Nvidia has seemingly confirmed that its newly-announced Ampere GPU architecture will be coming to both GeForce and data center graphics cards.
When it unveiled its 7nm Ampere microarchitecture earlier today, Nvidia focused entirely on the data center, with no mention of PC gaming or the consumer-facing GeForce RTX 3080. Instead, the 7nm architecture will debut with the Nvidia data center-focused A100 GPU, which should deliver an impressive 20x improvement in raw compute power compared to Nvidia Volta.
The company also announced that it has bundled eight of these GPUs inside the $1 million DGX A100, which can handle up to 56 tasks at once and reach up to 5 petaflops of AI performance.
While none of this means much to the average PC gamer, Nvidia CEO Jensen Huang said in a media briefing ahead of its virtual GTC conference that the 7nm Ampere microarchitecture will be used for all of its next-generation graphics cards, according to Market Watch – this presumably includes the next GeForce cards.
This doesn’t reveal much about what these cards will actually look like, but we’re sure Nvidia will reveal more when it shows off the cards – hopefully later this year. And we’ve reached out to Nvidia for clarification, and we’ll update this article if we hear anything.
All in the architecture
While it’s yet to release any information about consumer-facing GeForce GPUs using Ampere, when asked by a reporter in the briefing about the difference between enterprise and consumer approaches to Ampere, Huang said “there’s great overlap in the architecture, but not in the configuration.”
This now-confirmed move will mark the first time that Nvidia will unify all its products under a single microarchitecture. It’s previous generation of GPUs, for example, used Turing for its consumer-facing GeForce and Quadro CPUs, and Volta for Tesla GPUs destined for the data center.
The long-rumored Nvidia GeForce RTX 3080 is widely expected to be Team Green’s first consumer GPU to be based on the 7nm Ampere platform. According to a recent leak, the graphics card will boast 3,840 CUDA cores, compared to 2,944 in the RTX 2080, along with a 320-bit memory bus and probably 10GB of video RAM.
The GeForce RTX 3080, naturally, is expected to launch alongside the 3080 Ti, and a recent rumor suggests this GPU be some 40% faster than the current GeForce 2080 Ti.
Nvidia’s next-gen Ampere graphics cards are expected to arrive in the third quarter of 2020, starting with the higher-spec flagship models.