• 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.

The first "proper" Kepler news Fri 17th Feb?

Because when you are about to charge £400+ for something and have been waiting for it due to delays (which are Nvidia's fault) then you deserve better.

Trying to stop people from buying a product that already exists and is already faster than any Nvidia effort deserves more than a ****in static bag with a poorly printed piece of card on (the black isn't even black).

Depends if they actually rebench the 7970 and 7950 again with different driver set when they are benching the GTX680. Wasn't one of the recent driver by AMD actually made the cards slower than the previous verson? I think I recall people were rolling back from 12.2 to 12.1 or something.

This I hope. I did read the same but can't remember on what part of the forum.

I would hate to think Toms has been biased. I want "Fair" reviews and no cheating.
 
HKEPC measured the GK104 as being around 319MM2 in size.


Well, if that's true then I was within 2% with my guess. I'll take that.

As a engineer, anything within 10% is reasonable :p


HKEPC didn't have the raw silicon to measure. They took a vernier caliper to the die with some packaging. The only way we'll know the size is if NVIDIA tells us. 1 mm off in the breadth and length will easily make the difference between 280 something and 319mm.
 
NONE of the major hardwarereview sites can be trusted they have all at some time or the other taken obvious advertising bribes to claim this or that product is worth your hard earned money ;) Same as with games for many years now the advertising budgets are so large when was the last time you saw an accurate & negative review of something expensive on a mainstream website!!

Several sites have even been caught out doing so :( Ignorance is bliss :rolleyes:

To be fair to OCUK though if they post benchmarks you can usually trust those results so if your unsure always wait for OCUK to bench!!
 
Last edited:
NONE of the major hardwarereview sites can be trusted they have all at some time or the other taken obvious advertising bribes to claim this or that product is worth your hard earned money ;) Same as with games for many years now the advertising budgets are so large when was the last time you saw an accurate & negative review of something expensive on a mainstream website!!

Many times when I write them :p.
 
GK110 Specifications Approximated
Even as launch of the GK104-based GeForce GTX 680 nears, it's clear that it is emerging that it is not the fastest graphics processor in the GeForce Kepler family, if you sift through the specifications of the GK110 (yes, 110, not 100). Apparently, since GK104 meets or even exceeds the performance expectations of NVIDIA, the large-monolithic chip planned for this series, is likely codenamed GK110, and it's possible that it could get a GeForce GTX 700 series label.

3DCenter.org approximated the die size of the GK110 to be around 550 mm², 87% larger than that of the GK104. Since the chip is based on the 28 nm fab process, this also translates to a large increment in transistor count, up to 6 billion. The shader compute power is up by just around 30%, because the CUDA core count isn't a large increment (2000~2500 cores). The SMX (streaming multiprocessor 10) design could also face some changes. NVIDIA could prioritize beefing up other components than the CUDA cores, which could result in things such as a 512-bit wide GDDR5 memory interface. The maximum power consumption is estimated to be around 250~300 Watts. Its launch cannot be expected before August, 2012.

nVidia GK110

~ 550mm ² die size (28nm in production at TSMC)
Round 6 billion transistors
DirectX 11.1 Kepler architecture
most likely (compared to the GK104) different structure of shader clusters (SMX)
clearly more than in 2000 (1D) shader units (to 2500 shader units)
2 + Double Precision teraflops computing power, accordingly, probably 4 + Single Precision teraflops computing power
512-bit DDR memory interface
Game Power consumption 250 to 300 watts
Tape-out until after January 2012 launch not before August 2012

http://translate.google.com/transla...vom-nvidia-gk110-chip-zu-erwarten-ist&act=url
 
Interesting, keeping an eye on that...
Worst comes to the worst I end up with a 680 as my main gpu driving card to keep TDP down and just drop in that card for compute right? Or the other way round for frames, guess that's the benefit of CUDA/OpenCL.
 
nVidia GK110

~ 550mm ² die size (28nm in production at TSMC)
Round 6 billion transistors
DirectX 11.1 Kepler architecture
most likely (compared to the GK104) different structure of shader clusters (SMX)
clearly more than in 2000 (1D) shader units (to 2500 shader units)
2 + Double Precision teraflops computing power, accordingly, probably 4 + Single Precision teraflops computing power
512-bit DDR memory interface
Game Power consumption 250 to 300 watts
Tape-out until after January 2012 launch not before August 2012

http://translate.google.com/transla...vom-nvidia-gk110-chip-zu-erwarten-ist&act=url

That's something to get excited about! ... guess I could wait have to see how the reviews pan out for the 680 -
 
Back
Top Bottom