Neliz, you really think we won't see Kepler until April ?
Printable View
Neliz, you really think we won't see Kepler until April ?
I have seen nothing that indicates otherwiseQuote:
Originally Posted by Olivon
When Matose says that plan is now for february, you don't believe him ?
I believe that one vendor (not MSI! :p) showed him a roadmap that is either heavily out-dated or wrong on purpose (to catch leakers.)Quote:
Originally Posted by Olivon
Again, these things take time (doing the boxes etc.) people would've noticed if that was going on and the chinese factory workers would've start sneaking off pictures.
If you want to launch early February, you need to beat Chinese new-year's holidays (which start Saturday) and this would have you shipped everything this week. if you want to ship after Chinese new-year, you're looking at a good two weeks before production actually ramps up to normal speed again
Nearly what i was think, you cant start production in manufacturers ( and most worldwide, build for both brand ), transport the cards, and keeping it completely secrets. You can do it, if you made your product in your fabric, and nobody then will see them before they are send in the retailers chanell. (intel ) .
Yes we'll probably see more leaks soon as AIBs get their cards. In general this has been quiet compared to past launches though. We know GK107 is ready. GK104 is probably done and the big boy has most likely taped out too. Yet not a peep recently about tape out dates, yields or die sizes from the usual suspects. The fact that Charlie hasn't written his "Kepler is slow, broken, power hungry and unfixable" article yet is good enough for me. Either there's no bad news for him to report or his moles got squished.
Besides Fuad, I haven't seen anyone regularly name the correct product names anyway.
the real shocker is when you learn there is no GK104 at all..Quote:
Originally Posted by Olivon
Don't steal my cloud tags! :p
haha sorry I could not resist anymore :DQuote:
Originally Posted by neliz
http://www.guru3d.com/news/amd-radeo...-in-two-weeks/
The article is about 7950 launch ( still fixed on 31st jan as allready mentionned ), but at same time it give some input about Kepler..... so intox or not.. oh well.
( GK100 ) abandonned ? , GK104 ( GTX 680) > 2x GK 104 = GK110 ? GK 110 > GK 112? = Kepler GTX 780 - Q4 2012 ? Damn the Nvidia's marketing teams should have a nice headache if half true.Quote:
By Hilbert Hagedoorn, January 17, 2012 - 10:32 PM N/A
"" ..... The sources noted that Nvidia wishes to make sure that the power consumption and the manufacturing process of the graphics chip all reach perfection before entering the 28nm generation. Since Nvidia is set to release its 28nm graphics card around the same time as Intel's upcoming 22nm Ivy Bridge processor, the sources believe Kepler series GPUs may have a chance to catch up with the demand for Intel's new CPUs.
Nvidia is set to release several 28nm Kepler-based GPUs including GK104, which will replace the existing GeForce GTX 560Ti; GK107, targeting the entry-level PC market; GK106, targeting the mid-range to entry-level market; GK110, which is equipped with two GK104 GPUs; and the highest-end GK112, which may be released in the fourth quarter or 2013.
I still cannot believe nVIDIA would call GK110 to a Dual GK104 card. Makes no sense. They give the name GK1xx to chips, not SKUs.Quote:
Originally Posted by Lanek
I dont say it make sense, untill they have cancelled the GK100 ... ( remember all rumors was speak about GK104-110, 107, 106 ) we have never seen anything about GK100.Quote:
Originally Posted by Picao84
dont tap the messenger, i report the article thats all. :D
Well for be honest, it is a nice marketing tricks: - you give a known info about 7950 launch, give a lot of strange and contradictory "infos" about the competitors, and if you look well, nobody will speak about the 7950 launch, and only about Kepler... booouh, marketing at his best.
I will be really happy to know the source.
My head hurts every time I see GK104 and GK110=2xGK104.
lol.....
There may not be a GK100 (or GK102) at all. Just like there was no GF109 (as far as I am aware…).Quote:
Originally Posted by Lanek
to me, that this strange rumor exists at ALL means there is probably something to it.Quote:
Originally Posted by neliz
my first guess is that the first generation of kepler has had such problems that nvidia dropped the highest end geforce+tesla chip. GF104/GF114 was so successful compared to the high end that this could be a fine idea. then they bring the big chip back with the first redesign/respin of kepler many months later (that rumored Q4 date above). so I can see the possibility of no giant nvidia chip for up to 12 months.
