Isn't that what I said in post #502? 8800 beats HD38_0 in games but looses in 3DM?
:p:
btw, 8800GT is G92, not G98.
Printable View
Isn't that what I said in post #502? 8800 beats HD38_0 in games but looses in 3DM?
:p:
btw, 8800GT is G92, not G98.
g98 is the 8400gs, the exact same die is becoming the 9400gs or whatever it is, I wasn't talking about the 8800gt.
You said it wins in 3dmark, which is only partially true, the radeons lose in 3dmarkVantage
Quote:
Originally Posted by largon
Someone had to do it didnt they? lol.Quote:
Originally Posted by bhavv
1) I have a crossfire P35 so I chose to get an ATI graphics card
2) I bought my 3870 in january when it was £30 cheaper then the 8800 GT and the 9600 GT didnt exist.
The difference between the 3870 and 8800 GT is unnoticable at 1280x1024 which is the resolution that I play at.
Your just a good old xxxxxxx that cant understand why people would buy an 3800 card.
Edited.. Have a little class huh and an insult is an insult no matter how you spell it.
Movieman
^Reported.
And for the record, I merely corrected your factual error (performance in benchmarks). I did not comment you ramblings about drivers. Read my post.
I say again:
That attitude won't get you far on this forum I reckon.
since when did this thread become a flame fest?
Blah blah blah. WTF is your problem? Instead of trolling this thread, please go do something productive with your life. If you attempt to call me an nvidiot, look @ my hwbot records :shakes:Quote:
Originally Posted by bhavv
Quote:
Originally Posted by largon
Corrected?
Nvidia cards score higher in every 3d mark benchmark, AND games so where is your correction coming from?
ATI 3870's score around 11-12k on 3d mark 06, whereas 8800GT scores around 12.5-13.5k (at stock frequencies).
I was stating that Nvidia cards are faster then ATI, why do you have a problem with that?
Did I say anything to you?Quote:
Originally Posted by [XC] gomeler
I can't quite understand how the rumoured texture buffer sharing for the dual die solution would work. Any PCIe-based bridge chip would choke on the bandwidth involved with GDDR5. How would it work?
bhavv,
That's nice. Now begone before you go on any further.
As far as I know I haven't recommended anyone to buy or not to buy anything or trashed ATi in any way here.
:shrug:
As far as I know I was talking to someone else that said ATI drivers are worse then Nvidia on the previous page, then you come out of nowhere and start misquoting and misreading what I said.Quote:
Originally Posted by largon
Quote:
Originally Posted by largon
No but you are being a :banana::banana::banana::banana: and if I had a "give a free week long XS vacation" button, I'd have exercised it in this case. The usage of derogatory terms is not necessary in an intelligent conversation, something which you seem to be borderline incapable of handling judging from the past few posts. I just hope having enough people telling you to pipe down would get the message across, maybe a PM from a mod will settle you down a bit :shakes:Quote:
Originally Posted by bhavv
This quote for you.Quote:
Originally Posted by Origin_Unknown
Quote:
Originally Posted by [XC] gomeler
hmmmm, I wonder what your bananas were....Quote:
Originally Posted by [XC] gomeler
You would fail as a moderator m8, its good job that you arent one, and you are reported too.
Tries to find Mod hat thru half opened eyes:
Why do you guys have to fight over dumb crap?
Both companies have made good and bad and that's life.
You pick the one you like and thats what you use.
Yes, in my house there's a 7800GTX, a Ti-4400, a HD2600XL, and a couple of X550's for the crunchers..
oops, and a 1 gig HD2900 XT card..
A little more friendship and less fanboyism would go a long way here my friends.
Thanks for reading
People come on its just a graphics card, i cannot believe people are getting arsey over such things. I started reading this thread because i thought the people on this forum are knowledgeable and it may be the best source for info regarding the upcoming ati card not some fanboy fest. :)
It really does reminds me of last year with the R600 release its playing out just the same, false benchmarks popping up everywhere, people speculating. Is there anything that is factual at this stage?
