Kepler Nvidia GeForce GTX 780

[Handrox]

If the GTX 680 is faster than the HD7970 GPU clock with a smaller (~ 200MHz) It's really amazing the power of this chip, smaller, less clock and stronger than the competition .... lol

[boxleitnerb]

How is QDR triple-pumped (6GHz vs. 2 GHz)? I vote fake.

[spicypixel]

Yeah evidently it's 1.5ghz, guess that's ruined another day of speculation.

[Gilgamesh]

Dual GK104 in May:
http://www.techpowerup.com/162275/Du...es-in-May.html

[SubZero.it]

How is QDR triple-pumped (6GHz vs. 2 GHz)? I vote fake.

Yeah in fact.
Guys stop dreaming and wait till NDA lifts.

[flyck]

A few months behind a competitor isn't late. 6+ months is late. We've discussed that fact earlier.

GK104 is only being looked at as high end because NVidia found themselves in a unique position where their midrange gpu was strong enough to beat their oppositions high-end. As such, they can sit and reap major profits and force AMD to show their next card, which will have to deal with the GK110.

You seriously believe Nvidia will choose to be on-par (IF the rumours are true which i don't think so) with AMD when they can easily be on top as well? I mean seriously?

Its better to be described as: they needed their GK104 to compete with the high-end because their own high-end isn't production ready.


specs from wcf are wrong.

[Dimitriman]

You seriously believe Nvidia will choose to be on-par (IF the rumours are true which i don't think so) with AMD when they can easily be on top as well? I mean seriously?

Its better to be described as: they needed their GK104 to compete with the high-end because their own high-end isn't production ready.


specs from wcf are wrong.

You forget Nvidia doesn't think like you or like any 1 person. Nvidia is a company who's major concern is profit and sustaining that profit.
So if they can sell a 300mm2 chip for 550$, and in order to commit their limited resources to a 520mm2 chip they must forego 2x 300mm2 chips (just as example), they will most likely choose the most profitable route first route.

The consumer is not really missing anything as there is head to head competition on all ends. And performance wise, we don't "gain" very much by having an 800$ card in the market you know. Very few bought the 8800 Ultra, as the GTX and GT were clear better choices perf/$.

[RPGWiZaRD]

You seriously believe Nvidia will choose to be on-par (IF the rumours are true which i don't think so) with AMD when they can easily be on top as well? I mean seriously?

Its better to be described as: they needed their GK104 to compete with the high-end because their own high-end isn't production ready.


specs from wcf are wrong.

That's flawed reasoning IMO, I'm much more with DilTech on this one. But then again I think it's rather silly to speak about a product we don't have solid performance numbers on yet haha. However let's say the rumors of GK104 beating HD 7970 in average with a couple of % would be true it doesn't make any sense roll out the highend chip now, why? Think of it from this point of view; provided GK104 is meant to be a midrange/performance chip that may have been initially targeted towards 299~$399 pricepoint range or so and the GK110/100 probably 549~$649 range. Due to AMDs subpar performance and high pricing strategy (squeesh as much cash as possible the months advantage they have strategy) Nvidia noticed GK104 is enough it can make it compete very nicely with AMDs new cards they probably decided to only postpone the highend chip until later when AMD releases its next refresh and this saves Nvidia time & money as they don't have to ramp up another chip (call it for example GK114b or whatever). It buys them time and hazzle with the next generation in mind too, if they can use GK110 as competitor against AMD's next refresh, that's a really big win for Nvidia if true.

Besides that you have to remember GK104 doesn't seem to be a very big chip at all, actually from Nvidia's point of view a very impressive size from size/performance point of view, it's not a big & power hungry chip that shouldn't be too expensive to manufacture so if they purposedly leave out the big chip now, they can instead jack up the prices of the what was meant to be the "performance" chip and that means A BIG profit increase per chip. If they'd also release the big chip now they'd potentially both sell less GK104 chips but also the pricings would have to be adjusted somewhat as Nvidia has learnt by now customers doesn't accept much above $649 for a single highend GPU card, not in this day and age at least so the GK104 would also then have to be adjusted somewhat lower, say $449 instead of $549. There's a lot of cash to be made out of a ~300mm^2 chip if it can both COMPETE in performance and SELL nicely at a pricepoint of $500+ xD

So speaking from maximum profitable business strategy Nvidia is certainly playing the cards right if they are delaying the highend chip and competiting GK104 with HD79xx even if it's about a draw, that would be a big victory already for Nvidia under these circumstances. These circumstances are very rare sight in these businesses (midrange/performance offering can compete with highend offering) and I bet the green camp is feeling quite confident at the moment.

Of course for us customers we had heavily benefitted from the highend chip being released at the same time, it had meant AMD had to lower the prices a lot more significantly and Nvidia's pricings also would stay lower especially for GK104, by the looks of it Nvidia might get away selling GK104 for a high price and making a lot of profit out of it without AMD having to cut prices significantly either => bad for us customers but insanely good scenario from Nvidia's point of view.

