Nvidia ADA Lovelace, the new RTX 4090 and 4080 arrive | Prices and availability

Nvidia has unveiled the new ADA Lovelace architecturewhich characterizes the new top range proposals in the GPU field of this 2022. The new RTX 4080 and 4090 have finally been unveiled and we also have the first information on prices, release times, but above all we know the definitive features.

Nvidia today unveiled its third generation Ada Lovelace RTX architecture by showing a demo of Racer X, a simulation of an off-road kart racing game. The Racer X demo was powered by a single Ada Lovelace GPU, which includes 76 billion transistors and is based on TSMC’s 4nm process.

NVIDIA cards based on Ada Lovelace represent a huge generational leap in performance and efficiency and mark the beginning of a new era of real-time ray tracing and neural rendering, which uses artificial intelligence to generate pixels.

“The era of RTX ray tracing and neural rendering is in full growth and revolutionizing the industry, our new Ada Lovelace architecture represents an evolution that takes everything to the next level. Ada offers a quantum leap in performance for players and paves the way for creators of fully simulated worlds. With up to four times the performance of the previous generation, Ada sets a new standard for the industry. “

This was stated by Jensen Huang, founder and CEO of NVIDIA, on the occasion of the GeForce Beyond: Special Broadcast at the GTC.

In addition, the RTX 40 Series GPUs feature a number of technological innovations, which we report below.

• Streaming multiprocessors: Up to 83 teraflops shader power, over 2 times the previous generation.
• RT Cores of the third generation: Up to 191 effective ray-traced teraflops, 2.8 times higher than the previous generation.
• Generation IV Tensor Core: up to 1.32 petaflop Tensor – 5x over the previous generation using FP8 acceleration
• Shader Execution Reordering (SER): improves execution efficiency by instantly reprogramming shading workloads to make better use of GPU resources. A significant innovation as was the out-of-order execution for the CPUs, SER improves ray tracing performance by up to three times and game frame rates by up to 25%.
• The Ada Optical Flow Accelerator: performance twice as fast, allows DLSS 3 to predict motion in a scene, allowing the neural network to increase the frame rate while keeping the image quality unchanged.
• Architectural improvements: combined with customized TSMC 4N process technology, they achieve a leap up to two times higher in energy efficiency.
• The dual NVIDIA encoders (NVENC): they cut export times by up to half and offer AV1 support. NVENC AV1 encoding has been adopted by OBS, Blackmagic Design DaVinci Resolve, Discord and many others.

Let’s start talking about RTX 4090 right away!

According to Nvidia, the RTX 4090 is the fastest gaming GPU in the world with truly amazing power, acoustics and temperature characteristics. In full ray-traced games, the RTX 4090 with DLSS 3 is capable of up to 4 times higher performance than the RTX 3090 Ti with DLSS 2. It is also up to 2 times faster in current games, while maintaining the same power consumption of 450W. It has 76 billion transistors, 16,384 CUDA cores, and 24GB of high-speed Micron GDDR6X memory, and consistently delivers over 100 frames per second in 4K resolution games.

The company also announced the RTX 4080, available in two configurations. The RTX 4080 16GB has 9,728 CUDA cores and 16GB of high-speed Micron GDDR6X memory, and it is twice as fast in games as the GeForce RTX 3080 Ti and more powerful than the GeForce RTX 3090 Ti. The RTX 4080 12GB has 7,680 CUDA cores and 12GB of Micron GDDR6X memory and is faster than the previous generation flagship GPU.