GTX680 to arrive at the end of February!

[chief barker]

No it's not....i'm trying to read it after getting up from a night shift.

Then go have a coffee/tea/drink or something to eat and wake up before reading?.

Thanks dad....you must be 60 years old as i'm 40.

 

[kitch9]

http://semiaccurate.com/2012/02/01/physics-hardware-makes-keplergk104-fast/

Uh Oh Nvidia fans, Charlies back pedalling.........

 

[zoomee]

http://semiaccurate.com/2012/02/01/physics-hardware-makes-keplergk104-fast/

Uh Oh Nvidia fans, Charlies back pedalling.........

All of the benchmark numbers shown by Nvidia, and later to SemiAccurate, were overwhelmingly positive. How overwhelmingly positive? Far faster than an AMD HD7970/Tahiti for a chip with far less die area and power use, and it blew an overclocked 580GTX out of the water by unbelievable margins. That is why we wrote this article. Before you take that as a backpedal, we still think those numbers are real, the card will achieve that level of performance in the real world on some programs.

The problem for Nvidia is that once you venture outside of that narrow list of tailored programs, performance is likely to fall off a cliff, with peaky performance the likes of which haven’t been seen in a long time. On some games, GK104 will handily trounce a 7970, on others, it will probably lose to a Pitcairn. Does this mean it won’t actually do what is promised? No, it will. Is this a problem? Depends on how far review sites dare to step outside of the ‘recommenced’ list of games to benchmark in the reviewers guide.

Key note here is those 'optimised games'.......

 

[kitch9]

Key note here is those 'optimised games'.......

So now he's basically saying NV are designing a relatively low power gpu (GK104.) with good Physx performance and they intend to bribe devs to nerf AMD by using Physx more .

Lol, now what do we believe?

 

[Freddie1980]

Oh come on now who actually believed Charlie when he said a $299 which had lower power consumption, smaller die size that was going to blow the 7970 out the water? Just apply some common sense to the stories these B.S internet troll sites (Bright side of News, Fudzillia, S.A, nordichardware, Expreview etc) come out with and reality will soon follow.

 

[dave_beast]

Oh come on now who actually believed Charlie when he said a $299 which had lower power consumption, smaller die size that was going to blow the 7970 out the water?

Nvidia shills trying to derp AMD sales, ironically just before the 7950 went on sale.

 

[Stripes]

Oh goodie, so it's going to be the Crysis II Tessellation debacle, only this time spread across multiple "TWIMTBP" titles.

Still, more grist for the news site mill. Reviewers should have a field day too, once their hands are no longer tied by review pack guidelines.

 

[bru]

well that article almost read like certain ocuk members post, as in very long winded .
but seriously did i just read all that only to come to the conclusion that we still have no idea what is gong to happen with Kepler. i mean on one hand the 299 price tag was shills posting garbage and then on the other hand it might not be, on the other hand there is no dedicated physx hardware then on the other hand there is, then the other hand all the companies make deals with developers to include code to help out their hardware, but on the other hand lets have a million words of diatribe slagging off Nvidia's alleged use of such tactics.

the only thing that is certain from that article is that Charlie is feeling better now and things are back to normal.

 

[drunkenmaster]

Oh come on now who actually believed Charlie when he said a $299 which had lower power consumption, smaller die size that was going to blow the 7970 out the water? Just apply some common sense to the stories these B.S internet troll sites (Bright side of News, Fudzillia, S.A, nordichardware, Expreview etc) come out with and reality will soon follow.

Where did he say that exactly? I'd love to see you quote it rather than just make a BS claim of your own.

 

[MichaelM]

Sounded to me like Kepler is going to be unbelievably faster in a physx enabled game but in any other game they will be slower than an AMD equivalent.

Please don't make me reject Kepler on moral reasons. "May the better man win" unless they are found to be cheating and the result is overturned...

 

[pugheaven]

My heads just exploded with some of the discussion above, and I've got a masters in maths rofl!

 

[Mookzen]

Mommy and daddy are fighting again.

 

[Dan2kx]

Summary of rumours in thread so far:
1.)The first Kepler models will be released in either late February,or late March/early April or June 2011
2.)It will be faster than an HD7970,as fast as an HD7970,slightly slower than an HD7970 or slightly faster than an HD7950
3.)It will be priced around the same level as a lower end GTX570 or higher end GTX560TI or priced higher
4.)It will either have additional hardware for PhysX or not
5.)It will have a higher TDP than an HD7950 or a lower one
6.)Nvidia is not worried about GCN or is worried about GCN
7.)The GPU being released first is meant to be smaller than the Tahiti GPU used in the HD7900 series

LOL, looks like i saved my self some time by starting on page 12!!!!