[Pantsu]

I don't see any reason or logic in delaying products in GPU business. There's always people who are willing to pay more for more performance, and the best time-to-market is as soon as possible, otherwise you're just letting the competition catch up. By now it seems fairly obvious that GK100 was cancelled early on and they need to take their time with GK110. The release time frames are getting too far apart between AMD and Nvidia, so comparing gen vs. gen is useless, you can only look at what's available on the market at a given time. So far AMD has had a quarter of sales whereas Nvidia simply hasn't shown up to the fight. I'd say AMD's strategy of showing up in time has worked quite well. It doesn't matter if Nvidia will end with the faster card since by the time they get their chips out in meaningful quantities, AMD is already preparing for the next gen.

[FedericoUY]

Nvidia is a company who's major concern is profit and sustaining that profit.

Every hardware company's major concern are profits (they live for it), then they think in the rest of the stuff. They would not live if they don't have it as primary goal.

[Dimitriman]

Every hardware company's major concern are profits (they live for it), then they think in the rest of the stuff. They would not live if they don't have it as primary goal.

If it is so obvious I wonder why people still claim that they will make decisions that will go against this principle. Scarce resource allocation is not that hard to comprehend. And until 28nm really ramps up well, there isn't any clear reason to rush out the bigger chip if the smaller will sell at the same price point one would previously expect the 500+mm chip to sell for.

[hyperdoggy]

While i have the up most respect for the engineers at Nvidia(AMD for that matter) and i have no doubt that their next part is going to live up to its performance claims, my hats comes off to its marketing team. Not only its buyers is convinced that a non-existing product is far better than its competitors. Never mind that the product is coming 3 months after their competitors, rumored to be 5, or the fact that is only their "mid-range" part with its high-end product at the at the end of 3rd quarter, but the customers themselves find ways to justify its profit milking by the company.

By that logic my 580 must of been a steal since it was a massive chip....

Green camp is starting to sound like a certain fruit vendor user base, it makes me hang my head in shame.

[Dimitriman]

While i have the up most respect for the engineers at Nvidia(AMD for that matter) and i have no doubt that their next part is going to live up to its performance claims, my hats comes off to its marketing team. Not only its buyers is convinced that a non-existing product is far better than its competitors. Never mind that the product is coming 3 months after their competitors, rumored to be 5, or the fact that is only their "mid-range" part with its high-end product at the at the end of 3rd quarter, but the customers themselves find ways to justify its profit milking by the company.

By that logic my 580 must of been a steal since it was a massive chip....

Green camp is starting to sound like a certain fruit vendor user base, it makes me hang my head in shame.

If you are referring to this page of the thread then I think you are confusing an economics/business strategy analysis with fanboyism. People CAN make a discussion based on what they believe each company should or will be doing. But nobody is going to be thanking NVidia for selling GK104 at $550.

As for performance estimates, this is a general forum discussion based on rumoured performance of Kepler, if we didn't discuss based on rumours, there would be no thread at all.

[hyperdoggy]

If you are referring to this page of the thread then I think you are confusing an economics/business strategy analysis with fanboyism. People CAN make a discussion based on what they believe each company should or will be doing. But nobody is going to be thanking NVidia for selling GK104 at $550.

As for performance estimates, this is a general forum discussion based on rumoured performance of Kepler, if we didn't discuss based on rumours, there would be no thread at all.

So you're telling me you don't sense even a hint of fanboyism mixed in this page of the thread? i guess is just me then. I apologize.

[Vardant]

If you are referring to this page of the thread then I think you are confusing an economics/business strategy analysis with fanboyism. People CAN make a discussion based on what they believe each company should or will be doing. But nobody is going to be thanking NVidia for selling GK104 at $550.

Nor should you or anyone else for that matter.

But if somebody wants to really blame NV for this, then they might as well blame AMD.

[RPGWiZaRD]

I don't see any reason or logic in delaying products in GPU business. There's always people who are willing to pay more for more performance, and the best time-to-market is as soon as possible, otherwise you're just letting the competition catch up. By now it seems fairly obvious that GK100 was cancelled early on and they need to take their time with GK110. The release time frames are getting too far apart between AMD and Nvidia, so comparing gen vs. gen is useless, you can only look at what's available on the market at a given time. So far AMD has had a quarter of sales whereas Nvidia simply hasn't shown up to the fight. I'd say AMD's strategy of showing up in time has worked quite well. It doesn't matter if Nvidia will end with the faster card since by the time they get their chips out in meaningful quantities, AMD is already preparing for the next gen.

What about R&D costs/time/energy company would have to put into a revamped Kepler refresh to combat ATIs next refresh instead of saving current Kepler highend part for that? Ramping up production of a different chip isn't that "simple". About being first to launch a product has positive but also negative sides, since Nvidia launches this much later they've had at least some time on their hand to adjust clock speeds to perfectly compete with the competitor, if it would be just a month or two beforehand the time would be limited now Nvidia have had at least some time to do some final touches (internal design decisions and such would be already decided by this time though so no time to do any drastic changes at that point).

