http://www.3dcenter.org/news/nvidias-gp104-chip-geht-derzeit-anscheinend-seine-testphase
http://wccftech.com/nvidia-gp104-pascal-zauba/
http://videocardz.com/58101/nvidia-gp104-and-first-polaris-gpu-supposedly-spotted-on-zauba
>Nvidia is employing TSMC for the fabrication of its GPUs and we also know what their estimates are for performance increase with the jump to 16nm FinFET. 16FF+ will be approximately twice at dense and will be able to achieve higher speeds than before. Nvidia itself has stated a performance jump of 2x.
>Pascal GPUs are slated to be pretty damn amazing. They will feature 4X the mixed precision performance, 2X the performance per watt, 2.7X memory capacity & 3X the bandwidth of Maxwell. We will be seeing the GP104 flagship this year, and the GP100 one as well near the end
GTX 1070/1080 (GP104) GDDR5x will beat the GTX 980ti/Titan X (GM100)
GTX 1080ti (GP100) with HBM2 is for later
>>52368917
yeah but will it have 3.5GB?
>the 970 has 4gb of vram we swear, now buy our overpriced products
>have to wait until the end of the year for HBM2, the reason everybody is waiting for Pascal in the first place
Enough with the fucking waiting game already, jesus christ.
>>52369056
OP posted clearly 2.7x improvement in memory.
So it will have 9.45GB but will be marketed as 10.8GB card.
>>52368917
so its shit
If it costs as much as the Titan X, I'm literally not going to dump my GTX 980.
Especially if >>52369096 holds true. I don't want to be stuck with a "new" non-HBM2 card.
>>52369096
Look the Fury X. HBM was useless and expensive in this card.
>>52368917
About time we hear some more information, but I'm getting sick of waiting. It would be stupid to buy something like a 980ti now and my 670s are feeling really old.
>>52369165
No it wasn't, retard. The Fury X was hamstrung in other areas, especially having the same amount of ROPs as the 290X.
>>52369164
>>52369159
GP104 =/= GP100
>>52369219
They should use GDDR5/GDDR5X not HBM1
Saving muh monies for a GP100. Except this time Nvidia will probably be dicks and gimp the 1080Ti to be significantly worse than their newest Titan.
>>52368917
>2X the performance per watt
The prototype AMD demoed recently has 3x the performance per watt of a GTX 950. Nvidia are finished!
>>52369358
>he believes everything nvidia says in press releases
stay pleb my friend now go buy a new apple product
>>52369378
So the performance per watt is going to be even worse? Then Nvidia are even finisheder than finished! The finishedest!
So I have to wait until next year for the actual good shit?
AMD might be able to release their GPUs first this time around. Depending on how fast they are, they could have half a year headstart.
Maybe they'll finally win back all that market share they lost.
>>52368917
>gtx 1070 beat beat a gtx 980 ti
At least this time they were honest about it.
>>52368917
>twice at dense
>same power
So 200°C it is. Time for liquid metal cooling?
>>52370088
>I can't read
>>52368917
I will wait GP100
>>52370906
See you in 2017.
They better deliver a $350-$400 1070 that beats the Titan X.
so long as it plays vidya at 4k on a single card idgaf
>>52369066
ebin meme™
>Double the performance
>Just bought 980ti
fuck im fucked gg no re
>>52370968
Maybe Q3-4
So there is no reason to buy one until you are gaming on a 4k right?
1080p, 1440p 980ti is good enough for 4 years, right?
>>52372256
No? Because gaming devs. will start to gear their games towards these GPUs
980Ti will be left in the fucking dust like fish on a beach
>>52369723
>At least this time they were honest about it.
NVIDIA always brags about how their newer tech is better than old tech.
If anything, they lie the other way. The "970 is superior to the 780 Ti SO UPGRADE NOW!" when it's actually worse in rendering due to lower cores.
>>52372290
Yeah. But there is only so much they can do before a 980ti couldn't handle those games at those resolutions. . . I mean a 970 to this day can do 90% of what a 980ti can do at those resolutions.
>>52372341
thats cuz thye're both maxwell this is new architecture with hbm
>>52369268
>GDDR5X
But thats worse
>>52372513
HBM1 was was stupid
>>52372634
So is GDDR5X.
>stupid
According to AMD, the low memory amount could be solved easily by optimisations nobody had bothered doing because of the way GDDR5 is being used.
Not sure if they actually did though.
