There is something else that worries me. Nvidia put all attention at ray tracking . While real world performance wasn't a topic at all , no tflops numbers , no game comparison numbers . If performance increase would be big , don't you all think they would share that with us , for example during Pascal debut they disclosed that numbers . That makes me worried that performance increase wouldn't be spectacular , and if you consider a price to performance ratio it's going to be dissipointment at least that's my opinion , considering that Pascal is almost 3 years old architecture .

Yeap! I have seen them all... the date the top consumer GPU is more than 3X the price of the top consumer CPU (2700X)!

OK, I'll get one... but...
Hey NV... how much my arm traded for?

Back to post:
Seriously, is this some kind of papers launch? It's nothing more than bells and whistles.. choo... chooo...

Liviu CojocaruI understand your point of view in regards to this, but I would not agree with the fact that we should just swallow these and don't complain about it...as far as we know now nothing has been proven we don't really have any statistics to show that this is a fair price for this technology. Imo the "revolutionary" changes are not that important for the gaming industry...rays and shadows are often ignored by the average gamer and also cut down in the game settings so to ask for that price when you haven't actually proven the performance increase in FPS (what actually matters in games) since the last gen it's a bit too much even by today standards. So yes I think people should moan and argue about this as it may change somebody mind about blindly pre-ordering stuff. I was going to pre-order if I had compelling data to justify it...but excuse me, nVidia is feeding us some bullsh*t right now and I think this needs to be stopped one way or another :)

I've posted above: the silicon is huge, that is always expensive.

The real puzzler for me it that one week ago we got out Threadripper2 review (another large die, albeit made up of smaller ones) and when its price was listed as a con, many people argued that was unfair, because the price needs to be read "in a context" or that considering its use case, the price is ok. This week, pretty much the same people tell me otherwise.

Also, you seem to have absolutely no handle on ray tracing.

Whenever nvidia release a so-called new techonolgy/segment, that means there would be a price increase

and all of these techonolgy/cards where already available things but nvidia just renamed them. Cuda is a marketing name of gpu shaders. Titan was the best single gpu that was priced for 650$ at most. Gsync is simpley adaptive sync. so the rtx/ray tracing thing is just another lie in this series of lies.

This isn't a Quadro, don't put Quadro prices on it.

bugI've posted above: the silicon is huge, that is always expensive.

The real puzzler for me it that one week ago we got out Threadripper2 review (another large die, albeit made up of smaller ones) and when its price was listed as a con, many people argued that was unfair, because the price needs to be read "in a context" or that considering its use case, the price is ok. This week, pretty much the same people tell me otherwise.

Also, you seem to have absolutely no handle on ray tracing.

Again you are missing a point . Threadripper 2 is for prosumers . If that prices were for quadro lineup , or for prosumers i would be alright with that , but for god's sake these are gaming chips . Isn't that sick , I understand that the chip is big , but Thale into account that 12 nm is basically improved 16 mm finfet , so there aren't many defective wafers , and price for mm2 is much lower than while 16 mm debuted . Besides there is 7 nm taping out soon ,so I would call 12 nm outdated . 10 mm is already almost for a year in phones soc . I am not saying it wouldn't be good cards but I think it's overpriced piece of tech , almost like being robbed by Nvidia , since there is no real real competition Nvidia is being to greedy

bugI've posted above: the silicon is huge, that is always expensive.

The real puzzler for me it that one week ago we got out Threadripper2 review (another large die, albeit made up of smaller ones) and when its price was listed as a con, many people argued that was unfair, because the price needs to be read "in a context" or that considering its use case, the price is ok. This week, pretty much the same people tell me otherwise.

Also, you seem to have absolutely no handle on ray tracing.

I've seen the live conference when it was presented, have you seen anything else? Do you actually have any other data to judge this on...if yes please let me know, I might be wrong...I've seen lots of people including famous IT youtubers being reserved and reluctant on these as we should be given the few info that we've been given...you can call it revolutionary man but others have opinions as well and this is a forum which it's made exactly for that...

SomethingnewAgain you are missing a point . Threadripper 2 is for prosumers . If that prices were for quadro lineup , or for prosumers i would be alright with that , but for god's sake these are gaming chips . Isn't that sick , I understand that the chip is big , but Thale into account that 12 nm is basically improved 16 mm finfet , so there aren't many defective wafers , and price for mm2 is much lower than while 16 mm debuted . Besides there is 7 nm taping out soon ,so I would call 12 nm outdated . 10 mm is already almost for a year in phones soc . I am not saying it wouldn't be good cards but I think it's overpriced piece of tech , almost like being robbed by Nvidia , since there is no real real competition Nvidia is being to greedy

There aren't many defective wafers? You have a lot of catching up with how chips are made, grasshopper.

