At long last, the GeForce RTX 40 series revealedbut in true Nvidia fashion, CEO Jensen Huang didn’t delve into initial velocities and nutrition while presenting RTX 4090 And the 4080 During his keynote speech at GTC. There’s only so much time during these things, after all, and audiences don’t like sifting through verbal descriptions of technical footnotes. Fortunately, the Nvidia website includes major technical details that are lacking in presentation – details that confirm several very interesting tidbits about this new GPU-powered “Ada Lovelace” screen cards.
Here are six details you should know about the GeForce RTX 40-series he did not do We hear during the Jensen reveal. To get the full scoop on Nvidia’s new graphics cards, check out our coverage of GeForce RTX 4090 and 4080 إعلان ad.
One name, two very different types of RTX 4080s
In an anti-consumer move, Nvidia is introducing a pair of GeForce RTX 4080 offerings, which ostensibly differ in memory capacity. Nvidia simply gave them the names “16GB RTX 4080” and “12GB RTX 4080”, after all. But while Huang fails to mention it, these two “forties” would also offer incredibly different base performances.
As you can see in the above graph, the 12GB GeForce RTX 4080 card not only has less memory, but also has a much narrower 192-bit bus, and massive power 21 percent less CUDA cores. This means that it will be much slower than the 16GB model, often. Calling these two very dissimilar GPUs by the same name is sure to cause confusion among graphics card buyers.
The 12GB RTX 4080 will not have the Founders Edition model
Speaking of scrolling through the spec sheet for the RTX 4080, he revealed this interesting additional piece of news. While the 16GB GeForce RTX 4080 has specific length, width, and slot measurements for Nvidia’s Founders Edition, the 12GB GeForce RTX 4080 simply says “varies by manufacturer.” It doesn’t look like the 12GB model will get Nvidia’s custom Founders Edition treatment. Modernization: Nvidia’s Brian Burke confirmed to PCWorld that there will be no Founders Edition of the 12GB RTX 4080.
GeForce RTX 40 series supports AV1 codec
The AV1 codec is the holy grail for media creators, delivering much better visuals with much lower bandwidth needs. Intel beat AMD and Nvidia by including files killer AV1 in its graphics cardsHowever, footnotes to Nvidia’s RTX 4090 and 4080 spec sheets reveal that Team Green will support AV1 encoding for this generation as well (AV1 decoding was already supported).
The GeForce RTX 4090 and GeForce RTX 4080 graphics cards feature two new 8th Generation NVIDIA (NVENC) encoders, now with support for AV1 encoding, enabling a range of new capabilities for live stream creators, video editors and video callers, Share the announcement of the RTX 40 series Hoot.
You’re reading that right – not one, but two NVENC encoding with AV1 encoding support in RTX 40 series graphics cards. Signs, note.
DLSS 3 is not coming to older GPUs
It is clear that the latest generation of GPUs will not include new generation encoders. But Nvidia’s very popular DLSS 3 software feature isn’t coming to RTX 20 and 30 series cards either, although DLSS 2.0 and 2.1 have been ported to both. Nvidia GPU Generation Comparison Page DLSS 3 only lists the RTX 40 series while older generation RTX offerings remain listed with DLSS 2.0.
That’s because DLSS 3 requires hardware that older GPUs don’t have. Nvidia spokesperson Brian Burke explained the situation to PCWorld via email:
“DLSS 3 consists of 3 technologies – DLSS Frame Generation, DLSS Super Resolution (also known as DLSS 2) and NVIDIA Reflex.
DLSS Frame Generation uses a high-speed RTX 40-series optical flow accelerator to compute the traffic flow used for an AI network, and then executes the network on 4th generation Tensor cores. Supporting previous GPU architectures will require further innovation and optimization of the optical flow algorithm and AI model.
DLSS Super Resolution and NVIDIA Reflex will of course still be supported on previous generation hardware, so game creators and existing GeForce game creators will take advantage of games that integrate DLSS 3. We continue to research and AI training for DLSS Super Resolution and will provide sample updates to all RTX customers as we’ve been doing since the initial release of DLSS. For the vast majority of game integrations, DLSS Super Resolution and Frame Generations will each display as separate UI settings and the player can choose to play one, the other, or both.”
You will need a bigger boat
The GeForce RTX 4090 doesn’t suck in as much 600W as some early rumors suggested — at least not in Nvidia’s Founders Edition iteration — but it does. Do It comes with a 450 watt rating, with a minimum power supply of 850 watts recommended. This matches the flagship RTX 3090 Ti from the last generation. As we said at the time: You will need a bigger boat. And by boat, we mean the power source. However, not all news is expensive. While the RTX series supports 40 files 12VHPWR Pin Connectors Found in a new breed of ATX 3.0 power supply, you’ll also be able to use three or four standard 8-pin power connectors if you already have a powerful PSU.
NVLink is dead for GeForce
Nvidia’s SLI technology for multi-GPU setups has been discontinued for a while, but the “NVLink” technology that replaced it has remained in the last-generation RTX 3090 GPUs. no more. The spec pages for the GeForce RTX 4090 and 4080 explicitly state that NVLink is Not Support this generation. single casting.
That’s all about these buried treasures. We’re sure to learn more about the GeForce RTX 40 series in the coming days and weeks, but once again, to get the full scoop on Nvidia’s new graphics cards, check out our coverage of GeForce RTX 4090 and 4080 إعلان ad.
Editor’s Note: This article has been updated to include comments from Nvidia’s Brian Burke.