NVIDIA GeForce RTX 40 Series Takes a Break in Performance

NVIDIA released a version GeForce RTX® 40 Series GPUsLed by the new flagship, the RTX 4090 GPU, designed to deliver revolutionary performance for gamers and creators, with up to 4 times the performance of its predecessor.

Delivering the world’s first GPU based on the new NVIDIA® Ada Lovelace architecture, the RTX 40 series delivers huge leaps in performance and efficiency, and represents a new era of real-time ray tracing and neural rendering, which uses artificial intelligence to create pixels.

“The era of RTX ray tracing and neural rendering is in full force, taking the new Ada Lovelace architecture to the next level,” said Jensen Huang, NVIDIA founder and CEO, at GeForce® Beyond: Special Broadcast at GTC.

“Ada provides a paradigm shift for gamers and paves the way for creators of fully simulated worlds. With up to 4 times the performance of the previous generation, Ada sets a new standard for the industry.”

DLSS creates 3 full frames for faster gameplay

Huang also announced NVIDIA DLSS 3 – the next revolution in the company’s neural graphics technology Deep Learning Super Sampling for games and creative applications. The AI-powered technology can create entire frames to play games faster. It can overcome CPU performance limitations in games by allowing the GPU to independently generate whole frames.

The technology comes to the world’s most famous game engines, such as Unity and Unreal Engine, and has received support from many of the world’s leading game developers, with more than 35 games and apps coming soon.

In addition, the RTX 40 series GPUs feature a range of new technological innovations, including:

1. Stream multiprocessor with up to 83 teraflops of shading power – 2x compared to the previous generation.

2. 3rd generation RT cores with up to 191 teraflops effective ray tracing – 2.8x compared to the previous generation.

3. Fourth generation Tensor cores up to 1.32 petaflops strung – 5 times the previous generation using FP8 acceleration.

4. Shader Execution Reordering (SER) Improves execution efficiency by rescheduling shader workloads on the go to make better use of GPU resources. As significant an innovation as an out-of-order execution for CPUs, SER improves ray tracing performance up to 3x and in-game frame rates by up to 25%.

5. Ada optical flow accelerator with two times faster performance allows DLSS 3 to predict movement in a scene, allowing the neural network to boost frame rates while maintaining image quality.

6. Architectural improvements tightly coupled with custom TSMC 4N processing technology result in a 2x jump in energy efficiency.

7. Dual NVIDIA (NVENC) encoders cut export times in half and feature AV1 support. NVENC AV1 encryption is certified by OBS, Blackmagic Design DaVinci Resolve, Discord, and more.

Redefining creativity with RTX Remix, new AV1 encoding

RTX 40 Series GPUs and DLSS 3 provide advancements for NVIDIA Studio creators. 3D artists can render full ray tracing environments with precise physics and realistic textures, and view changes in real time, without agents.

Video editing and live streaming also get a boost from improved GPU performance and the inclusion of a new 8th generation AV1 encoder. The NVIDIA Broadcast SDK contains three updates, now available to partners, including facial expression estimation, eye contact, and quality improvements for the virtual background.

NVIDIA Omniverse™ – included in the NVIDIA Studio suite of software – will soon be adding NVIDIA RTX Remix, a mod platform for creating stunning RTX versions of classic games. RTX Remix allows depositors to easily capture game assets, automatically optimize materials with powerful AI tools, and quickly enable RTX with ray tracing and DLSS.

The RTX 4090 is the world’s fastest gaming GPU with amazing power, sound and temperature. In full ray tracing games, the RTX 4090 with DLSS 3 is up to 4 times faster than the last generation RTX 3090 Ti with DLSS 2. It’s also up to 2x faster in today’s games while maintaining the same 450W power consumption. It features 76 billion transistors, 16,384 CUDA® cores and 24 GB of high-speed Micron GDDR6X memory, and consistently delivers over 100 frames per second in 4K gaming. The RTX 4090 will be available Wednesday, October 12, starting at $1,599.

The company also announced the RTX 4080, which was launched in two configurations. The RTX 4080 16GB has 9,728 CUDA cores and 16GB of high-speed Micron GDDR6X memory, and with DLSS 3 is twice 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 RTX 4080 12GB has 7,680 CUDA cores and 12GB of Micron GDDR6X memory, and with DLSS 3 is faster than the RTX 3090 Ti, the previous generation mainframe GPU.

Both RTX 4080 configurations will be available in November, with prices starting at $1,199 and $899, respectively.