Taipei
Thu, Sep 22, 2022

Nvidia launches next-gen GeForce RTX built on TSMC N4 node
Monica Chen, Hsinchu; Jessie Shen, DIGITIMES Asia
Wednesday 21 September 2022

Nvidia has launched its next-generation GeForce RTX gaming GPUs built using TSMC's 4nm process technology.

Led by flagship RTX 4090, Nvidia's GeForce RTX 40 GPUs are designed to deliver "revolutionary performance for gamers and creators," according to the company.

In full ray-traced games, Nvidia's RTX 4090 with DLSS 3 is up to 4x faster compared to last generation's RTX 3090 Ti with DLSS 2, the company said. It is 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 24GB of high-speed Micron GDDR6X memory, and consistently delivers over 100 frames per second at 4K-resolution gaming.

Nvidia also announced the RTX 4080 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 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 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 flagship GPU.

The GeForce RTX 4090 and 4080 GPUs will be available as custom boards, including stock-clocked and factory-overclocked models, from top add-in card providers such as Asustek, Colorful, Gainward, Galaxy, Gigabyte, Inno3D, MSI, Palit, PNY and Zotac. The GeForce RTX 40 series GPUs will also be featured in gaming systems built by vendors including Acer, Alienware, Asustek, Dell, HP, Lenovo and MSI.

In addition, Nvidia announced that its H100 Tensor Core GPU is in full production, with global tech partners planning in October to roll out the first wave of products and services based on Nvidia's Hopper architecture.

Unveiled in April, H100 is built with 80 billion transistors and benefits from a range of technology breakthroughs. Among them are the new Transformer Engine and an Nvidia NVLink interconnect to accelerate the largest AI models, like advanced recommender systems and large language models. H100-powered systems from the world's leading computer makers are expected to ship in the coming weeks, with over 50 server models in the market by the end of 2022 and dozens more in the first half of 2023. Partners building systems include Atos, Cisco, Dell, Fujitsu, Gigabyte, Hewlett Packard Enterprise, Lenovo and Supermicro.

Nvidia also disclosed that Amazon Web Services (AWS), Google Cloud, Microsoft Azure and Oracle Cloud Infrastructure will be among the first to deploy H100-based instances in the cloud starting 2023.
© 2022 DIGITIMES Inc. All rights reserved.