 

[drunkenmaster]

Sounded to me like Kepler is going to be unbelievably faster in a physx enabled game but in any other game they will be slower than an AMD equivalent.

Please don't make me reject Kepler on moral reasons. "May the better man win" unless they are found to be cheating and the result is overturned...

Basically, AMD's reviews suck balls because, the cards ARE 30% + faster, but they've clocked them like **** headed idiots to be under 250W's, they only use 160-165W in average use in gaming ffs

Awesome cards, crap reviews.

Nvidia WILL WIN THE REVIEWS. This is what Charlie is saying, how they win them is an entirely different thing, if only 5-6 phsyx raped benchmarks get shown and Nvidia is paying people off left right and centre to add patches to games for physx...... Nvidia will win the reviews, hands down, and opposite to AMD, real world experience will be apparently WAY worse performance in non physx/patched games and it will barely rival pitcarn.

Fact is, Nvidia will claim the win, and fanboys who love reveling in an underclocked 7970 and the few insane ones who claim its barely faster than a 6970(while multiple people have switched from 6970 xfire to 7970 and had equal/better performance when overclocked say otherwise), will also claim these reviews prove the GK104 is faster in everything.

Of course.... I was horrifically wrong in interpretting Charlie saying(not word for word, i cba'd to look up the post)

in games Nvidia will make Wall street look like Ghandi

to mean he's suggesting Nvidia is going to make the cheating in Batman and Crysis 2 look like nothing compared to this generation. Clearly that isn't what Charlie meant at all and I was soooo wrong assuming this and...... was it blowing my own trumpet.... for interpretting his statement in the way I did.

 

[bhavv]

My I7 980 even at at stock speed plus 512 Gb crucial M4 are overkill, I have no idea what the OP is.

 

[Locky]

long winded tripe and fanboys who love reveling in an underclocked 7970

it's not under clocked, its how AMD designed and built the card, you can't blame that one on anyone else apart from amd

 

[drunkenmaster]

it's not under clocked, its how AMD designed and built the card, you can't blame that one on anyone else apart from amd

That would be true except, they both designed and built a card capable of far higher speeds..... errm, which suggests it was both designed and most definately built for faster speeds.

here's a hint, if it wasn't built to run at 1200Mhz +, it couldn't, it wouldn't have VRM's more than overspecced for such speeds, it wouldn't have a cooler capable of dealing with those speeds, etc. Extra VRM's, or higher spec vrm's and a better cooler than it needs all add's cost, or reduces profit. It is unquestionably built to go faster, suggesting something else is daft.

As for not blaming AMD and the rolleyes, considering I errm... blamed AMD, you can point your eyes elsewhere thanks.

 

[Locky]

No you never, you blamed "the fan boys".

 

[drunkenmaster]

No you never, you blamed "the fan boys".

I've repeatedly blamed AMD since the 7970 launch for the reason they released a lowly clocked card. I in no way blamed the fanboys for AMD's poor review and I've stated AMD screwed up many times.

Talking about the Nvidia fanboys(yes the ones who insist in no situation is the 7970 much faster than the 6970) I in no way came close to blaming them for the reviews. I said the fanboys will both ignore the ultimate speed you can get out of a card "outside" of a review, and also ignore the fact that Nvidia cards are likely to be massively slower outside of reviews. If you can explain where I blamed Nvidia fanboys for the poor reviews, go ahead.

 

[kitch9]

Guys, it only takes common sense to see why AMD (And probably NV.) are being conservative with 28NM clocks, whilst over speccing the VRMs etc.

Supply of 28nm fab time is scarce. Apple want it ALL, and if they could they would have it all just to nerf their competitors so they are aggressively taking as much as they can get.

This will push silicon prices up, so the stuff is precious and cannot be wasted. AMD have set conservative standard clocks to get the extra % yeild, but the good news for us is it appears the clockers can have a field day.

The only problem is the one made up in some of your heads to "prove a point" that's not there to be proven. At the end of the day if someone buys a £400 card but refuses to use all of its available features (AMD overdrive at least.) to improve performance then more fool them.