , specifically MLB Friday Night Baseball and the MLS Season Pass. A multi-view option was spotted in the tvOS software last month, but the code was hidden and not enabled. MacRumors reported that the feature would be enabled this weekend, and beta testers have since been able to use it. As yet multi-view hasn't been officially announced by Apple, but it's expected that tvOS 16.5 is going to be pushed out in its final form within the next month or so. WWDC 2023 is around the corner as well, when we should be hearing about the next major updates for Apple's various operating systems – including tvOS 17. How it works Over at 9to5Mac there's a hands-on demonstrating how the multi-view feature works, and it's pretty much as you would expe...
Post a Comment
Read more

Quantum computers are fast becoming cheaper and smaller — and they could be coming to a data center near you very soon

IonQ claims we’re closer to widespread enterprise quantum computing deployment as it lifted the lid on two rack-mounted models that can be deployed on-premises.   The startup has built the fourth-generation #AQ35 IonQ Forte Enterprise and fifth-generation #AQ64 IonQ Tempo, both of which are designed to be deployed in enterprise and government data centers. It’s also said it is deploying two quantum computers to the US Air Force.  While revealing these two models, IonQ co-founder and CTO Jungsang Kim said quantum computers are already in use by enterprises to churn through machine learning workloads. This, he added, suggests we’re much closer to readily available and affordable machines. Priming enterprises for a quantum future “We believe in the enterprise-grade quantum computing, which is where it can be something of value for enterprises, can happen in the next few years as we build powerful enough quantum computers that can actually do things that classical computers w...
Post a Comment
Read more

Nvidia RTX 4080 GPU could get cheaper with a new version – but don’t get your hopes up

Nvidia’s RTX 4080 is purportedly getting a new spin on the GPU which could reduce the cost, but any price reduction will likely be very minor, sadly, if it happens at all. Tom’s Hardware flagged up this rumor – and treat it with caution, as with anything from the ever-spinning mill – that originated from HKEPC (a tech site in Hong Kong), claiming that while the current RTX 4080 graphics card is built on the AD103-300 chip, Nvidia is going to use a slightly different GPU in the future, namely AD103-301. There’s now more evidence this is actually happening, Tom’s points out, courtesy of a graphics card maker, Galax, which under its RTX 4080 product details lists the GPU as ‘AD103-300/301’. Furthermore, VideoCardz , which also picked up on this, informs us that Gainward, another card maker, has also listed the updated GPU variant AD103-301 in its product specs. With two separate third-party graphics card makers mentioning this new spin on the GPU in their specs, it seems pret...
Post a Comment
Read more