The best time to bring up highend Kepler part would be like 2 weeks ~ a month before AMD launches its next refresh.

I'm just trying to look from Nvidia's point of view and to me it's clear why they'd decide to delay highend part Kepler and jack up prices of GK104 as much as possible at this point, you have to constantly see into the future making decisions today.

[Snow Crash]

If these really do turn out to be killer GPGPU cores I can't wait to see what it can do on the Help Conquer Cancer project on WCG. If the world thought XS was leading in CPU crunching I think their jaws are gonna drop when we get the GPUs fired up :-)
http://www.xtremesystems.org/forums/...-march-13-2012

[phantomferrari]

so any news on the "high end" kepler? the non dual one?

[Pantsu]

What about R&D costs/time/energy company would have to put into a revamped Kepler refresh to combat ATIs next refresh instead of saving current Kepler highend part for that? Ramping up production of a different chip isn't that "simple". About being first to launch a product has positive but also negative sides, since Nvidia launches this much later they've had at least some time on their hand to adjust clock speeds to perfectly compete with the competitor, if it would be just a month or two beforehand the time would be limited now Nvidia have had at least some time to do some final touches (internal design decisions and such would be already decided by this time though so no time to do any drastic changes at that point).

The best time to bring up highend Kepler part would be like 2 weeks ~ a month before AMD launches its next refresh.

I'm just trying to look from Nvidia's point of view and to me it's clear why they'd decide to delay highend part Kepler and jack up prices of GK104 as much as possible at this point, you have to constantly see into the future making decisions today.

There's no need to "save it for later", it can compete against AMD next gen just as well then regardless of when it was originally launched. There's only so much polish you can do for GPUs, and the benefit of having the knowledge of competitor's released cards and the current market situation is IMO insignificant compared to being the one selling the cards. Prices can be adjusted post release, but you can't make a chip go any faster, or if you can, you were doing something wrong before. If GK110 launches in September by that time it's more likely that the prices have already gone down and there's plenty of room for yet another Ultra enthusiast card. I certainly see it as far more advantageous proposition than waiting until AMD comes up with something similar. And when they do, Nvidia would have the edge in production quantities and can easily adjust the price accordingly.

[Piledriver]

Basically what we have here is the new feel good Nvidia gimmick...

After the single GPU nonsense, i present you the "midrange" nonsense.

Let me give examples on how to use this gimmick:

"Hey guys food for thought, Bulldozer is the midrange, Piledriver is going to be the high end!!, so Bulldozer it's not so bad after all"
"hey guys food for thought, the 7xxx series of Southern Islands are the lowend, the midrange and highend are coming end of the year!!!, Basically AMD just needed his lowend to fight NVIDIA's late "midrange, how about that, what a spectacular cad 7970 is! One of the best ever"

Of course this level of idiocy had to be coming from the woodscrew green team. Where Dual gpu's now come before the "high end".


Food for thought, how about calling it what it is? The BEST thing Nvidia can put for sale 3 months AFTER the competition. How about some sanity?


Nvidia doesn't put for sale anything better, because doesn't need to...
So basically Fermi was late because Nvidia didn't need to, and cores had to be taken away so that Nvidia was able to put something on sale, because Nvidia didn't need to, right?

[Vardant]

Does it really matter, if they can put something better on the market, if this card can compete and probably win in most cases against AMD? The MSRP hasn't been set in stone, yet.

[SimBy]

Basically what we have here is the new feel good Nvidia gimmick...

After the single GPU nonsense, i present you the "midrange" nonsense.

Let me give examples on how to use this gimmick:

"Hey guys food for thought, Bulldozer is the midrange, Piledriver is going to be the high end!!, so Bulldozer it's not so bad after all"
"hey guys food for thought, the 7xxx series of Southern Islands are the lowend, the midrange and highend are coming end of the year!!!, Basically AMD just needed his lowend to fight NVIDIA's late "midrange, how about that, what a spectacular cad 7970 is! One of the best ever"

Of course this level of idiocy had to be coming from the woodscrew green team. Where Dual gpu's now come before the "high end".


Food for thought, how about calling it what it is? The BEST thing Nvidia can put for sale 3 months AFTER the competition. How about some sanity?


Nvidia doesn't put for sale anything better, because doesn't need to...
So basically Fermi was late because Nvidia didn't need to, and cores had to be taken away so that Nvidia was able to put something on sale, because Nvidia didn't need to, right?

I could not have said it better myself so I'm just quoting for the heck of it

[WeaponX]

If the current Trend is to overpriced cards in upwards for 500+ for top cards, I think my bleeding edge days are over, this is just ridiculas now...

[kaktus1907]

http://forum.beyond3d.com/showpost.p...postcount=2489

[Callsign_Vega]

2GB is epic fail. I use more than that on a single monitor with high res texture packs in many games. Forget about Surround users. Hopefully they come out with 4GB versions.