GDDR5 will be used in some of the next gen R700 cards...
The next gen cards will launch sometime between end of may and july...
You'd expect the enthusiasts (Top End) cards likely to be atleast a minimum 5% - 10% faster then nvidia's best offerings (9800 GX2).
Anything else at this stage that we know of which is likely to happen with this card... :shrug:
Sorry, I just hate when people start name calling to get a point across. I called him the other name for Roger as he was acting as one. I suppose this is a classic case of stooping down to a lower level :rolleyes: Time to go watch planes fly around pylons :cool:
Need moar sleep? :(Quote:
Originally Posted by Movieman
I don't think that :rofl: .Quote:
Originally Posted by azza21
Yeah probably wishful thinking, still you can hope eh.Quote:
Originally Posted by whocaresbg
Aah, what I would have done xD
Now I sit back and enjoy the circus :up:
ATI and Nvidia both have their trade offs, unlike AMD vs Intel where one side has the trades and the other side has the offs x( ATI will come out strong this time around, and that's with my conservative estimates of a 25% increase in performance. No one knows if that'll be enough to challenge the GT-200, but everyone knows that while Nvidia will be busy fine-tuning a new process, ATI can whip out a newer more shader/ROP heavy card in no time if the 3870 -> 4870 transition tells us anything.
I've said it before and I'll say it again though, those who underestimate Nvidia and overestimate ATI are usually sorely disappointed.
Perkam
*sigh* Been away for a week and came her to look for hopefully more hd4000 news, only to find a stupid and oh so boring flame war. Can someone unsticky this thread as its useless, and lets get a proper hd4000 thread instead...
Come on big players please leak something already :D all this waiting is killing me.
I cleaned up some of the garbage in this thread.
This is my second time here.
Can't some of you take a hint?
Do I have to open the closet door and let the "Mod from hell" run loose here?
Keep it nice huh? I don't like letting that side of me run loose.
Thanks for reading..
Down Frankie Down..
Fudzilla post a news about RV770 :
Die shrink with minor changes
sad if this is true
But it's possible that's the RV770XT is two die on the same packtage.
We've seen a pict of the cooler of the 4870 and we can clearly see two dies !!!
480 shaders ? 320 ? 640 ? ....
get out a nice one please AMD :p
No, not really. As Fuad points out, "they will bring some significant performance improvements compared to the previous RV670 generation." RV670 was in general a good design, it was just that the architecture was fairly unbalanced - it had a preponderance of shaders and a dearth of TMUs, explaining the strengths of the card (3DMark, shader-intensive games) and the weaknesses (AA/AF, high-res texture-intensive games). I never quite understood why ATi made this design decision at the time, but that's neither here nor there. If ATi were to simply bump the core and shader speeds and even out the architecture, RV770 stands to be a very competitive product - and as Fuad has pointed out, neither of these is a huge change in and of itself.
Well not sure if that is going to answer your question but as far as I know AMD had its price chart towards 3Dmark, probably that may be the reason why AMD was pricing it looking at 3Dmarks results, not sure concerned it as proof of testing HRD3 and SM2 results. I hope they learned now 3Dmarks results work fine but not that great, games use different engines and has its own drawbacks.Quote:
Originally Posted by SoulsCollective
SourceQuote:
Originally Posted by Digital Urban
How to
Game Engines
I wonder what technology based Crytek used to make its engine as it is the only difficult game to real time.
Metroid.
"ATI said a few things about its new upcoming RV770 chips, and as we've said before you can expect RV770PRO with DDR3, RV770XT with DDR5 support and the top end, R700 aka (RV770X2) with two RV770XT chips in a dual-card configuration. The new GPUs are 55nm and they are actually an architecture shrink chip with minor architectural changes. The new RV770 chip will also have great improvements in power consumption. The launch date is late Q2 2008, most likely June, but real volume availability is expected in early Q3 2008, probably July."
source; http://www.fudzilla.com/index.php?op...=7153&Itemid=1
already posted in the thread.Quote:
Originally Posted by Monkeywoman
Nothing new :down:, but FUAD .....Quote:
Originally Posted by Monkeywoman
any set in stone dates for a release? to many replies in this thread to read it all:D
I hope they can get this out alognside 9900
i don't like the silence !!! this card can be a dissapointment too
Pssh... the silence leading to the launches are the good ones. :D
R600 was super noisy, RV670 was leaked way too early, RV770 is a refreshing break.
