• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.
  • The forums have been upgraded with support for dark mode. By default it will follow the setting on your system/browser. You may override it by scrolling to the end of the page and clicking the gears icon.

Kepler Unbeatable: NVIDIA

to be fair dude you are on TPU and this is a place not oft visited by the Average user, i want it all personally max performance and minimal power draw, the power pulled can be highly regarded by some as it is by me, if you fold and can run two cards 24/7 with a smaller psu and cheaper case doors can open(welll not doors more folding oportunities:))
:roll: This place is littered with average users. But the point you may have missed is how I defined an average user and the exception(s). Take a minute and reread my posts again.

And for the rest of your post, sorry, Im tired as hell but that makes no sense to me... :confused:

More power consumption boils down to more than energy savings per month. I don't even look at it that way. I think about a smaller power supply, a power supply lasting longer, and a quieter system due to less heat output.

This argument is pointless though, for all we truly know Kepler could use very little energy.
You looked at it that way up top.. now the numbers come out so more reasons come out? Timely... :D

PSU wont last longer with a slightly lesser load, my god man..pass the dutchy this way.

So you are going to go out and buy a lesser PSU? Does that make sense...?

The discussion (not an argument) is relevent.. or it was when you brought up those points... now...... its not? :wtf:
 
Don't expect a "performance" chip to beat AMD's top dog. That will come later with the GK110. I think GK104 will be (at stock clocks) between the 7950 and the 7970.

Well I fully expect that to happen actually. GF114 (aka fully enabled GF104) did match AMD's top dog, Cypress. 40 nm didn't play very well for Nvidia, BUT if everything had gone well, their performance chip GF104 would have matched AMD's fastest, and GF100 would have been 40% faster (like GF110 is).

Most people don't take these things into account, but they are very important, because that's what Nvidia is going to aim for this time around too. Why? Because of the die size, we know they are aiming at the same kind of improvement they tried with GF104 over the previous gen. And we know how that would had played if 40 nm had not become a nightmare for Nvidia. AMD released Barts and Cayman, replacements that were significantly bigger than the chips they were replacing at the time that Nvidia only "fixed" GF100/104, and that's why GF110/GF114 vs Cypress/Juniper is a comparison no one does, but in order to better understand what are the posibilities with Kepler it's very very important to note them, because once again the die sizes are the same. Conditions are pretty much the same, except that 28nm is simply much better.

This time around things are supposed better for Nvidia, and GCN is clearly less efficient (for gaming) than VLIW, so 10% here + 10% here and GK104 could easily end up being significantly faster than HD7970.
 
This place is littered with average users. But the point you may have missed is how I defined an average user and the exception(s). Take a minute and reread my posts again.

And for the rest of your post, sorry, Im tired as hell but that makes no sense to me...

ok , but im not sure what kind of language your typeing their dude , try again

I will,,,,,, if Kepler runs Cooler and cheaper(low performance per watt) i can buy more of them, and the bits to run them, Cheaper grammar tart fag :eek: yeh it was me, i said it:banghead:

People really name their PC? ,er yes, same as i name my car ,but a different name < much better version of a gay dig at someone , just so you know of course

and if something costs the earth, eats too much of ya life, and rapes you of any available cash, ya better call it something ,if not', your wife!.
 
Last edited:
I kinda remember another hype that was going about the 6000 series and how they gonna smoke the hot and power hungry Fermi. Fanboys will always create hype. This time NV is extremely quiet everything you see and hear comes from speculations and fanboys. But rather sooner than later we'll know what's going on.