>>52372634
Not really.
It was a show stopper.
It came along, first generation, offering vast improvements in power usage, reduced surface area, and x28 the bandwidth of GDDR5 and to top it off, high density.
It showed the market "We've been busy, look at our new toys!" and caused for another movement in memory technology. It opened a gateway to a whole new world of GPU manufacturing possibilities in itself. All while serving as a stop-gap until HBM2 arrives.
To say HBM was stupid is only to prove your unwillingless to accept advances in technology for the better.
>>52372679
>AMD
>Theoretically it's better if the entire industry catered to our whims and fairies and unicorns existed.
>>52372735
>To say HBM was stupid is only to prove your unwillingless to accept advances in technology for the better.
HBM1 m8
Riddle me this
After lying about VRAM, and lying about power consumption, why should I give a single shit about Nvidia hype?
>>52372762
You fail to see the point, but continue to shitpost.
Please get a trip.
>>52372770
Right now, there is only the one, so to specify 1/2 is pointless.
Even then, HBM, implies first edition, should it be in close proximity to HBM2, which defines a clear iteration over the original HBM.
>>52372786
>why should I give a single shit about Nvidia hype?
Because Pascal will outsell Polaris 4-to-1
>>52372786
You shouldn't.
So far as gaming goes, nVidia is only worth it in the High end, GTX980 and the like.
Should you need PhysX for the software you work with, you need to pay attention to the comings and goings, especially with the enterprise GPUs.
>>52372811
They should put cheaper gddr5 and wait hbm2
>>52372852
And then no developers are used to working with HBM, no software can be updated, no change can happen to welcome HBM2 and make as much use as possible upon it's arrival.
The point of bringing HBM to market was to allow for these changes.
>still buying nvidia after 970 catastrophe
>>52372959
>>52373110
;^)
>>52373228
pls :stop:
>>52373237
:stopmusic:
>>52372256
No card is good enough for 4 years, unless you want to get shit performance at shit settings, then yeah, maybe you can do it.
But if you want the performance and image quality a card like the 980Ti gets you now, why would you want a shit-tier experience in 4 years? Wouldn't you want to keep everything fast and high quality?
>>52373295
>No card is good enough for 4 years
Radeon 7k series has been recycled for almost as long now, and it still holds its own well due to driver improvements.
8800Ti and Radeon 9700 both had performance leads so great that they worked fine 4 years later.
Obviously not at fullhd res with 16xAA on the most recent titles, but they worked great.
>>52371007
With all this marketing bullshit I can only agree with this post, pascal 1070 should be far superior than anything Nvidia put out recently
>>52373154
>stock vs OCed
>Ru website
Never change AMDumbs
>>52373365
That's my point, sure a 7970 would do fine, but it won't provide anything close to the top-tier experience it was able to provide when it was brand new. Also, these last few years are somewhat atypical in recent history since we were stuck on 28nm shit for a very long time, which is why the first 28nm cards still hold up as well as they do.
A 980Ti will likely not benefit from that, especially since it's the last breath of a node that should've died long ago and we're essentially getting 2 shrinks with Pascal/Polaris. I would definitely not expect it to be as good as a 7970 is now in 4 years, especially not with shit like VR and 4K making a push.
>>52373563
>Only m-my cherrypicked benchmarks c-c-count!
;^)
>>52373647
>Only m-my cherrypicked benchmarks c-c-count!
:'3
>>52373647
>Only AMD are allowed to factory OC despite the fact that reference 970s can't even be found!
:'3~~
>$350 plebs will have your $650 performance card a year later
GPU stagnation when? I wouldn't mind only 5% increases yearly forcing devs to optimize.
So are the first generation after a die shrink typically great, or does it usually take them a few tries to get it right?
I spent 450 bucks on a GPU in 2015 and upgrade every 2.5 years, will be slightly salty if performance/dollar doubles in a year.
>>52372892
They shouldn't o that, they should make the GPU cheap for /me/ right now.
I don't like people optimizing for AMD anyway.
>green team vs red team
I hope you AMDfags enjoy that electric furnace next to you.
I'm sticking with my Intel+Nvidia combo, maybe for very cold winters I will buy an AMD CPU and GPU so I don't have to adjust thermostat.
>>52373295
Who told you this crap? The only reason you need a new card is if a new game as some crazy new engine your card cant push already.
>>52374228
Well memed friendo
>>52369723
they were not, since they never said that.
it was the articles opinion.
