Nvidia announces RTX 4090, but it’s the 4080 to watch out for • The Register

Nvidia CEO Jensen Huang unveiled his GPU giant’s flagship RTX 40-series graphics cards at GTC today.

Powered by Nv’s Ada Lovelace microarchitecture and a TSMC 4nm process, the RTX 4090 and 4080 are said to offer more than twice the performance of the previous 3090 TI and 3080 TI flagships.

Starting with the RTX 4090, the device bears more than a passing resemblance to the 3090 that TI Huang compared it to during his keynote presentation. The card features the same 24GB of GDDR6X memory, including a 384-bit interface, and 450W TDP as the 3090 TI.

In addition, the specifications of the new card indicate that it will deliver significantly higher performance, presumably thanks to improvements in the architecture and processing nodes. The 4090 has 16,384 CUDA cores, up from 10,752 in the 3090 TI, while Nvidia has bumped the base clock from 1.67GHz to 2.23GHz.

In addition to more CUDA cores and faster clocks, the card – and the 4080 for that matter – also features Nvidia’s third-gen real-time ray tracing cores and fourth-gen Tensor cores, as well as support for Nvidia’s DLSS 3 AI supersampling technique

When Nvidia claimed the units would deliver roughly twice the performance of their predecessors, it based this on a carefully curated selection of games, including Microsoft Flight Sim and Warhammer 40K Darktide.

The chip designer further claimed that when testing a pre-release version of Cyberpunk 2077, the performance was four times faster with its next-gen AI supersampling technology. That’s not to say these cards are just for gaming: As GPU devices, they can accelerate many other workloads.

But that swing won’t come cheap. Nvidia is asking an MSRP of $1,599 for the card, although it’s still cheaper than the 3090 TI when it shipped this spring with an MSRP of $1,999.

Of course, what with the dwindling world of GPU-based cryptocurrency mining thanks to the Ethereum is changing, and all that economic uncertainty causing people to buy less stuff, customers might have a better chance of finding one of these 4090 cards at that suggested price when it arrives in October. We’re not holding our breath with that.

Be careful not to buy the wrong 4080

Things get a little more interesting with Nvidia’s mini-boss or mini-bosses: the 12GB and 16GB 4080s.

Nvidia compared the RTX 4080 series cards favorably to the outgoing 3080 TI, touting twice the performance in games over the Ampere-based card.

And that’s despite the fact that the 3080 TI has a narrow CUDA core lead of 10,240 over the 9,728 CUDA cores of the 4080 16GB. The difference is even greater with the 4080 12 GB variant, which has 7,680 CUDA cores, around 2,000 fewer than its predecessor.

And that’s not the only way Nvidia has seemingly brought the 4080 to its knees. While the cards use the same GDDR6X memory as their predecessors, Nvidia has reduced the memory interface to 256-bit on the 16GB model and 192-bit on the 12GB version. Even the 10GB 3080 had a 320-bit interface.

Nvidia seems to have made up for this by making architectural changes and increasing the 4080’s clock speed, which is now at 2.51GHz on the high-end 16GB model and 2.61GHz on the 12GB model, while claiming to have done so with less power. Yay, TSMC?

The 12GB version claims a TDP of just 285W, while the 16GB version is said to draw 320W. That’s roughly 9 to 19 percent less power than the 3080’s 350 W TDP.

If Nv’s numbers are to be believed – and some preliminary specifications indicate that the 4080 12GB outperforms the 3080 and 3080 TI in terms of FP32 performance and memory bandwidth – then the 4080 series should outperform the 3080 TI despite the reduced CUDA core count and memory bus width.

Just note that there is a small gap between the 16GB and 12GB 4080 models. Both the 12GB and 16GB 4080 will launch in November at a suggested retail price of $899 and $1,199, respectively.

Nvidia awaits mid-tier 40-series cards while AMD prepares RNDA 3

As in previous years, Nvidia is sticking to its flagship cards. The GPU giant is expected to start rolling out 40-series updates to the 3070, 3060, and 3050 cards over the course of the next year. But for now, Nvidia’s mid-tier 30-series cards remain.

In the meantime, we’ll have to wait a few more weeks to see how Nvidia’s Ada Lovelace-based cards stack up against AMD’s RDNA 3 architecture. While little is known about AMD’s upcoming consumer cards, aside from a few seconds of gameplay demoed during last month’s desktop launch of the Zen Titan’s Ryzen 7000, we do know that they will be based on a 5nm TSMC -Manufacturing process will be based.

And if AMD follows a similar partner as it did when it launched RDNA 2 in 2020, we won’t be getting mid-tier cards from AMD out the door either. ®

https://www.theregister.com/2022/09/20/nvidia_rtx_40_series/ Nvidia announces RTX 4090, but it’s the 4080 to watch out for • The Register

Laura Coffey

World Time Todays is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – admin@worldtimetodays.com. The content will be deleted within 24 hours.

Related Articles

Back to top button