fensisuperstar
Ray tracing itself does require additional functional hardware blocks, and AMD has confirmed for the first time that RDNA2 includes this hardware. Using what they are terming a ray accelerator, there is an accelerator in each CU. The ray accelerator in turn will be leaning on the Infinity Cache in order to improve its performance, by allowing the cache to help hold and manage the large amount of data that ray tracing requires, exploiting the cache’s high bandwidth while reducing the amount of data that goes to VRAM.
AMD is not offering any performance estimates at this time, or discussing in depth how these ray accelerators work. So that will be something else to look forward to once AMD offers deep dives on the technology.
Čitav članak - https://www.anandtech.com/show/16202/amd-reveals-the-radeon-rx-6000-series-rdna2-starts-at-the-highend-coming-november-18th/2
Drugdje sam vidio da spominju do 10X veće performanse u RT operacijama u odnosu na prethodni gen. Čak i da je to nekim slučajem sve izvedeno softverski, opet bi im trebali skinuti kapu, zar ne? Ali da, konkretno testiranje se tek očekuje. Rekoh već da očekujem slabije performanse od Nvidije jer tu zaostaju s primjenom techa, no vjerujem da će uhvatiti korak s vremenom. Kako god okreneš, impresivno je ovo što su najavili i napravili na istom proizvodnom procesu i samo s preinakama na arhitekturi.
Edit: Da, evo i s Tom´s Hardware:
One Ray Accelerator per CU, 10x speedup for RT calculations
https://www.tomshardware.com/news/amd-rx-6000-rdna-2-big-navi-gpus-revealed
