It's time for a new graphics upgrade—two years after the last major generational leap, graphics company Nvidia unveiled the GeForce RTX 40 series today. GeForce RTX 40 Series GPUs is the market leader's vision for the next generation of PC graphics technology.
In a lengthy keynote video that covered everything from gaming graphics to Nvidia's use of artificial intelligence to improve self-driving cars, Nvidia CEO Jensen Huang detailed the company's vision for the future, enabled by the new Ada Lovelace architecture, named after the famous mathematician. who is often called the first programmer in history.
The new Lovelace architecture provides a significant power boost, which means a big boost for the new 40-series GPUs, which will initially be three.
The RTX 4090 is the new flagship, and according to Huang, it offers four times the performance of its direct predecessor while packing 24GB of memory. It will be released on October 12 and, according to Huang, will be the most powerful consumer GPU on the market at that time. However, all this power doesn't come cheap—you'll have to shell out $1599 for it.
A month later, two variations of the RTX 4080 will join it. The main difference between these two versions is the amount of memory: versions with 16 and 12 GB of memory will be released at the same time. Supposedly they are equivalent in power to the RTX 3080 Ti, while gaining access to some new 40-series-exclusive features. The 16GB model will cost $1199, while the 12GB version will set players back $899.
Overall, the 40-series GPUs feature a number of improvements over the previous generation, including a new generation of RT cores and tensor cores, double the bandwidth of streaming multiprocessors, and more.
Our friends at DigitalFoundry have already had a chance to check out the 4090—we've included their teaser video at the top of this article. We'll also be doing official testing on the VG247 over time - so look forward to that.
For gamers, the biggest news, aside from the new hardware, is the arrival of DLSS 3.0, an improved version of an impressive technology that allows gamers to achieve higher frame rates in games without a noticeable loss in visual fidelity. DLSS, aka Deep Learning Super Sampling, has been around for a while, but this new version is exclusive to the 40 series, which is likely to disappoint those with 20 series cards older or newer by a couple of years.
Like previous versions, DLSS 3 will require developers to update their games to support it - but already more than 35 games and applications have supported it since launch. During the stream, Nvidia talked about the improvements and performance boosts this feature brings to several games, giving an example of what gamers can expect.
One example shows Cyberpunk running with maximum ray tracing. With DLSS turned off, it runs at 22 fps - turn on DLSS 2 and get 62 fps. At the same time, DLSS 3 reaches 100 frames per second. In Microsoft Flight Simulator, DLSS 3 increases the frame rate from approximately 60 fps with DLSS disabled to over 120 fps with DLSS enabled.
Overall, this looks very impressive - although the cost of such equipment is high, both in terms of initial costs and how much it costs to operate due to rising energy prices. Still, it's exciting to see the next generation of graphics hardware and we can't wait to test it out. Stay here - we'll be back with reports as soon as we can get started.