and they totaly did, when nvidia released fermi i thot it was a total flop, a gtx480 performed like 10-15% better than a hd5870 but consumed like 25% more energy(meaning it was less efficient) what that translates to is that amd with the same 5000series architecture couldve released a card that is 15% more powerful and 15%more power hungry to match a gtx480 and still be 10% better in consumption meaning they had a better architecture(tho fermi smoked amd in compute and GPGPU thats for sure) ;)
i see everyone in this thread neglecting power efficiency but it is actualy everything! not only for the enthusiast side but all across the spectrum, it is what one would look at to see which architecture is superior, a gtx580 is faster than a hd6970 but it also has a bigger die size and higher tdp and requires more power
comparing nvidia and amd in the past has always been like comparing american car engines to european car engines, europe having smaller refined engines(amd), while america replies with its big engines with MOAR POWER(nvidia)
that being said its interesting to see nvidia changing directions with its new kepler chips
 
GTX 580 also beats the 7970 but at 450W TDP

GTX 670 beats the 7970 @ 225W TDP bhutwhutevuh no one listens to little ole Seronx
 
Last edited:
:roll: This place is littered with average users. But the point you may have missed is how I defined an average user and the exception(s). Take a minute and reread my posts again.

And for the rest of your post, sorry, Im tired as hell but that makes no sense to me... :confused:

You looked at it that way up top.. now the numbers come out so more reasons come out? Timely... :D

PSU wont last longer with a slightly lesser load, my god man..pass the dutchy this way.

So you are going to go out and buy a lesser PSU? Does that make sense...?

The discussion (not an argument) is relevent.. or it was when you brought up those points... now...... its not? :wtf:

It seems you are trolling at this point in time.
 
It seems there are lots that are willing to accept rumors as truth and ride AMD and their crap drivers right off the ledge.
 
I find the whole fan boy talk hilarious.

AMD and NV and been one upping each other for how many years now and it will continue aslong as they are making money.

Who really give a fuck who is faster aslong as it plays your games and doesn't break your wallet.

It really sad to have so much invested in a brand and unless you own stock what is the point. They both just want your money....


When I see NV released a product that is reviewed then this will catch my interest until then its all hearsay and utterly USELESS!

Except to have you guys fighting like little girls watching oprah...
 
Unbeatably hyped up. LOL
 
Yup ... I saw this coming a mile away !

nvidia-vs-ati.jpg
 
This happens every year the past 10 years...
For crying out loud, please... :shadedshu

And mister bellerano, ur in trouble mate :D
 
Which is hilarious since the driver support for the 7xxx series is nothing short of terrible. I am willing to wait for an Nvidia solution since I have had it with AMD Drivers BSoDing during installation and failing to properly install unless I take precautions that make it take upwards of an hour to do a driver upgrade. Fermi was rushed, and was using a different design (Kepler is like an evolved Fermi) so most of the problems that presented themselves with Fermi, won't be as big, or even an issue with Kepler. If all goes according to plan at least.
I never had problem with ATI and now AMD drivers. I know nobody that had problems. The only time I remember was back then with the good old 9700 Pro, 9800 Pro and 9800 XT where the 1st driver release were a little buggy, but got resolved quick.

Blast from the Past
ati_vs_nvidia.jpg

ATI_vs_Nvidia_by_masquevale.jpg

ATI-VS-NVIDIA.jpg

b4340e19_vbattach172842.jpeg


:roll:
M5YDu.jpg
 
nshittya will for sure be charging way to much for the news cards when the come out...
Remember the XFX 8800 ultra XXX. here in Australia they were over $1000.
 

Attachments

  • Xzibit_Nvidia-1.jpg
    Xzibit_Nvidia-1.jpg
    57.6 KB · Views: 972
I never had problem with ATI and now AMD drivers. I know nobody that had problems. The only time I remember was back then with the good old 9700 Pro, 9800 Pro and 9800 XT where the 1st driver release were a little buggy, but got resolved quick.

same as mine,

i've got 6 years experience with radeon. and what they had called buggy driver. i've only experienced not much than all the fingers in my hand..

what they faced isnt a buggy driver, but mostly crappy and bad configuration on their hardware ..
 
Hahaha oh wow, you guys! I just got the CRAZIEST idea!

