Nvidia is bringing ray tracing and DLSS 3 to your car

By Jacob Roach Published March 21, 2024

Cyberpunk 2077 running in a Tesla. — Tesla

I know it sounds crazy, but a new MediaTek chip powered by Nvidia graphics promises to bring AAA gaming, ray tracing, and the coveted DLSS 3 to your car. The chips I’m talking about are MediaTek’s new Dimensity Auto Cockpit, which integrated an Nvidia GPU, along with a host of AI and gaming capabilities.

It’s not clear what Nvidia graphics are packed on MediaTek’s chips, but clearly, they’re using some variation of the Ada Lovelace architecture we see on RTX 40-series GPUs. Those are the only GPUs that support DLSS 3’s frame generation capabilities, and they’re extremely efficient — important for a chip packed into a car.

Recommended Videos

The basis of MediaTek’s new chips is a 3nm node that’s designed around the Armv9-A CPU. This chip has “deep learning capabilities,” according to MediaTek, but it sounds like the Nvidia GPU is really packing the AI hardware.

DLSS 3 is already an AI feature, but MediaTek boasts that the Nvidia graphics include a Deep Learning Accelerator (DLA), allowing you to run things like a Large Language Model (LLM) directly from the car. The chip also supports Nvidia’s full software platform, including CUDA, Drive OS, and TensorRT. MediaTek is building the chip, but it’s clear Nvidia has a big influence on it.

I won’t drop an insane amount of cash on a car that can play Cyberpunk 2077 with all the shinies. However, there are some applications here for other products.

Nvidia is showing that it can build what is essentially an RTX 40-series GPU on a small system-on-a-chip (SoC), fit with support for ray tracing and DLSS 3. That holds a lot of promise for handheld gaming devices, where Nvidia has been somewhat of a sleeping giant for the past few years.

Rumor has it that the next version of the Nintendo Switch will support DLSS and ray tracing with an Nvidia GPU. On top of that, Nvidia is reportedly worried about “missing the boat” on handheld gaming PCs, such as the Steam Deck. Up to this point, we’ve only seen AMD chips in handheld gaming PCs.

These automotive chips aren’t going to show up in a gaming device, but at the very least, they show that Nvidia can pack a modern GPU into what is essentially a mobile SoC. I’m not too excited about ray tracing and DLSS in my car — but on a Steam Deck, I’ll take it.

Lead Reporter, PC Hardware

Jacob Roach is the lead reporter for PC hardware at Digital Trends. In addition to covering the latest PC components, from…

Topics

Computing

Intel just stole a page from Nvidia’s DLSS playbook

hp omen transcend 32 review 13

Intel is giving its XeSS upscaling tech a huge makeover. The aptly-named XeSS 2 steals -- or borrows, if we're being generous -- a page from Nvidia's DLSS 3, which has been a staple feature of some of the best graphics cards you can buy. XeSS 2 comes packed with super resolution like the original version, but also frame generation and a latency-reducing feature called XeLL. And it's launching alongside the new B580 graphics card.

Point-for-point, XeSS 2 is basically identical to DLSS 3. The super resolution portion functions much in the same way as the original XeSS, providing you with various different quality settings to render your game at a lower resolution in order to improve performance. On the upscaling side, the major change is native support for DirectX 12 and Vulkan, which should open up XeSS to more games.

Computing

Nvidia CEO in 1997: ‘We need to kill Intel’

NVIDIA CEO Jensen Huang at GTC

Those headline above includes strong words from the maker of the best graphics cards you can buy, and they have extra significance considering where Nvidia sits today in relation to Intel. But in 1997, things were a bit different. The quote comes from the upcoming book The Nvidia Way, written by columnist Tae Kim, and was shared as part of an excerpt ahead of the book's release next month.

The words from Nvidia CEO Jensen Huang came as part of an all-hands meeting at the company in 1997 following the launch of the RIVA 128. This was prior to the release of the GeForce 256, when Nvidia finally coined the term "GPU," and it was a precarious time for the new company. Shortly following the release of the RIVA 128, Intel launched its own i740, which came with an 8MB frame buffer. The RIVA 128 came with only a 4MB frame buffer.

Computing

Nvidia warns gamers of an incoming GPU shortage

The RTX 4090 sitting alongside the Fractal Terra case.

Get ready for yet another GPU shortage, as Nvidia has warned about potential shortages in the current quarter. Although the company’s third-quarter revenue saw a healthy growth, in its recent earnings call, company Chief Financial Officer Colette Kress said that the fourth-quarter revenue is expected to decline sequentially due to supply constraints.

The anticipated GPU shortage could potentially stem from a strategic shift in production to prepare for the next-generation RTX 50-series “Blackwell” GPUs, slated for release in 2025. This supply transition, coupled with surging gaming and professional use-case demand, seems to have left the company in a tight spot. Nvidia acknowledged its struggle to maintain stock for both gamers and enterprise customers, emphasizing its ongoing efforts to expand manufacturing capacity.