After months of anticipation and controversy among its expansion card partners, NVIDIA’s 40-series GPUs are finally here. The company today unveiled the GeForce RTX 4090 and GeForce RTX 4080 during its GTC 2022 keynote. Taking full advantage of its new “Ada Lovelace” architecture, NVIDIA claims that both GPUs deliver ray tracing performance significantly better. The company has worked with Taiwan Semiconductor Manufacturing Company (TSMC) to co-develop a new “4N” manufacturing process that NVIDIA claims is up to twice as energy efficient as the 8nm process used for its boards in the 30 series.
Ray-tracing performance is dramatically improved thanks to Ada Lovelace with NVIDIA’s new third-generation RT cores, and the inclusion of a new rendering technique called Shader Execution Reordering and DLSS 3.0. In some games, NVIDIA said you can expect two to three times better ray tracing performance than was possible with its Ampere GPUs. The company demonstrated Cyberpunk 2077 running at a nearly constant 100 frames per second with all of the game’s ray tracing features set to maximum. NVIDIA said that rasterization performance is up to twice as fast thanks to the new architecture.
The first of NVIDIA’s new Ada Lovelace GPUs will arrive next month when the GeForce RTX 4090 goes on sale for $1,599 on October 12. With 24GB of GDDR6X memory, NVIDIA claims its latest flagship is two to four times faster than the 3090 Ti while consuming the same amount of power. Good thing too because it starts at $100 more than its predecessor. Inside the RTX 4090, NVIDIA managed to fit 16,384 CUDA cores clocked at a base speed of 2.23 GHz.
Alongside the 4090, NVIDIA will offer two different variants of the RTX 4080. The base model, starting at $899, has 12GB of GDDR6X memory, while the 16GB version will set you back $1,199. Both configurations will arrive in November. However, NVIDIA will only sell a Founders Edition model of the more expensive model. For the 12GB version, you’ll have to look to the company’s partners, which can make it difficult to find models that actually start at $899.
In terms of performance, the 16 GB 3080 has 9,728 Cuda cores and a base clock of 2.21 GHz, with a maximum boost clock of 2.51 GHz. Meanwhile, the 12GB model has a more modest 7,680 CUDA cores, but 100MHz faster base and boosted clocks. Luckily, you probably won’t need to upgrade your power supply if you plan to upgrade from a 3070 or 3080, with NVIDIA recommending a 700 watt PSU for the 12GB variant and a 750 watt PSU for its more powerful brother. However, if you decide to buy a new PSU, you’ll have to wait for more ATX 3.0 PSUs to arrive later this year. Indeed, at least the Founders Edition models will support the new 16-pin PCIe Gen-5 connector standard. That said, NVIDIA will also include an 8-pin adapter for those who don’t want to rewire their system.
NVIDIA’s 40-series GPUs come at a difficult time for the company. For much of the pandemic, it has been impossible to buy the latest GeForce GPUs at MSRP due to demand from gamers and crypto miners. Everything has changed in the past few months due to the recent crypto crash and Ethereum’s much-anticipated shift to proof-of-stake minting. As a result of these events, the used market was flooded with 30-series GPUs, making it nearly impossible for the company’s AIB partners and retailers to sell new video cards at MSRP.
All products recommended by Engadget are selected by our editorial team, independent of our parent company. Some of our stories include affiliate links. If you purchase something through one of these links, we may earn an affiliate commission. All prices correct at time of publication.
#NVIDIAs #GeForce #RTX #arrives #October #Engadget