Uite asta e secretul fine whine. I realitate AMD-ul din punct de vedere hardware e placa mai buna. Asa cum o arata hartia.
Nu neaparat. SI nu e vb de drivers ci de directx, implentari ale jocurilor, etc. Degeaba ai un hardware cu o arhitectura care e puternica pe hartie dar software-ul nu o utilizeaza. A fost nevoie de o rescriere a dx si lansare vulkan pt ca arhitectura sa fie folosita cat de cat eficient.
AMD se arunca la inovatii fara a avea suport in OS, nvidia face lucrurile cat mai simple dar targetat pe ceea ce este posibil practic, pentru generatia respectiva. Da, AMD poate va avea suport mai eficient peste 1-2 generatii dar pana atunci generatia actuala este crippled.
Ah, si o completare la ceea ce spuneam mai sus relativ la tflops:
"With Turing, Nvidia said that in many games (looking at a broad cross section of games), roughly 35% of the CUDA core calculations were integer workloads. Memory pointer lookups are a typical example of this. If that ratio still holds, one third of all GPU calculations in a game will be INT calculations, which could potentially occupy more than half of the FP32+INT portion of the SMs.
Nvidia's own performance numbers reflect this. It has shown a generational performance increase of roughly 2X when comparing RTX 3080 to RTX 2080, but if you look just at TFLOPS, the RTX 3080 is nearly triple the theoretical performance. But the reality is the RTX 2080 could do FP32 + INT at around 10 tera-OPS each, whereas the RTX 3080 has nearly 30 tera-OPS of FP32 available and only 15 tera-OPS of INT available.
Even though compute performance has still received a massive increase, it's also important to note that bandwidth hasn't grown as much. The RTX 3080 has triple the FP32 potential, 1.5X the INT potential, and about 1.5X the bandwidth as well (1.53X to be exact). There are probably improvements in memory compression that make the effective bandwidth higher, but overall we likely will never see a 3X increase in performance, unless someone can make a pure FP32 theoretical test."