Out of curiousity . So you think these prices are alright ? I think they are just riddicoulus , Nvidia is taking advantage of no real competition and try to milk all of us . Unfortunately money are not growing on the trees. Almost 3 years of waiting and for flagship card the SEP price is almost 50 percent higher . The same amount of memory , outdated process , and even if the price increase would be in 40 percent range comparing gtx 1080 to to etc 2080 ti , then still we would end up paying more per frame after that long of a wait . Isn't there something wrong with that. Then if the next flagship card would be 50 percent faster then it would cost 1500 $ .

Liviu CojocaruI've seen the live conference when it was presented, have you seen anything else? Do you actually have any other data to judge this on...if yes please let me know, I might be wrong...I've seen lots of people including famous IT youtubers being reserved and reluctant on these as we should be given the few info that we've been given...you can call it revolutionary man but others have opinions as well and this is a forum which it's made exactly for that...

Not sure what data you need. The die size is right in the presentation.
Anyone serious about graphics drools over ray tracing to the point they build server farms to do it. Probably this generation of hardware will not be great at ray tracing, but neither was the first Voodoo graphics accelerator (it wasn't even a video card) for 3D as we know it today.

In a nutshell, we get a feature that's the Holy Grail of lighting in an implementation that requires a ton of transistors and is therefore expensive. Nobody forces you to buy it, but would you rather not have it at all?
And to turn things around a little: if this catches on and AMD isn't on board, Polaris and Vega will start looking like really good days for their graphics division.

SomethingnewOut of curiousity . So you think these prices are alright ? I think they are just riddicoulus , Nvidia is taking advantage of no real competition and try to milk all of us . Unfortunately money are not growing on the trees. Almost 3 years of waiting and for flagship card the SEP price is almost 50 percent higher . The same amount of memory , outdated process , and even if the price increase would be in 40 percent range comparing gtx 1080 to to etc 2080 ti , then still we would end up paying more per frame after that long of a wait . Isn't there something wrong with that. Then if the next flagship card would be 50 percent faster then it would cost 1500 $ .

I don't think any price over $300 is alright, I don't buy above that limit.
I'm just saying, big silicon is expensive and this silicon is really big. So this may not be entirely taking advantage of AMD's no-show, it could be at least partially justified. There are huge prices, but me moaning about them won't magically lower them.

Just to the point . We are paying for possible tech that could be used in future . While they aren't disclosed performance in games during presentation . Isn't that sketchy ? Considering that price increase , I don't know how anybody can defend that riddicoulus price increase , unless they are working for Nvidia or are shareholders . Gtx 980 to gtx 1080 . Check price increase then , it was small and performance increase was big , not to mention double the memory size . So why this time it's so big ? Simple answer is that Nvidia is abusing leading position .

Simple answer is don't buy new cards for that riddicoulus price unless you don't have to. Just buy older generation , soon there will be 7 nm taping out . Just vote as consumer.

bugNot sure what data you need. The die size is right in the presentation.
Anyone serious about graphics drools over ray tracing to the point they build server farms to do it. Probably this generation of hardware will not be great at ray tracing, but neither was the first Voodoo graphics accelerator (it wasn't even a video card) for 3D as we know it today.

In a nutshell, we get a feature that's the Holy Grail of lighting in an implementation that requires a ton of transistors and is therefore expensive. Nobody forces you to buy it, but would you rather not have it at all?
And to turn things around a little: if this catches on and AMD isn't on board, Polaris and Vega will start looking like really good days for their graphics division.


I don't think any price over $300 is alright, I don't buy above that limit.
I'm just saying, big silicon is expensive and this silicon is really big. So this may not be entirely taking advantage of AMD's no-show, it could be at least partially justified. There are huge prices, but me moaning about them won't magically lower them.

I understand that new tech comes with a price...but you're probably too excited as it is so obvious that there was not enough shown to justify this at this point in time...a few videos which ,for me and others, are purely not enough. Maybe your favourite thing in a game is light and shadows but I don't think the majority of gamers are thinking like you...if you could get your hands on the production cost of one unit and show it to me I would agree...but for now I see the same tactic that Apple uses. I totally agree that the lack of competition helps but this is quite bad for consumers and I think we should not just accept it easily

Since when is the truth (these prices are bad at worst, questionable at best) moaning? Beating a dead horse at this point and all that but at least it's not speculation about the cost increase due to die size or whatever else when we don't know how that affects cost. Plus the regular gaming performance of these things is unknown and RT performance looks bad. If the 2080ti struggles with RT on in Tomb Raider how badly are the 2080 and 2070 going to perform, under 30FPS and <20FPS respectively?