Why don't we all.... Get this. Why don't we all buy what we want to buy and not flame anyone who buys something else?
 
Don't kock it till you see reviews, just because AMD laucnhed barely 3 months ago (without availiability) doesnt mean Nvidia had to... this is all going according to their roadmap remember, have some patience.

IMO given their stance these new cards will perform very well.
 
Don't kock it till you see reviews, just because AMD laucnhed barely 3 months ago (without availiability)

There are tons of 7970 available now. Just need the $$$ to get one. ;) The availability of new-gen GPU is normally scarce on the first month or so especially if they are top-end cards. Mid-ends and lower tend to have lots of availability because they're easier to manufacture and get 'quality pass'.

I agree that we should wait for the reviews before judging Kepler.
 
I agree that we should wait for the reviews before judging Kepler.

How can you "judge" Kepler if you don't know the architecture for Kepler?! It's not like CPU architectures where AMD & Intel go out of their way to say we introduced this and that ISA and we now have an ops cache! I have yet to see a whitepaper of Nvidia Kepler or a die shot of AMD Graphic Core Next.

Also, you would have to wait for reviews anyway because whitepapers aren't always accurate.
 
Last edited:
4 pages of spam generated by a single stupid facebook post... good going tpu.
 
How can you "judge" Kepler if you don't know the architecture for Kepler?! It's not like CPU architectures where AMD & Intel go out of their way to say we introduced this and that ISA and we now have an ops cache! I have yet to see a whitepaper of Nvidia Kepler or a die shot of AMD Graphic Core Next.

Also, you would have to wait for reviews anyway because whitepapers aren't always accurate.

well this isnt about kepler being bad, both nvidia and amd had good products in the past and always been on par. however kepler has to be better than the hd7000 since its coming out almost 4-5 month after. with graphic cards refreshing every 12month that is a huge chunk of time for extra tricks.
but on the long run for some1 like me who usually cant afford the top end it really makes no difference what i buy since competition in the market almost always leads to the cards being priced accordingly.
i guess it all nails down to the features and which architecture you prefer(certain games favor some architectures to other)
 
Luckily GK104 isn't the top end

The top-end for the HPC community doesn't come with GK104.

"This is going to be an exciting year in Oak Ridge as our users take advantage of our new XK6 architecture
and get ready for the new NVIDIA Kepler GPUs in the fall," Wells said. "A lot of work by many people is
beginning to pay off."

GK104 Spring
GK106 Summer
GK112(GK110) Fall

Also, (my) projections:

GK104 Max ASIC Stock Clock: 3,891.2 GFlops/ 3.8 TFlops, $299 ~342 mm²
GK112 Max ASIC Stock Clock: 9,830.4 GFlops/ 9.8 TFlops, $499-599 ~544mm²
2 x GK112 Max ASIC Stock Clock: 15,974.4 GFlops/ 16 TFlops, $899-999 2x ~544mm²
 
GTX 580 also beats the 7970 but at 450W TDP

GTX 670 beats the 7970 @ 225W TDP bhutwhutevuh no one listens to little ole Seronx

Might want to check W1zzard's 7970 review, nope.

Less hate more love for competition!
 
NVidia is far more competent at making powerful GPUs than AMD is at making powerful CPUs...:laugh:

It also helps if you have been in the lead the past two generations already, which AMD wasn't when Bulldozer came out, but nVidia is with Kepler.

Nvidia was not in the lead for years. GTX580 is not a better solution than 6970, it is just bigger and hotter. Ever heard of the sweetspot strategy from AMD? If you want to compare where they are, compare a 6990 and an 590. This is where they have an equal power barrier.
 
It is unbeatable! AMD just keeps on messing up things. First with their 8 core CPU's that cant complete against Sandy Bridge and secondly launch the 7XXX series ahead of Nvidia's Kepler when they know the green team will obliterate them!
 
Back
Top