It is the possibility i was open, not cause terrible problems, but cause they need maybe time to work on it, or just the 28nm process mature ( remember too the rumor about different process used ( charlie ) between Nvidia and AMD for top end ) they dont want experience again the Fermi 480 launch ( delayed and not under the best mood ). it is maybe more valuable to drop GK100, push the GK104 to GTX680 lineup.
lets imagine the GK100 will not come before 6 months, and they had plan a Kepler refresh for the end of 2012 ( the called 110-112), the question if both launch / production are too close, it is maybe better to drop the first and jump on the second, whatever they lost 3 months. Nvidia release the GTX680 with GK104SKU, and hope can push the top end with 2x GK104 dual core cards. ( similar of what AMD have done by the past with the 4870 and 4870x2 )
But all of this are pure speculation, lets not kill our day with that. This look a little bit as a bad joke, so i tend to believe this is not the case.
Why will you get a GF109?, in general for nvidia the top sku is a round numbers: GF100 ( GTX480/470 Fermi gen1), then the lineup is declined from top to low, with last numbers indicate the position in this line up: 104 (460) > 106 ( 450)> 108 (430).Quote:
Originally Posted by iMacmatician
If we look the GK110 numbers, this one should be on the next line up.. the refresh.
Just because a rumor exist means nothing or have you seen the XDR2 Tahitis yet?;)Quote:
Originally Posted by bamtan2
So much different stuff floating around at the moment, i hope after 7950 Launch we'll see some facts. A architecture presentation a few days later wouldn't surprise me.
No GK104 doesn't mean no big chips. Forget the leaked roadmaps.Quote:
Originally Posted by bamtan2
first page updated. thx
My point is that we can see a GT/GF/GK11x without a corresponding GT/GF/GK10x beforehand. My "GF109" example was because there was a GF119 without there being a GF109 before that (from my knowledge). Thus, we can see a GK112 without there ever being a GK102.Quote:
Originally Posted by Lanek
More generally, the lineup of third digits in a G*10x lineup may be different from the lineup of third digits in a G*11x lineup.
that was a retarded rumor, not a strange one.Quote:
Originally Posted by AffenJack
you mean no GK100? I didn't say none. I said the delay could be up to 12 months from now, which could be 8 months after GK104, which is not unusual because if wikipedia is right then GF104 came 3-4 months after GF100, and GF110 came 5 months after that. if they killed the big chip for this generation, then the next big chip for the next generation could be ready in under 12 months from now, as I said.Quote:
Originally Posted by neliz
nvidia just lived through GTX 480. I do not think it was a big financial success. the august dx11 steam survey shows GF100 480+470 at 7.18% and cypress 5870+5850 at 18.7%. and the cypress cards are older, so more of them have been replaced. and the nvidia cards cost more to make. and they used so much power there is no way they made a dent in the computing market. you could say there are fewer GF100 out there because cypress was on sale for longer. that is true, because nvidia killed GF100 as quickly as possible.
if nvidia thought the first big kepler would suck that much, they could have killed it already. I do not find this an unreasonable rumor.
where did the "NV killed their big chip" rumor come from? Kepler should be fine, no need to conjure mystical delay theories and shunted upgrade paths.Quote:
Originally Posted by bamtan2
Btw, regarding "february launch": http://www.obr-hardware.com/2012/01/...ia-kepler.html
Quote:
GeForce GT 680 will be launched in April. The first cards based on Kepler architecture are GeForce 600 not 700! Who's talking about launching in February, is wrong, this info is based on the old roadmap (from July). According to the last one is launch in April. According the old one, launch was supposed for january/february, now is planned for april.
It would take a lot, I mean a LOT of responsibility to "kill" a chip that has been in development so long and has been a budget drain of a lot of money. NV30, R600 and GF100 all made it to the market despite their shortcomings. A bad product on the market is still better than no product on the market. And in this case, it still doesn't make sense to kill the high end kepler chip in favor of something that isn't faster than Tahiti.Quote:
Originally Posted by bamtan2
I think that Matose knows better and if he sad that GTX 680 will launch in february than that it is.
It may be late february close to the end of the month.
Neliz has never let me down (although we don't know eachother :)).Quote:
Originally Posted by xdan
Every source is saying april for few months now. February seems like a wannabe from the community and the Nvidia dealers.