More news on the RV770 from our favorite most honest site fudzilla.
Apparently the RV770 is now only 1.5 times faster then the RV670 rather than their previous thought 2 times as fast predictions they made 2-3 weeks ago.
"We've learned (apparently fudz learnt something) that ATI's new chip might end up 1.5 to 1.6 times faster than the current RV670 solution.
In the real world, this should mean that if one game gives 50FPS with RV670 that the new chip should be able to get you around 75FPS at the same settings. On average, the new chip will have to be at least 30 percent faster than the old one to make you even consider it but at least specification wise there is not anything that you might miss.
RV670 was a shrinked and better speced version of R600 with 512bit memory controller crippled to 256bit and it looks that R770 will get that memory upped to 512bit again. At least we know it will end up being fast but we still don’t know what's Nvidia’s real answer to this one."
Fudzilla's ever changing predictions (LINK)
50% faster usually means 1.5 times so its still 50% faster... 100% faster is 2 times
I personally doubt there's any chance of the rv770 getting a 512 bit memory controller, unless if he's talking about the r700 which may have a different controller as its an mcm, because 512 bit+ gddr5=big waste of R&D not to mention higher costs for no benefit. The gddr4 2900xt had more bandwidth than the card would ever need, I'm pretty sure ati took some notes after thatQuote:
Originally Posted by azza21
AMD stock up 15% in last two days while rest of Market down. Somethings going on within analysts. Maybe some positive future News coming out?
yeah, I got a tip to buy some from a friend yesterday at the business school
I dunno what's up though but I hear it's related to AMD restructuring
or/and are being silently acquired...just a guess. Read a couple of times NVidia could afford it...Quote:
Originally Posted by Jowy Atreides
But they wouldnt be allowed to.Quote:
Originally Posted by Logos4
Hector leaving perhaps?Quote:
Originally Posted by Jowy Atreides
Can't be. It would be up 50% then. :p:Quote:
Originally Posted by xoqolatl
There are no mysteries there: Puma is about to be unchained, and will mark broad acceptance of AMD platform in notebook market and RV770 is just around the corner and will rock!Quote:
Originally Posted by Jowy Atreides
I hope RV770 is a monster, I really do... But last I had read Puma would still be inferior to C2Ds. :(Quote:
Originally Posted by Nedjo
http://www.tgdaily.com/content/view/37116/135/
Quote:
Regardless Intel's 45 nm design has the edge and and consumes less power. However, the current situation apparently prompted AMD to adjust its marketing message, stating that it is focused on delivering “balanced” platforms. An AMD source told us that "Griffin will not be able to touch Core 2 Duo", which is quite a bombastic statement coming from a senior source.
we'll see how much impact puma will have, but the bigger the better -> I hope puma puts some preasure on montevina, so they get nice and cheap :D
it's a bit faster than a K8, it's a cpu with K8 and HT3.0Quote:
Originally Posted by Beefy22
Puma still stay faster ;)
why ?
Just because the IGP is a lot faster for games and for aero, ... HD-DVD & Blue-ray ;)
if i want to play games on a laptop i wont get a igp... :p:Quote:
Originally Posted by madcho
The new IGP is actually quite insane, eons ahead of the X3100...so though the Intel laptops will do well in sysmark and what not, they will lose badly in 3d benchmarks, which most notebook reviewers use nowadays, even if that MAY not be the purpose of a notebook.Quote:
Originally Posted by Hornet331
Perkam
Why do peole find it hard to grasp the point of Puma?
Remember when the Geforce 7300 M/Radeon X1400 was in a lot of notebooks for Aero support and whatnot?
