Moderátoři: Walker1134, Wilik
No hotova ofiko neni a to jeste se da cekat kolorit jako day 1 patch. Az to vyjde i s kartami a RT patchem, pak se to da zhodnotit.Riku píše:pochybuju, že 3 týdny před vydáním je hra nehotová
Je to PR slide, je v tom i DLSS, pockej s "revoluci" na recenze.HEAD píše:Takze je to fakt revolucni architektura.
pokial to neni je fejk a aj ked vezmeme do uvahy cherry picked hry, tak stale viac ako dobry vysledok...HEAD píše:vykon 2080 vs 1080 podle nv.Narust tam je 40-50%.Coz je teda hodne divny pac 2080 ma jen o 15% vic sp a stejny takty.Takze je to fakt revolucni architektura.Nak zvysili IPC o 20-30%.
https://videocardz.com/newz/nvidia-publ ... comparison
Ono nemusi to byt fake, ale vyberes tu spravnou scenu (treba koukani do zdi 
) a do procent doplnis "Up to" a mas jako marketak vydelano. Ale aspon neco ohledne vykonu ukazali. Huang je taky marketer, takze vse co rekne se musi prosit sitem. Kazdopadne pokud zvedli o dost IPC, tak uvahy o jejich uarch, ktera narazi na limity, muzu splachnout do zachoda.
čo ty vieš, možno na 1080ke pojde TR na 25 fps a na 2080ke 35, grafy by potom sedelihnizdo píše:...a nyni bych se rad vratil k diskusi o 1080p a 35fps
50k ne jen cca 40khavli píše:Pokud by to takhle vyslo, tak s nastupem 7nm delam upgrade. Pokud ovsem v te dobe nebude "3080" za 50k
Klidne by se na to dalo nahlizet jako na refresh Pascalu, proc ne? Uz to totiz zavanelo (resp zavani - stale nevime) urcitou stagnaci, asi jako kdyz Intel uz 10 let recykluje Nehalem.Eddward píše:Ja si tiez myslim ze to tak moze byt a zrejme aj je. Neviem kto a z akeho dovodu toto vidi ako nejaky refresh Pascalu? a 7nm ma byt nova architektura ?
Je to skor presne naopak. Toto je nova architektura a 7nm prinesie zmensenie cipu/narast jednotiek/vyssiu frekvenciu a par drobnosti navyse...
Turing SM: Dedicated INT Cores, Unified Cache, Variable Rate Shading
Alongside the dedicated RT and tensor cores, the Turing architecture Streaming Multiprocessor (SM) itself is also learning some new tricks. In particular here, it’s inheriting one of Volta’s more novel changes, which saw the Integer cores separated out into their own blocks, as opposed to being a facet of the Floating Point CUDA cores. The advantage here – at least as much as we saw in Volta – is that it speeds up address generation and Fused Multiply Add (FMA) performance, though as with a lot of aspects of Turing, there’s likely more to it (and what it can be used for) than we’re seeing today.
The Turing SM also includes what NVIDIA is calling a “unified cache architecture.” As I’m still awaiting official SM diagrams from NVIDIA, it’s not clear if this is the same kind of unification we saw with Volta – where the L1 cache was merged with shared memory – or if NVIDIA has gone one step further. At any rate NVIDIA is saying that it offers twice the bandwidth of the “previous generation” which is unclear if NVIDIA means Pascal or Volta (with the latter being more likely).
Finally, also tucked away in the SIGGRAPH Turing press release is the mention of support for variable rate shading. This is a relatively young and upcoming graphics rendering technique that there's limited information about (especially as to how exactly NVIDIA is implementing it). But at a very high level it sounds like the next generation of NVIDIA's multi-res shading technology, which allows developers to render different areas of a screen at various effective resolutions, in order to concentrate quality (and rendering time) in to the areas where it's the most beneficial.
