After much anticipation and rumors, NVIDIA has officially introduced the GeForce RTX 40 series GPU, based on the new Ada Lovelace architecture, NVIDIA claims that the flagship RTX 4090 will have up to 4x better performance than its predecessor along with the introduction of DLSS 3.
Touted as the world’s fastest gaming GPU with astonishing power, acoustics and temperature characteristics, the RTX 4090 is up to 2x faster in today’s games while maintaining the same 450W power consumption, while the new architecture allows it to feature 76 billion transistors, 16,384 CUDA cores and 24GB of high-speed Micron GDDR6X memory.
On the other hand, NVIDIA has also announced the RTX 4080 in 16GB and 12GB memory GDDR6X memory variants, the RTX 4080 16GB has 9,728 CUDA cores and is 2x as fast in today’s games as the RTX 3080 Ti and more powerful than the RTX 3090 Ti at lower power, while the RTX 4080 12GB features 7,680 CUDA cores and with DLSS 3, it is faster than the RTX 3090 Ti.
The RTX 40 series performance improvements are also enabled by a series 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 utilise 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
The GeForce RTX 4090 will be available on October 12 starting at US$1599 (RM7,288), while the RTX 4080 will only be made available in November starting at US$1,199 (RM5,465) for the 16GB model and US$899 (RM4,097) for the 12GB model.
As usual, these new GPUs will be available from the usual custom board partners including ASUS, Colorful, Zotac, Gigabyte and more, OEMs such as Acer, Alienware, Dell, HP and more will soon be offering systems with RTX 40 series GPUs as well.