Prince ValiantSince when is the truth (these prices are bad at worst, questionable at best) moaning? Beating a dead horse at this point and all that but at least it's not speculation about the cost increase due to die size or whatever else when we don't know the regular gaming performance of these things and RT performance looks bad. If the 2080ti struggles with RT on in Tomb Raider how badly are the 2080 and 2070 going to perform, < 30FPS and <20FPS respectively?

That is not the final thing, see here:wccftech.com/tomb-raider-nvidia-rtx-gamescom-demo/

I agree that we need way more than these to accept that price.

Yep, not touching Turing at those prices, NVidia can keep 'em. I'll hang on to my 1080Ti cards for a while longer. Thing is, $ isn't even the issue for me. I'm appreciative to be in the bracket of gamers that are not limited by $, but there is such a thing as greed and price gouging that becomes out of control and to me, that's what this feels like, so I'm not biting on these.

I’m not arguing for or against. Technically against since I’m upgrading a gen behind to 1080 Ti.

Yes, the prices are expensive. But I would like everyone to stop and take a few minutes. Why are they high? Sure, some can be blamed on lack of decent high end competition. However:

Has anyone considered the cost of 10 years of R & D? Does anyone know the cost of fabricating this large die? Does anyone know what it costs to produce this card compared to previous generations?

These are all factors which go into pricing. Pricing is not made up in a vacuum. Until you know these things, or are willing to take them into account, then complaining is just that: complaining.

The goal of any manufacturer is to sell their product. Price it too high and your inventory doesn’t sell. The market will determine if these are priced too high to sell all the stock. If it’s too high, they and AIB’s will adjust.

I personally have found it too high, and have opted for Pascal. Thanks for reading! :)

Everybody just check financial report from nvidia , then you will know when all that money that they would take from us will go , higher margin , more profit . No competition , equals much higher margins

rtwjunkieI’m not arguing for or against. Technically against since I’m upgrading a gen behind to 1080 Ti.

Yes, the prices are expensive. But I would like everyone to stop and take a few minutes. Why are they high? Sure, some can be blamed on lack of decent high end competition. However:

Has anyone considered the cost of 10 years of R & D? Does anyone know the cost of fabricating this large die? Does anyone know what it costs to produce this card compared to previous generations?

These are all factors which go into pricing. Pricing is not made up in a vacuum. Until you know these things, or are willing to take them into account, then complaining is just that: complaining.

The goal of any manufacturer is to sell their product. Price it too high and your inventory doesn’t sell. The market will determine if these are priced too high to sell all the stock. If it’s too high, they and AIB’s will adjust.

I personally have found it too high, and have opted for Pascal. Thanks for reading! :)

I incline to agree but to convince me that the prices are this high mostly because of the price of the technological evolution I need some numbers some compelling evidence...anyone can make that affirmation but do you have the behind the curtain information...I don't think so. AMD for one demonstrated that you can achieve great performance for a lower price (including lots of PCI-e lanes) with the Threadripper so we've seen this tactic with so many companies that have an advantage over the competition

Liviu Cojocaruanyone can make that affirmation but do you have the behind the curtain information...I don't think so

You’re right, I don’t have that info. That’s why I posed that before people get out the pitchforks, they know that info. Only with it can someone really complain they are being ripped off. Or it may absolve NV of any of those claims. Who knows? But to be an informed dissenter, one must first be informed...have information.

rtwjunkieYou’re right, I don’t have that info. That’s why I posed that before people get out the pitchforks, they know that info. Only with it can someone really complain they are being ripped off. Or it may absolve NV of any of those claims. Who knows? But to be an informed dissenter, one must first be informed...have information.

I agree, in this case though with such an achievement I would've expect nVidia to show more but I think that for marketing reasons they did not...I am not gonna insist with this anymore...I really appreciate your decision to not buy this gen but I don't agree that if the price is too high the product won't sell...if people are manupulated just enough to think that the price is correct then...but then again that is on them. I wish people can educate themselfs to make a better purchase that's all :)

This thread..

GoldenXMan, so many Nvidia shills defending stupid pricing.

A few people arguing against a mass. Conclusion = so many shills. Seems about right. /sarcasm

GoldenXThis isn't a Quadro, don't put Quadro prices on it.

1200$ is entry level Quadro price. High end Quadro goes for 10000$. Compared to that 2080Ti OK.