I remember a post some time ago from nvidia AIB who were wondering how they should handle the AMD 28lineup push while they didn't had anything from Nvidia....
I'm curious about the first information about Kepler that Nvidia will present before their release (or leaks before their release). Given all the rumours i'm really interested in what they really changed in Kepler to get their DP increase.
Huum i read your quote and now i read this one, when have been posted the line from OBR you are quote ? this blog look more as a joke when we read this 2 post in follow.Quote:
Originally Posted by neliz
OBR write ....
OBR write ....Quote:
GeForce GT 680 will be launched in April. In February, will be launched only GeForce GTX 550. The first cards based on Kepler architecture are GeForce 600 not 700! Who's talking about launching in February, is wrong, this info is based on the old roadmap (from July). According to the last one is launch in April. According the old one, launch was supposed for january/february, now is planned for april.
Quote:
You've all probably read on many sites, VGAs with graphics architecture Kepler is postponed to April, May etc (which is semi-official info from NV rep). It's maybe all just BS and Camouflage maneuver. Launch can be literally in a few weeks, all this is just to appease the competitor AMD ... before crushing blow! But only time will tell ... maybe in April, maybe soon ... will see who has right. Look above to newest post ... launch is in APRIL!
I think he means GTX 650?Quote:
in February, will be launched only GeForce GTX 550. The first cards based on Kepler architecture are GeForce 600 not 700!
Probably. It could also be a non-Ti version of the GTX 550 Ti, but if that's the case then that would seem to imply that any Kepler released for at least a few months around that time would be significantly more powerful than a "GTX 550."
stop to try find a speculation about release about it, this was just for point, in 1-2 weeks he change the type of accusation, but use the same words.... dont take his words too seriously.
maybe kepler will come tomorrow, maybe it will in february, maybe in march, maybe in April... who know ? Nvidia teams know...
http://www.xtremesystems.org/forums/...2&daysprune=60
says it all there, theres your 128bit card that arrives in feb / kepler in april
http://www.nvidia.com/docs/IO/82749/...ing_nvidia.jpg oh hang on http://t2.gstatic.com/images?q=tbn:A...yYth2j6_07JVxQ
Neilz has always been right in my experience so.... I am betting on April.
Well, going by this:
http://www.abload.de/img/0057t1b9.jpg
Then Kyle Bennet's comment about the enthusiast chip Kepler coming in June seems more likely, Neliz's comment about the incoming chip in April that's not the Kepler enthusiasts would be hoping for is also correct. It's also collaborated with Charlie's claim that NVidia would have its hand full with orders of low end Keplers for their Ivy Bridge's laptop design wins & Apple's contract, that basically making desktop-highend variants in backburner.
Slide from november... too little ... too late... bet they will be in Hannover :)
Who's Neliz anyway ?
I've tried to get the most unflattering pic off of youtube.Quote:
Originally Posted by Leeghoofd
http://i40.tinypic.com/2lj0oqp.jpg
:rofl: :rofl: :rofl:Quote:
Originally Posted by GoldenTiger
Do some of us have to post all those links with his comments about Cayman and Fermi again?
The power of selective benchmarking ;)Quote:
Originally Posted by SKYMTL
You invested yourself a bit too much in rumors of launches past with some outlandish claims.Quote:
Originally Posted by neliz
Don't worry though, it happens to the best of us. Conflicting info from even the "best" of sources and all that. ;)
With GF110 I was wrong with the 128 TMU's and for Cayman I saw some selective benchmarks.. but that's the price you pay for trusting people too much sometimes :) but hey.. 6950 is still a helluvalot better bitcoiner than a 580 :pQuote:
Originally Posted by SKYMTL
but we can tally that in PM's no need for more thread pollution :(
Well, we'll agree on that at least. :)Quote:
Originally Posted by neliz
And the fact that Kepler won't launch around the Chinese New Year...
Quote:
Originally Posted by SKYMTL
Anyway is there not a gaming convention soon? ( february or March ) the same they have shown Fermi the first time ?
E3 is JuneQuote:
Originally Posted by Lanek
GDC is March
PAX East is April
PAX Prime is August
Quakecon is usually in August too
So plenty of opportunities.
