NVIDIA introduced the GeForce RTX 40 Series of GPUs, geared for gamers and content makers, with their new ADA Lovelace architecture and DLSS 3 technology.
The RTX 40 Series, the world’s first GPUs based on the new NVIDIA Ada Lovelace architecture, employs AI to generate pixels.
Jensen Huang, NVIDIA’s founder and CEO remarked at the GeForce Beyond: Special Broadcast at GTC, “The age of RTX ray tracing and neural rendering is in full swing, and our new Ada Lovelace architecture takes it to the next level.” Ada offers a quantum leap for gamers and paves the path for creating entirely virtual environments. With up to four times the performance of the previous generation, Ada sets a new industry benchmark,” he stated.
Huang also unveiled NVIDIA DLSS 3, the latest generation of the company’s Deep Learning Super Sampling neural graphics engine for gaming and creative applications. The system powered by artificial intelligence may produce complete frames for speedier gameplay. It can circumvent CPU performance limits in games by permitting the GPU to create complete frames independently. The technology is coming to various prominent gaming engines, including as Unity and Unreal Engine, and has gotten backing from many of the world’s greatest game developers; more than 35 games and apps are forthcoming.
Additionally, the RTX 40 Series GPUs feature a range of new technological innovations, including:
- 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 utilise 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 framerates by up to 25%.
- Ada Optical Flow Accelerator with 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 improvements tightly 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 new third-generation RT Cores have been upgraded to provide ray-triangle intersection testing that is twice as fast and incorporate two crucial new hardware modules. A Micro-Mesh Engine develops micro-meshes on the fly to generate more geometry, while an Opacity Micromap Engine speeds up ray tracing of alpha-test geometry by a factor of two. The Micro-Mesh Engine gives the advantages of higher geometric complexity without the performance and storage expenses typically associated with complicated geometries.
GPUs from the RTX 40 Series and DLSS 3 provide enhancements for NVIDIA Studio developers. Without proxies, 3D artists may create completely ray-traced worlds with accurate physics and natural materials in real-time. Enhanced GPU speed and the addition of new twin eighth-generation AV1 encoders provide a boost to both video editing and live broadcasting. The NVIDIA Broadcast software development kit has received three updates, including Face Expression Estimation, Eye Contact, and Virtual Background quality enhancements.
Using RTX Remix, NVIDIA Lightspeed Studios reimagined Valve’s legendary video game Portal, widely recognized as one of the best video games of all time. Full ray tracing and DLSS 3 give the game a visually appealing new appearance. In November, Portal with RTX will be released as free, official downloadable content for the classic platformer with RTX graphics, coinciding with the 15th anniversary of Portal.
The RTX 4090 with 24GB of Micron GDDR6X RAM and 100 frames per second at 4K resolution will be available for $1,599 beginning on Wednesday, October 12. Moreover, the RTX 4080 will be available in two configurations. One having 16GB of Micron GDDR6x and the other with 12GB. In November, both RTX 4080 models will be available for a starting price of USD 1,199 and USD 899, respectively.