Today NVIDIA’s CEO Jensen Huang showed off their latest 40 series cards, boasting impressive upgrades compared to their previous versions.
Of the Two cards announced the GEForce RTX 4090 is the more expensive. being touted as two to four times faster than its predecessor the 3090 Ti, it has an impressive 24GB of onboard memory and MRSP will be 1,599 USD at its release on October 12th (The 3090 Ti’s MRSP was 1,999 USD on release). NVIDIA’s Spec Sheet shows the 4090 having a power draw of 450W with a minimum system power requirement of 850W. The 4090’s Full Specifications can be found on NVIDIA’s website here
They have also announced the GEFORCE RTX 4080, again cited as two to four times faster than its predecessor the 3080 Ti, the 16GB one’s MRSP is 1,199 USD slated to release in November (The 3080 Ti launched with a MRSP of 1,199 USD ) but they do mention a 12GB version on the Spec Sheet that seem to be starting from 899 USD. These devices have a power draw of 320W for the 16GB version and 285W for the 12GB version with a Required System power requirement of 750W and 700W respectively. The 4080’s Full Specifications can be found on NVIDIA’s website here
NVIDIA claim 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) 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.
Also announced in the Keynote a new Portal Mod using the latest technology to remaster the games graphics using Ray Tracing and DLSS 3 to bring it visually to the future, this mod will be released Free to Portal owners shortly.
RTX Remix was also shown off, a modding tool that allows modders to upscale and improve on the graphical options. Using Bethesda’s 2002 game Morrowind as a showcase they show an impressive upscaling and re-resolution of the graphics that can be exported as an RTX Modpack and played via a RTX render, although I can’t currently find anything that supports this.
Both the RTX Remix and Portal mod will be released shortly after Ada’s Launch, with the Portal Mod being aimed at landing in October.
For a look at what the new Ray Tracing and DLSS updates mean for your favourite games NVIDIA Produced the video below.
You can watch the Full Keynote here and NVIDIA’s Press release here