This was PAX, cant get the name when i was write it. thanks
April, God told me so..;)
mobile, consoles, and professional add up to being way more important than PC gaming to nvidia! if a chip is only good for gaming then what is the good of it to them! they're better off buying something else!Quote:
Originally Posted by neliz
professional is based on the high-end SKU. both NV's console chips are based on desktop parts (either high-end or performance chips) and even mobile tech is based on desktop tech. Scaling up is much harder than scaling down.Quote:
Originally Posted by bamtan2
when I said professional I meant quadro which is mostly NOT the big chip. sorry. the tesla HPC product is all the big chip.Quote:
Originally Posted by neliz
ALMOST all of nvidia's business now does NOT have to do with the big chip. gamers and nerds overstate the significance of the big chip.
Charlie weighs in on Kepler
Quote:
The short story is that Nvidia (NASDAQ:NVDA) will win this round on just about every metric, some more than others. Look for late March or early April availability, with volumes being the major concern at first. GK104 cards seen by SemiAccurate all look very polished and complete, far from rough prototypes or “Puppies“. A2 silicon is now back from TSMC, and that will likely be the production stepping barring any last second hitches. Currently, there aren’t any.
For the doubters, both of the current cards we saw have two DVI plugs on the bottom, one HDMI, and one DP with a half slot cooling grate on one of the two slot end plates. The chip is quite small, and has 8 GDDR5 chips meaning a 256-bit bus/2GB standard, and several other features we can’t talk about yet due to differences between the cards seen. These items won’t change the outcome though, Nvidia wins, handily
Source
For a well known Nvidia hater, this makes me believe its probably true. Thoughts?
Quote:
Originally Posted by Tenknics
Highlighted some other parts given we don't know what he compares (if he even talks about performance given his sarcastic sentences in other part of the quote).
Just curious what nvidia would need to do to get better performance than the 580 with less bandwidth. (i'm assuming nvidia won't run the ram at 1600MHz so)
If Charlie says that, then Kepler is simply going to be great. Years this guys job has been to utterly troll, flame and hate nVidia. If he is positive, this is going to be great.
That, or all his AMD contacts have been laid off and trying to find favour with the green team again lol.
That 104 is strange though, keeps popping up, the 4 has always been mid range performance hasn't it?
That's had me confused as well. Only possible explanation I can think of is that NVidia's midrange can tackle the 7970 so they feel there's no reason to bring forth the big boy until a later time. This is obviously advantageous as it gives NVidia time to tweak their design on the 28nm process before putting out a behemoth of a chip while also giving nvidia a haymaker to throw later on this year that AMD is going to have a tough time responding to. After all, as a publicly traded company, your main mission is to make the investors happy. Bringing out your $250 card at $400 will DEFINITELY make the investors happy.Quote:
Originally Posted by Tim
At the same time that sucks for the consumer, because we'll end up paying higher prices from both camps this round in each respective segment. Right now people are blaming NVidia for AMD's pricing--but AMD's pricing on their cards is going to also bring up NVidia's pricing since they see they're able to get away with it. That's a bad thing for all of us.
This is, however, the first time I can think of that charlie has EVER been positive regarding a NVidia product. That alone gives me a lot of faith in this chip.
Wow I never thought I would ever read such an statement from Charlie. Kepler is going to kick ass, head, teeth and everything.
This guy might just have stopped AMD's sales on it's track with just this single post.
No...Quote:
Originally Posted by DilTech
...7990?
Two gpu ....Quote:
Originally Posted by Dimitriman
Bad memory I guess then, haha on my part.....Quote:
Originally Posted by SKYMTL
EDIT: I meant as far as dates, primarily, though is what I had remembered.
I found this picture from zol site
http://diybbs.zol.com.cn/56/231_558125_49.html
The man says:
The first image GTX680!!
???
http://h9.abload.de/img/gtx680plxk8.jpg
http://www.abload.de/img/gtx680so5e7.jpg
Ummmm....no.Quote:
Originally Posted by Dimitriman
As stated above and many times in this forum, I'll take a $600 single GPU card over a $750 dual GPU card any day.
A personal choice... doesn`t take away that 7990 will likely be the fastest thing you can plug in a PCI slot..Quote:
Originally Posted by SKYMTL
BTW I too would make the same choice as you.. but I am talking about facts. AMD will have an answer to Kepler in the form of 7990.
