• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

No GK110. Instead GK114 will be the GTX 780

Caporegime
Joined
24 Sep 2008
Posts
38,284
Location
Essex innit!
Ever since NVIDIA first showed us Kepler in its full form as the Tesla K20, people have been asking about a GeForce card based on this silicon, GTX 780. However it was then speculated by OBR-Hardware that there would most likely not be a GeForce GTX 780 GK110 based card. Since then we have heard little, if anything about what GK11x derivative would see the light of day.

SemiAccurate is citing two sources as naming the “big gaming GPU”, meaning the 780, from NVIDIA as the GK114 and the GK114-GX. Similar to AMD, this chip is expected to be late and not see a release until the earliest being March 2013, but S.A. believes April or May is much more likely. Also like AMD, the jump in performance is not supposed to be mind boggling; partially due to die size restraints and in my opinion this is to be expected with Maxwell now on the horizon. If NVIDIAs next GPU release completely demolished the GTX 680, then the market enthusiasm for Maxwell would shrink dramatically when the time comes. So you have Maxwell playing a role most likely in expected performance and you also have AMD, which we wrote on yesterday, expected to jump only by 15%.

All of these factors play into the expected performance of GK114, however unlike AMD, NVIDIA has more room to play in the TDP department. This is due to the highly efficient architecture of Kepler. According to S.A. “those who have been briefed” are also saying NVIDIA is expected to have the same 15% jump in performance over the GTX 680 as was reported on AMD. So basically the next generation of silicon from both NVIDIA and AMD is only expected to gain 15% performance increase over their predecessors. However according to our sources the increase for the GTX 780 would be around 25% over the GTX 680, instead of the 15% S.A. is citing. This may not be the series launch you will tell your grandkids about, but may remind you more of the G92 vs G92b period. The GTX 600 Series was restrained heavily by its small 256-bit Bus, I believe NVIDIA could achieve this 15% increase simply by giving it the bus width seen on Fermi cards, instead of the Bus we saw on the FX5900 Ultra.

From reading this, It seems the next gen of cards from both counter parts will offer a 15% increase over the current 6XX/7XXX GPUs and this leaves me a little deflated.

Dye shrinks are not happening yet and the refresh of the current GPUs will only bring marginal increases. Ideal for new buyers and I guess good news for current gen owners (saves on our wallet). I was hoping for something spectacular after hearing the rumours of GK110 but I think it was just my wishfull thinking.

http://semiaccurate.com/2012/10/12/what-is-going-on-with-nvidias-gk114/

That is the original link but I couldn't copy and paste.
 
So looks like it'll just be fast enough, but will be saving something back for Maxwell. Any indication on Maxwell - presumably it'll be late 2014 going by that.
 
Expected increase.(Unless they keep all under wraps )
Unless a new design or a die shrink you wont get those numbers so the amd 8900 series will still be the fastest card on the block.
if nvidia still do the gaming type of card a lot of people using open Cl applications will go amd.
 
Kepler is about 10% better power consumption vs 7###, its down to the slower Memory bus, 2GB vs 3GB vRAM and much lower OpenCL performance

So they do have a little room to add more memory, and as they cite (a faster Memory bus) to match AMD on power consumption.

I would think its likely that they will, they need to as thats whats keeping Kepler from performing as well as AMD in multi-screen resolution.
 
Last edited:
looks like us nvidia boys will be holding onto our precious 680's for another year to come! This is bad news though for us as the prices for our cards wont be falling much more... meaning SLI will have to wait even longer :(
 
Disappointing. But I'll still probably upgrade to keep on the curve. Skipping a generation means higher costs later down the line as the sell on value of your previous card(s) diminishes rapidly.
 
Disappointing. But I'll still probably upgrade to keep on the curve. Skipping a generation means higher costs later down the line as the sell on value of your previous card(s) diminishes rapidly.

That's what i'll probably do.
I've either got to have my cards on air first or wait till the blocks are for sale before upgrading though =(

If it's only a 15% gain, the depreciation shouldn't be too bad for the current gen.
 
The lower TDP of Kepler should mean they can squeeze more out of the 780. It could/should mean that Nvidia regain the crown of top dog. Also to note as how cool Kepler cards currently run. This could be a big factor.
 
The lower TDP of Kepler should mean they can squeeze more out of the 780. It could/should mean that Nvidia regain the crown of top dog. Also to note as how cool Kepler cards currently run. This could be a big factor.

TDP is nothing to do with power usage, it is a maximum thermal power design.

7970 = 250w TDP

GTX 680 = 195w TDP

That means the Maximum the 7970 can draw (without board power line increases) is 250 Watt.

For the GTX 680 its 195 Watt.

The power usage (Total System) on Metro for example is,- 7970; 391 Watt, and for the GTX 680 its 362 Watt, 29 watt less, or about ~10%

If anything what this TDP difference means is the 7970 can draw 55 Watts more power, slightly more head room than the GTX 680.
 
If anything what this TDP difference means is the 7970 can draw 55 Watts more power, slightly more head room than the GTX 680.
I think you've missed the point, because the 680 is lower power than the 7970 all Nvidia need to do is simply make a beefier version of the 680 and up the TDP to something similar to the 7970 to deal with the extra heat. AMD don't have that luxury.
 
TDP is nothing to do with power usage, it is a maximum thermal power design.

7970 = 250w TDP

GTX 680 = 195w TDP

That means the Maximum the 7970 can draw (without board power line increases) is 250 Watt.

For the GTX 680 its 195 Watt.

The power usage (Total System) on Metro for example is,- 7970; 391 Watt, and for the GTX 680 its 362 Watt, 29 watt less, or about ~10%

If anything what this TDP difference means is the 7970 can draw 55 Watts more power, slightly more head room than the GTX 680.

Ermmmmmmmm :confused:

TDP is the ability to dissapate heat and because Kepler has a lower TDP, this means it can stretch its legs a little more. You should do some research before you start pulling people up and spouting a load of drivle that is complete rubbish. I thought you had a better understanding of these sort of things but then again, you did say a card that has a higher clock wins, so I shouldn't have expected more.
 
Nvidia have Less than 10% power usage in hand, and thats without upgrading the memory, which if they don't they will have the same problem they do now at very high res.

Its to much to think of what is less than 10% as it stands, and will be whittled down to almost nothing with those upgrades as anything significant.

With respect i think its wishful thinking, there is almost nothing there to play with.
 
Nvidia have Less than 10% power usage in hand, and thats without upgrading the memory, which if they don't they will have the same problem they do now at very high res.

Its to much to think of what is less than 10% as it stands, and will be whittled down to almost nothing with those upgrades as anything significant.

With respect i think its wishful thinking, there is almost nothing there to play with.

With respect, I don't think you fully understand how TDP works and your comment "I think it's wishful thinking", is your wishful thinking.
 
Back
Top Bottom