NVIDIA Accelerates Volta to May 2017?

[Darller]

Let's make something completely clear. Those of us who can afford the halo cards like GTX TITAN X, TITAN X, etc. are not and will not be crying over the release of these new cards. We'll be placing our orders.

You know the performance levels everyone is drooling over with the 1080? I've been enjoying that (and more since I always use SLI) for over a year.

Pathetic, jealous little internet denizens hope that we feel badly about our purchases, but the reality is we don't. We can afford it, and that pisses you off. Work harder, get a better job or education... do something about your situation, because mine is fine.

 

[PP Mguire]

Gr8 b8 m8 I r8 8/8.

 

[TheHunter]

It is used for TSAA in DOOM. 8x TSAA, on a card like Fury X with lots of idle shaders, is practically zero-cost in terms of framerate.

Pascal improves async compute functionality compared to Maxwell (which facepalms when trying) but NVIDIA's implementation is still behind AMDs. Then again, async compute is only beneficial when the card has idle hardware.

Well according to this benchmark here Maxwell e.g. 980ti benefits 5Fps @ Vulcan, Pascal 7fps

lol old Kepler actually lost 10fps


http://www.pcgameshardware.de/Doom-2016-Spiel-56369/Specials/Vulkan-Benchmarks-Frametimes-1202711/

One Nv driver PR tweeted there will be some magic boosts soon.
This was when all this async talk started (AoS, Hitman) by r362 & r365 branch,. So this current r367 obviously doesn't have it (disabled), Im thinking r370 or max r375 it should if not then...