If it takes a HD 7990 to truly respond to Kepler, then NVIDIA could easily respond with a dual Kepler card. Provided TDP stays within certain boundaries of course...Quote:
Originally Posted by Dimitriman
If it takes a HD 7990 to truly respond to Kepler, then NVIDIA could easily respond with a dual Kepler card. Provided TDP stays within certain boundaries of course...Quote:
Originally Posted by Dimitriman
Well you will have info way before I will so give us a hint when you know more about kepler :)Quote:
Originally Posted by SKYMTL
If the GK104 is faster than the 7970, and the GK104 is the midrange kepler chip, then how on earth would the 7990 have anything close to a prayer at being faster than NVidia's top end chip? Even if it DID happen, NVidia could release a dually of there own and out-right slaughter it.Quote:
Originally Posted by Dimitriman
If the news is true then NVidia will be in a very interesting position.
Look like a fake, since when they put the SKU numbers in bold.... can be just "thermal paste" traces, but it is a bit strange it appears specially on the "GK" and "2", look like the GK110 "fake" shown have just been modified with the 2. ( after the A2 revision surface. )Quote:
Originally Posted by Tha Last Meal
There might be a 680 close but it's yet to be seen if it's really going to be a high end Kepler part or the same as 5870->6870.
first page updated. thx
http://vr-zone.com/articles/report-n...led/14589.htmlQuote:
GK104 impressively doubles up on GF114's core count to 768 CUDA cores - although Kepler shaders will be different from Fermi counterparts. Single precision performance is rated at above 2 Teraflops, twice that of GTX 560 Ti and over 50% higher than GTX 580. GK104 will continue to feature a 256-bit memory interface, but with frame buffer doubled to 2GB presumably at higher clocks. With everything increasing, unfortunately so does power consumption, to a TDP of 225W. A GTX 660 Ti variant is also expected in the future.
woooooow.... gtx 660 battles with 7970? did i read well??? ..... i think i'll be scared about gtx 680 or 780 or what ever comes out after the 660.
AMD put out a hell of a card in the 7970 IMO, if any of this speculation about how fast Kepler will be ends up being true then I will be seriously impressed and it will be huge leap over previous gen. Think I will hang onto the 480's till the dust settles but would love to have a single GPU to replace them.
Don't know which is causes me to scratch my head more; nVidia's mid range chip potentially being faster than AMD's high end chip or nVidia's mid-range chip potentially having a higher TDP than AMD's high end chip...
Dunno, but i have the strange feeling, something still going strange in the infos we have: Why speak so much about the GK104, if the High-end will be outrageously fast ? Since when Nvidia launch a series by push first the middle range ?
Time will tell us what nvidia is deserving for us.... At the same time i do not want to remain dissapointed...
AMD set a pretty low bar with 7970. They can definitely raise it higher by tweaking the cooling/voltages/clocks though. A hypothetical 1100-1200MHz Tahiti seems like it would be hard to beat with GK104.
Leaks speak about a 225W card, if really this is the case for the middle end cards ( GTX560 = 150W, TI= 170W, 460= 160W, GTX580 = 243W ), i fear they can't release a higher end models under 280-290W ( and this is the minimum ( expecting it have at least 1024SP), a wider memory bus and more GDDR. Untill offcourse a lot of "informations/leaks" are merged between different SKU...
That rumor bit at chiphell about the 225w GK104 suggests that Nvidia is pushing to increase PCI-E power specs to 400 watts per slot. I guess they'll need like ~300-350Watts for a decently clocked 1024SP 28nm Kepler card.Quote:
Originally Posted by Lanek
Dp.
You guys realize that someone probably confused the 2x6pin requirement with the TDP, right? Actual TDP will be lower, I'm certain of it.
This man put another picture and says that GTX 680 performance is strong
http://diybbs.zol.com.cn/56/231_558125_50.html
http://www.abload.de/img/11gtx680405l1.jpg
What do you think is fake or Real?:confused:
From the VR-Zone article :
Seems like Dil-tech was in the right direction.Quote:
GK104 or GTX 660 will most likely end up competing with AMD's Radeon HD 7970
Now Charlie's comment makes complete sense too. If 660 beats 7970 then how fast will the flagship be?!!
Tick tock business blowing my mind. G80 all over again surely?
Fake. Has already been exposed as such.
