According to the company, the RTX 40 Series delivers massive generational leaps in performance and efficiency and represents a new era of real-time ray tracing and neural rendering, which uses AI to generate pixels. “The age of RTX ray tracing and neural rendering is in full steam, and our new Ada Lovelace architecture takes it to the next level,” said Jensen Huang, NVIDIA’s founder, and CEO, at the GeForce Beyond: Special Broadcast at GTC 2022. “Ada provides a quantum leap for gamers and paves the way for creators of fully simulated worlds. With up to 4x the performance of the previous generation, Ada is setting a new standard for the industry.” NVIDIA ADA LOVELACE ARCHITECTURE Based on Nvidia’s new TSMC 4nm Ada Lovelace architecture, the new GPU comes with several improvements, which the company terms a “Quantum Leap” in performance. This includes 3rd generation RT cores, 4th generation Tensor Cores, support for new features such as DLSS 3 and AV1 encoder, Ada Optical Flow Accelerator, and Shader Execution Reordering (SER). DLSS 3 TECHNOLOGY One of the more powerful features that was exclusively announced for 40-series graphics cards is NVIDIA DLSS 3, which accelerates performance by up to 4X. The new AI-powered technology can generate entire frames for massively faster gameplay. It can also overcome CPU performance limitations in games by allowing the GPU to generate entire frames independently. The technology is coming to the world’s most popular game engines, such as Unity and Unreal Engine, with over 35 games announced with support for this feature, including NVIDIA Racer RTX, Cyberpunk 2077’s new Ray Tracing: Overdrive Mode, and Portal with RTX. These will start appearing next month. However, Portal with RTX will launch in November and will be free for Portal owners. It’s a ray-traced reimagining of Valve’s classic game, built using a revolutionary modding tool called NVIDIA RTX Remix, which allows gamers to remaster classic games with ray tracing, NVIDIA DLSS 3, and NVIDIA Reflex. ADDITIONAL KEY FEATURES OF THE NEW NVIDIA RTX 40 SERIES CARDS:
Streaming multiprocessors with up to 83 teraflops of shader power — 2x over the previous generation. Third-generation RT Cores with up to 191 effective ray-tracing teraflops — 2.8x over the previous generation. Fourth-generation Tensor Cores with up to 1.32 Tensor petaflops — 5x over the previous generation using FP8 acceleration. Shader Execution Reordering(SER) improves execution efficiency by rescheduling shading workloads on the fly to better utilize the GPU’s resources. As significant an innovation as out-of-order execution was for CPUs, SER improves ray-tracing performance up to 3x and in-game frame rates by up to 25%. Ada Optical Flow Acceleratorwith 2x faster performance allows DLSS 3 to predict movement in a scene, enabling the neural network to boost frame rates while maintaining image quality. Architectural improvement slightly coupled with custom TSMC 4N process technology results in an up to 2x leap in power efficiency. Dual NVIDIA Encoders (NVENC) cut export times by up to half and feature AV1 support. The NVENC AV1 encode is being adopted by OBS, Blackmagic Design DaVinci Resolve, Discord, and more. The ShadowPlay capture resolution has been bumped to up to 8K resolution at 60fps in HDR.
Here’s everything you need to know about NVIDIA’s GeForce RTX 40 Series graphics cards: GeForce RTX 4090 The GeForce RTX 4090 GPU is the high-end card for the Ada Lovelace generation. It features massive 16,384 CUDA cores, a base clock of 2.23GHz that boosts up to 2.52GHz, 1,321 Tensor-TFLOPs, 191 RT-TFLOPs, and 83 Shader-TFLOPs. The card comes with 24GB of high-speed Micron GDDR6X memory and a 384-bit memory interface. NVIDIA claims that the RTX 4090 with DLSS 3 is up to 4x faster compared to the last generation’s RTX 3090 Ti with DLSS 2 in full ray-traced games. Also, it consistently delivers over 100 frames per second (FPS) when running video games at 4K resolution. Further, the card features 76 billion transistors and has a power rating of 450W, which is the same as the RTX 3090 Ti. It runs on a single 16-pin PCIe Gen 5 or 3x 8-pin PCIe cables. The RTX 4090 will be available on Wednesday, October 12 starting at $1,599 in the U.S. It will cost €1,949 in Europe and £1,679 in the UK. GeForce RTX 4080 (16GB and 12GB) The GeForce RTX 4080 comes in two configurations. The more premium variant, which is the RTX 4080 features 9,728 CUDA cores, a base clock of 2.21GHz that boosts up to 2.51GHz, 780 Tensor-TFLOPs, 113 RT-TFLOPs, and 49 Shader-TFLOPs of power. It comes with 16GB high-speed Micron GDDR6X memory and a 256-bit interface. NVIDIA claims that the RTX 4080 16GB with DLSS 3 is 2x as fast in today’s games as the GeForce RTX 3080 Ti and more powerful than the GeForce RTX 3090 Ti at lower power. The next variant comes with 12GB of Micron GDDR6X memory and a 192-bit memory interface. The RTX 4080 12GB has 7,680 CUDA cores, a 2.31GHz base clock that boosts up to 2.61GHz, 639 Tensor-TFLOPs, 92 RT-TFLOPs, and 40 Shader-TFLOPs. With DLSS 3, this card is faster than the RTX 3090 Ti, the previous-generation flagship GPU. While the 16GB variant has a power rating of 320W and requires a 750-watt PSU, the 12GB comes with a TDP of 285W and needs a 700-watt PSU. Both the RTX 4080 configurations will be available in November, with prices starting at $1,199 and $899, for the RTX 4080 16GB and RTX 4080 12GB models respectively. NVIDIA will be selling its own Founders Edition cards for the RTX 4090 and the RTX 4080 (16GB) with its own in-house design, alongside models from AIB partners, such as ASUS, Colorful, Gainward, Galaxy, GIGABYTE, Innovision 3D, MSI, Palit, PNY and Zotac.
