Today, NVIDIA unveiled the GeForce RTX 40 series of graphics cards, with the company's new flagship, the RTX 4090 GPU, leading the way.
The RTX 40 Series graphics cards are the first GPUs based on the new NVIDIA Ada Lovelace architecture, and represent "significant" generational improvements in performance and efficiency. The RTX 40 cards also includes real-time ray tracing and neural rendering.
The RTX 40 Series GPUs include a wide variety of new technological advancements, 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) that 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 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.
NVIDIA explains how the company's new ray-tracing technology for the new third-generation RT Cores has been enhanced to "faster ray-triangle intersection testing" and that it has two important new hardware units. An Opacity Micromap Engine speeds up ray tracing of alpha-test geometry by a factor of 2x, and a Micro-Mesh Engine generates micro-meshes on the fly to generate additional geometry.
NVIDIA's DLSS 3 is the next generation of the chipmaker's Deep Learning Super Sampling neural-graphics technology for games and other creative applications. This AI-powered technology can generate whole frames for massively faster gameplay, and can even overcome CPU performance limitations in games by allowing the GPU to generate entire frames independently.
GeForce RTX 4090: What's New
The G6X has 24GB of storage.
3090 Ti is 2-4 times faster than 3090 Ti.
Release Date: October 12
Information on press releases:
GeForce RTX 4080: A New Look
3080 Ti is 2-4x faster than 3080 Ti.
16GB G6X, 12GB G6X
Price: Starting at $1,199 and $899, this service is available now.
Release Date: November 2022
The RTX 4000 series comes with a lot more technical info right here.