Press "Enter" to skip to content

Nvidia’s Ada Lovelace GPU generation: $1,599 for RTX 4090, $899 and up for 4080

Enlarge / Time to bust out the checkbook again, GPU lovers. The RTX 4090 is here (and it’s not alone).

After weeks of teases, Nvidia’s next generation of computer graphics cards is here: the “Ada Lovelace” generation of RTX 4000 GPUs. Nvidia CEO Jensen Huang debuted two new models on Tuesday, complete with prices and release windows: the RTX 4090, which will start at a whopping $1,599, and the RTX 4080, which will launch in two configurations.

The pricier card, slated to launch on October 12, occupies the same highest-end category as the company’s 2020 megaton RTX 3090 from 2020 (previously designated by the company as its “Titan” product). Its jump in physical size will demand three slots on your PC build of choice. The specs are indicative of a highest-end GPU: 16,384 CUDA cores, up from the 3090’s 10,496 CUDA cores, and 2.52 GHz of boost clock, up from 1.695 GHz on the 3090. Both of these 4090 jumps perform within the same 450 W power envelope as the 3090. Its RAM allocation will remain 24GB of GDDR6X memory.

This jump in performance is fueled in part by Nvidia’s long-rumored jump to TSMC’s “4N” process, which is a new generation of 5 nm chips and a massive efficiency jump from the previous Ampere generation’s reliance on an 8 nm process.

Enlarge / The RTX 4080, coming in two SKUs.

Meanwhile, the RTX 4080 will follow in “November” in two SKUs: a 12 GB GDDR6X model (192-bit bus) starting at $899, and a 16 GB GDDR6X model (256-bit bus) starting at $1,199.

Both models include iterative updates to Nvidia’s proprietary RTX chipset elements: RT cores and tensor cores. Alongside these, Nvidia has announced updated processes for both its handling of real-time ray tracing in 3D graphics and its Deep Learning Super-Sampling (DLSS) upscaling system. The former system will be augmented on Lovelace GPUs with two new types of hardware units: an “opacity micromap engine,” meant to double raw ray tracing performance, and a “micromesh engine,” which will increase the amount of geometric coverage “without storage cost” on the rendering front.

Just came in:  Samsung Has Delayed Galaxy Tab S9 Due To Weak Demand

The latter has now been bumped to a new numerical version: DLSS 3. According to Huang, this system promises to “generate new frames [of gameplay] without involving the game, effectively boosting both CPU and GPU performance.” This frame-by-frame rebuilding of graphics in real time, if it works as promised, is a substantial leap as a concept over the pixel-by-pixel process that has been so successful across both DLSS and its TAA-boosted competitors, AMD’s FSR 2.0 and Intel’s upcoming XeSS.

On top of those proprietary systems, Nvidia’s newest GPUs will apparently lean on a new process that Huang calls “shader execution reordering.” While this will improve performance for raw rasterization, Huang’s brief description of the system hinges largely on ray tracing’s computationally expensive workloads and says it will drive “2-3 times” the RT performance of the company’s previous Ampere generation of GPUs.

This is a breaking report. Developing