Soundwave said: lol this is way better than PS5/XSX. |
I wouldn't be so fast to claim that, since it seems like Ampere flops are a very different beast from Turing flops, assuming these are FP32 flops at all. I'm thinking something like Terascale to GCN, but in reverse.
According to the benchmarks above, the 8,704 Ampere Cuda cores of the RTX 3080 perform closer to ~ 5,000 - 5,500 Turing Cuda cores, clock per clock. So they are just about 60% as efficient compared to Turing. I'm not sure how RDNA 2 would compare.
Edit - I do remember, years ago, that you were once mislead by Nvidia's PR speech and believed the Tegra portable was 1 TFLOP of FP32 too, so yeah.