Isn't this an unfair comparison, given they test the A6000 Ampere (half the price of MI210) instead of the Ada generation (still a cheaper than the MI210, but ~2x the CUDA cores as Ampere)?
Comparisons between different chip architectures are imperfect. In our opinion the most fair thing to do is 1) match the TFLOPs (since these workloads are compute bound), and 2) find a similar card that can run the same size models. Since MI210 has 64GB, the closest one is the A6000 with 48GB. Many of the less expensive ADA cards can't even fit a 13B model in VRAM, so a comparison could not even be made.
Oh I get it: you're matching compute hardware capability to test the performance of your software. Thanks! (and good job!)
I have an Ada 6000 installed here. How can I test this?