In the end, GeForce RTX 40-series revealedBut in true Nvidia fashion, CEO Jensen Huang didn’t delve deeply into the raw speed and feed when he started out. RTX 4090 And 4080 In your GTC keynote. There’s only so much time during these things, and the audience at large doesn’t like to be moved through verbal descriptions of technical footnotes. Fortunately, Nvidia’s website includes key technical details from the presentation—details that confirm a lot of deeply interesting information about these new “Ada Lovelace” GPU-powered graphics card,
Here are six essential GeForce RTX 40-series details you need to know was not Hear during Jensen’s revelations. For full details about Nvidia’s new graphics cards, check out our coverage GeForce RTX 4090 and 4080 Announcement,
One Name, Two Very Different RTX 4080s
In a deeply anti-consumer move, Nvidia is rolling out a pair of GeForce RTX 4080 offerings, which differ markedly in memory capacity. Nvidia eventually named them “16GB RTX 4080” and “12GB RTX 4080”. But while Huang failed to mention it, these two “4080s” would also deliver incredibly different baseline performance.
As you can see in the chart above, the 12GB GeForce RTX 4080 not only has less memory, but it also has a 192-bit bus and a much larger bus. 21 percent less CUDA Core. That means it will be significantly slower than the 16GB model, more often than not. Calling these two different GPUs with the same name would certainly create confusion among graphics card buyers.
The 12GB RTX 4080 won’t have a Founders Edition model
Speaking of, scrolling through the spec sheet for the RTX 4080 revealed this interesting additional quote. While the 16GB GeForce RTX 4080 includes specific length, width, and slot measurements for Nvidia’s Founders Edition version, the 12GB GeForce RTX 4080 simply says “varies by manufacturer.” It doesn’t look like the 12GB model will get Nvidia’s own custom Founders Edition treatment. Updates: Nvidia’s Brian Burke confirmed to PCWorld that there will be no Founders Edition version of the 12GB RTX 4080.
GeForce RTX 40-series supports AV1 encode
The AV1 encode is the holy grail for media makers, offering superior visuals with very little bandwidth needed. Intel beats AMD and Nvidia by joining them to the punch Killer AV1 Encoding in Your Arc Graphics CardBut a footnote to Nvidia’s RTX 4090 and 4080 spec sheets suggests that Team Green will support AV1 encode this generation as well (AV1 decode was already supported).
“The GeForce RTX 4090 and GeForce RTX 4080 graphics cards feature two of our new eighth-generation NVIDIA encoders (NVENC), now with support for AV1 encoding, enabling new possibilities for livestreamers, video editors and video callers,” RTX 40-Series Announcement Post crow
You read that right—not one, but Two NVENC encoders with AV1 encode support in RTX 40-series graphics cards. Streamers, take note.
DLSS 3 not coming to older GPUs
It is clear that previous generation GPUs will not include new-gen hardware encoders. But Nvidia’s much-hyped DLSS 3 software feature isn’t coming to RTX 20- and 30-series cards, even though both DLSS 2.0 and 2.1 were backported. Nvidia’s GPU Generation Comparison Page DLSS 3 is listed only on the RTX 40-series, while older-gen RTX offerings remain listed with DLSS 2.0.
This is because DLSS 3 software requires hardware that older GPUs do not have. Nvidia spokesman Brian Burke explained the situation to PCWorld via email:
“DLSS 3 includes 3 technologies – DLSS Frame Generation, DLSS Super Resolution (aka DLSS 2), and NVIDIA Reflex.
DLSS uses the RTX 40 series high-speed optical flow accelerator to calculate the motion flow used for the Frame Generation AI network, then executes the network on a fourth generation tensor core. Support for previous GPU architectures will require further innovation and optimization for the optical flow algorithm and AI models.
DLSS Super Resolution and NVIDIA Reflex will certainly continue to be supported on prior generation hardware, so current GeForce gamers and makers will benefit from games that integrate DLSS 3. We continue to research and train AI for DLSS Super Resolution and will provide model updates for all RTXs. As customers we have been doing this since the initial release of DLSS. For the vast majority of game integrations, both DLSS Super Resolution and Frame Generation will be exposed as separate UI settings and a gamer can choose to play one or the other or both. ,
you will need a bigger boat
The GeForce RTX 4090 doesn’t suck at 600 watts-plus like some of the early rumors—at least not in Nvidia’s Founders Edition iteration—but it does Come with a minimum 850W power supply with a 450W rating. It matches the previous generation flagship RTX 3090 Ti. As we said then: you will need a bigger boat, And by boat we mean power supply. It’s not all price news though. While the RTX supports 40-series 12VHPWR-PIN Connector Found in the new breed ATX 3.0 power supply, if you already have a PSU you will be able to use three or four standard 8-pin power connectors.
NVLink is dead for GeForce
Nvidia’s SLI technology for multi-GPU setups has been dead for some time now, but the “NVLink” technology that replaced it persisted in the previous generation of RTX 3090 GPUs. not anymore. The specific page for the GeForce RTX 4090 and 4080s explicitly states that NVLink is No Support this generation. put one out.
That’s all for these buried treasures. We’re sure to learn more about the GeForce RTX 40-series in the coming days and weeks, but once again, for the full scoop on Nvidia’s new graphics cards, check out our coverage GeForce RTX 4090 and 4080 Announcement,
Editor’s Note: This article was updated to include comments from Nvidia’s Brian Burke.