Nainstalovat Steam
přihlásit se
|
jazyk
简体中文 (Zjednodušená čínština)
繁體中文 (Tradiční čínština)
日本語 (Japonština)
한국어 (Korejština)
ไทย (Thajština)
български (Bulharština)
Dansk (Dánština)
Deutsch (Němčina)
English (Angličtina)
Español-España (Evropská španělština)
Español-Latinoamérica (Latin. španělština)
Ελληνικά (Řečtina)
Français (Francouzština)
Italiano (Italština)
Bahasa Indonesia (Indonéština)
Magyar (Maďarština)
Nederlands (Nizozemština)
Norsk (Norština)
Polski (Polština)
Português (Evropská portugalština)
Português-Brasil (Brazilská portugalština)
Română (Rumunština)
Русский (Ruština)
Suomi (Finština)
Svenska (Švédština)
Türkçe (Turečtina)
Tiếng Việt (Vietnamština)
Українська (Ukrajinština)
Nahlásit problém s překladem
Even if Vega manages to pull off a miracle and surprises everyone, NVIDIA isn't about to be caught with its pants down either. Rumors has already surfaced indicating that NVIDIA has sped up its Volta schedule and maybe ready as early as Q2 2017.
As to counter Zen expecting Q1 2017, Intel isn't sitting idle too all this time. Kaby Lake is entering mass production in Q4 2016 and may ready for sale in Jan/Feb. The 7th gen Core will be the last 14nm processor before Intel makes the next leap to 10nm(Cannonlake), so you can expect the most refined version in terms of power consumption and performance of this era.
It'd be nice if the red team finally deliver what they promise, but that doesn't mean the green and blue teams aren't gonna keep pounding them deadly hard on both sides.
About the GPUs, if Volta is being released in early 2017, then what will happen to the GTX 1080 Ti? I'm fairly positive that NVIDIA will release a GTX 1050 into the world later this year, but people looking for a true successor to the GTX 980 Ti may be out of luck.
HBM2 memory was planned to be on next gen AMD cards. It however never happened. They are actually still using GDDR5 memory and have become mainstream cards now.
Nvidia went another path: GDDR5 > GDDR5X. This is double bandwidth memory of the GDDR5 in their new Pascal series. Blazing fast, but still not quite HBM2 performance levels. Rather a stepping stone to GDDR6 memory in the future instead.
HBM2 is expensive, fast and you will find in Nvidia very high-end (not for the public) sciencific research cards. They couldn't justify the current price tag to performance level for the public at the moment. It's in the Nvidia Tesla P100 (great for advance calcuation and artificial intelligence, but not so much gaming).