Somethingnew12 nm is basically improved 16 mm finfet , so there aren't many defective wafers , and price for mm2 is much lower than while 16 mm debuted . Besides there is 7 nm taping out soon ,so I would call 12 nm outdated . 10 mm is already almost for a year in phones soc .

The bigger the die size the less dies can be manufactured on a single wafer. A single defect an ruin a big chunk of the wafer. This for example is why Intel's HEDT chips are so damn expensive too compared to small AMD ones. Also GPU's are one of the most complex thing to produce on any given node. Much less on a cutting edge 7nm which is OK for small low power mobile SoC's at this time but not yet viable for mass producing a 18+ billion behemoth. Next year - probably.

TU102 appears to be about 32mm x 25mm in size. Thus we can calculate how many dies can a industry standard 300mm (12inch) wafer fit. Given a defect rate of only 0,05 which is impossible for chip this size that would amount to:

Max dies per wafer (without defect): 58
Good dies: 39
Defective dies: 19
Partial dies: 8
Yield: ~68%

^ This is the absolute best case scenario. Ever.

More realistically we are looking at a defect rate of 0.15 which would give drastically worse numbers:

Max dies per wafer (without defect): 58
Good dies: 20
Defective dies: 38
Partial dies: 8
Yield: ~34%

Calculator: caly-technologies.com/en/die-yield-calculator/

Assuming each wafer costs about 25000$ (it can't be much lower because Quadro RTX 8000 goes for 10000$ by itself so wafer is at least 2x more costly).

25000/20=1250$ well surprise surprise. If we get 20 good dies on 25000$ wafer the price is exactly what it is now for 2080Ti. But while the chip itself may the biggest cost per card there are other components costs that make up the BoM (Bill of Materials).

OK so assuming best case scenario 25000/39= 641$ + other components = retail price.

So already due to the manufacturing cost of the die itself it is almost as expensive as a 1080Ti MSRP of 699$.
Still think Nvidia are robbing us?

Yeah you probably do. Facts are never an obstacle for a crowd with pitchforks screaming bloody murder.

TomorrowA few people arguing against a mass. Conclusion = so many shills. Seems about right. /sarcasm

1200$ is entry level Quadro price. High end Quadro goes for 10000$. Compared to that 2080Ti OK.

The bigger the die size the less dies can be manufactured on a single wafer. A single defect an ruin a big chunk of the wafer. This for example is why Intel's HEDT chips are so damn expensive too compared to small AMD ones. Also GPU's are one of the most complex thing to produce on any given node. Much less on a cutting edge 7nm which is OK for small low power mobile SoC's at this time but not yet viable for mass producing a 18+ billion behemoth. Next year - probably.

TU102 appears to be about 32mm x 25mm in size. Thus we can calculate how many dies can a industry standard 300mm (12inch) wafer fit. Given a defect rate of only 0,05 which is impossible for chip this size that would amount to:

Max dies per wafer (without defect): 58
Good dies: 39
Defective dies: 19
Partial dies: 8
Yield: ~68%

^ This is the absolute best case scenario. Ever.

More realistically we are looking at a defect rate of 0.15 which would give drastically worse numbers:

Max dies per wafer (without defect): 58
Good dies: 20
Defective dies: 38
Partial dies: 8
Yield: ~34%

Calculator: caly-technologies.com/en/die-yield-calculator/

Assuming each wafer costs about 25000$ (it can't be much lower because Quadro RTX 8000 goes for 10000$ by itself so wafer is at least 2x more costly).

25000/20=1250$ well surprise surprise. If we get 20 good dies on 25000$ wafer the price is exactly what it is now for 2080Ti. But while the chip itself may the biggest cost per card there are other components costs that make up the BoM (Bill of Materials).

OK so assuming best case scenario 25000/39= 641$ + other components = retail price.

So already due to the manufacturing cost of the die itself it is almost as expensive as a 1080Ti MSRP of 699$.
Still think Nvidia are robbing us?

Yeah you probably do. Facts are never an obstacle for a crowd with pitchforks screaming bloody murder.

Did I hit a nerve?
We want lower prices, no excuses.

Liviu CojocaruLooking at your situation...that is exactly what you do ;)

WTF? What situation? When did I complain? Are you completely incapable of following a conversation?

bugWTF? What situation? When did I complain? Are you completely incapable of following a conversation?

Nope, it's you, you're incapable of accepting others opinion ;) ... I did not reply first you did to me...as you do with I think most of the people on this forum...you feel the need for attention and reassurance that your opinion is the best, like you have all the answers and most important all the facts. You did not counter my opinion with hard facts...just assumptions...I said that the price is really high (as everyone says) and that nVidia did not show a lot to justify this...do you want me to go further?