The launch of Ampere-based consumer GPUs is supposedly right around the corner, with NVIDIA having already showcased its new architecture in June at its GTC keynote. The A100 is the first Ampere-based GPU that NVIDIA has unveiled, which it claims to be the "world's largest graphics card". Initial benchmarks of the A100 have failed to impress, but a new rumour about the RTX 3090 has put the Ampere architecture in a better light.
According to @KkatCorgi, the RTX 3090 may offer up to 50% improved performance over the RTX 2080 Ti, NVIDIA's current flagship consumer graphics card. This will apparently translate to a 3DMark Time Spy Extreme score of nearly 10,000 points, which would place the RTX 3090 miles ahead of any contemporary graphics card.
We should point out that it is unclear where @kopite7kimi or @KkatCorgi have received their information. However, Videocardz and @_rogame have not dismissed their claims, though. The RTX 3090 is believed to be based on the GA102-400 GPU, which reportedly has 5,376 CUDA cores and 24 GB of VRAM running at 17 Gbps.
Source(s)
Top 10 Laptops
Multimedia, Budget Multimedia, Gaming, Budget Gaming, Lightweight Gaming, Business, Budget Office, Workstation, Subnotebooks, Ultrabooks, Chromebooks
under 300 USD/Euros, under 500 USD/Euros, 1,000 USD/Euros, for University Students, Best Displays
Top 10 Smartphones
Smartphones, Phablets, ≤6-inch, Camera Smartphones