VRzone cite Fudzilla, Inpai cite Fudzilla, guru3D cite "i dont know", but call G104 the GTX680 and release date in february ... Inpai dont give any date and cite fudzilla as source, Softpedia cite Inpai, but give a date... Guru3D say February, Fudzilla Q2 ( April ), add then other forums take the 3 and make a compil with old, new infos .. huum .... outside charlie words, this look to turn in loop .. I was think Inpai is the initial source, but it is not..Quote:
Originally Posted by Tim
Even in Chipell, nothing new. The joy of Internet ...
You forgot EXPreview (PHK?), this site was the first to talk about 2GB/256-bit week ago, and a non-Q1 Kepler launch since many weeks.
source???Quote:
Originally Posted by boxleitnerb
some pages ago, you should find the same screenshots.Quote:
Originally Posted by clo007
I really do hope Nvidia will bring a fast and small chip that could compete with 7970. That could very well force a price war. I still doubt though that a 2GB 256-bit Kepler will perform the same as a 3GB 384-bit GCN, even though Kepler probaly is more mature as an architecture. But even if it came close it would be great. At the moment though I don't think we'll see it before april, and some people are saying june, and I guess the big chip before the end of the year.
OBR trash talking AMD?
Wake me up when there's coffee...
What i like is some days ago, it do a big post on his blog, saying: " dont believe what other write, kepler will be out in february.." now its is April in this post .... seriously..Quote:
Originally Posted by Dimitriman
Maybe he is right, but i start to think infos are seriously given for marketing right now.
GPU-Z GTX 680
http://h8.abload.de/img/gtx680gpu-za54qo.jpg
I do not see that this picture is fake
GTX 680
http://h8.abload.de/img/gtx68017q223.jpg
http://diybbs.zol.com.cn/56/231_558125_50.html
Of course it's fake, GPU-Z doesn't have the new cards in its database yet.
And you see that the version of Gpu-z is blurred to?
May be it a version not available yet?
I wouldn't rush to say it's fake yet.
Although 1024SP sounds to good to be true.
it's fake we are in 4th week of 2012 and manufacture date is written on gpu shows it's 28th week.. pls dont bring anything here from this kid..
That GPU-Z picture looks fake, even if it was real, I hope NVIDIA does not use 2GB on a 512 bit memory bus, looks like NVIDIA did not learn with lower VRAM on the GTX 580.
Learned what? The difference between 1.5GB and 3GB was negligible. Not to mention, they just upped it by 512MB...
http://tof.canardpc.com/view/a2f56c4...fce6c28e95.jpg
Hi, I work closely with the developer of GPU-Z, and I can confirm that screenshot is fake.Quote:
Originally Posted by Tha Last Meal
BF3 with bells and whistles on takes 1400mb on Video ram on my card. So 1.5gb is barely enought for current new games. If u buy a card for 2 years and have decent monitor to connect to, then 2GB is pure minimum.
What games are we talking about exactly?
Name one DX11 title, that is supposed to come close to the BF3 custom PC platform stuff, because I can't think of any. MS nor Sony are even close to launching (not just unveiling) their next gen console, so you don't really have to worry about that too. And when they do, I don't think this generation of cards will be fast enough to handle them at max. settings, so again, no real issue here.
I think 2GB should be also the bare minimum for midrange/highend cards today. It's enough but only just, 3GB is already overkill today but might be very useful in 2 years. I'd really need a VRAM upgrade, 1GB isn't cutting it anymore despite I'm a 1680x1050 res user, especially in Skyrim with texture mods! :P But yea I'd be perfectly OK with a new card being released with 2GB today if price is right.
The issue I see is that if NV's "mid range" Kepler part can compete with the HD 7970, then the high end Keplers will be so expensive, no one will be able to afford them. I mean imagine what the market would have looked like if the GTX 560 Ti competed on a level footing with the HD 6970 and was priced accordingly. Yikes!
One of the two would start a price war for sure. I don't expect more than 600$ for the top dog. What good does a card do that no one will buy?
They've had higher prices in the past. Then again if Nvidia's big chip comes late 2012 prices have probably fallen already, especially if GK104 and 7970 compete in price and performance. Though I don't see either one wanting a price war in that case. Nvidia wants a premium and AMD wouldn't want to drop prices if it had a more expensive card.
8800 Ultra was +$830 at launch