Now OEMs get 2x the performance, less power usage, and MUCH less cost as they do NOT need to add an extra chip.
Puma got so many wins because it was offered early and had a full scope, something that nVidia can't seem to do. Their hybrid SLi is still in Beta AFAIK.
i dont get why all people are so fixated on igps for gaming... seems amds marketing department does a very good job in this department... if people want to game and know they do it, they don't buy crappy ipgs... nowadays i would only accept a HD3650 or higher (doesn't matter which brand) for gaming on a notebook.Quote:
Originally Posted by perkam
Also i dont know what notebook reviews you look at, but most reviews i read only have a tiny fraction of the review focused on gaming performance.
There are more important things like viewingangels of the display, thermal signature of the notebook, runtime etc.
anyways this goes far to much in the off topic direction -> ends off topic.
The point isn't the igp alone,it is the igp that works with discrete graphics in Hybrid CF with mobile HT3.0 CPU(Griffin).The discrete gpu shuts down completely while not in 3d so it basically draws no power unless you game (in which case it boosts the fps quite dramatically compared to 780g which alone practically destroys anything else in its category).Quote:
Originally Posted by Hornet331
I puzzled by this as well.Quote:
Originally Posted by largon
Perhaps the ring bus is part of the solution, and the bridge chip is also part of some MCM package (2 dies + bridge chip + pershaps even an external memory controller). Perhaps the bridge chip isn't needed at all, if it is a MCM package with a little design change because of shared socket.
Pure speculation of course. I don't know or have any idea, because it shouldn't be a simple solution, at least not with the way stuff works now or is designed.
*drool* can't wait.
Thing is though, I think this is designed to be an mcm, not just two gpus on a single board, I don't think there will need to be an external bridge chip. Think about it, if they have a shared ringbus, then that means this is more than just two rv770s in a dual die mcm, there has to be some modifications to basically meld the chips to be detected as one thus eliminating the need for a bridge chip. That's probably the whole point of doing this rather than the 3870x2 design.Quote:
Originally Posted by Seraphiel
Man I just wish we'd finally get some legit info already, or if we have, that ati would confirm it
I totally agree :up:Quote:
Originally Posted by AliG
It really sounds promising and I rather be an optimist than a pessimist. This could be the advantage NVIDIA can't break until after its nextgen (GT-200(?)). I hope so, because NVIDIA needs a little humility... This said as a user that has spend >4500$ on NVIDIA product in the last 18 months.
Humility benefits everyone.
not even a month and we do not have a single pic of these cards. i just want some pr0n thats all.... :p::yepp::DQuote:
Originally Posted by w0mbat
doubled texture performance, but according to these specs they didnt add any stream processors :rolleyes:Quote:
Originally Posted by w0mbat
edit: RV770
card specs and chip specs dont lline up...
that doesn't have to correct though, that just seems to be exactly what Theo posted, which Andreas confirmed was wrong. the +200 mhz over the core clock for shader gives it away, not to mention if the card will launch on the 31st we would have at least heard something by ati by now, but that doesn't have to hold true with the way both companies have beenQuote:
Originally Posted by w0mbat
Says 480SP's here....maybe they changed it?Quote:
Originally Posted by generics_user
those specs are wrong, they quoted Theo, which Andreas (among others) have confirmed was wrong
So what are the certain specs (if any) :confused:
To hell with clock speeds for now, what is the specs of the architecture? I have read everything from doubled clocked SP, asyncronious (?) SP clocks, more SP (480), many more SP (800), simpler SP (like NVIDIA's 2+1, and not current 4+1) and X, and Y, and the most certainly Z.... and a combination of some of them.
If this is about to be released in a few weeks, then I would expect more certainty about specs and improvements.
I really hope ATI has a 8800 Ultra killer on their hand that is single GPU socket, unless they change most standards such as we know them.
Actually I said the +1GHz GPU frequency was wrong. It says 850MHz core here, and 1050MHz shader clock. That's not unreasonable.Quote:
Originally Posted by AliG
//Andreas
I thought you said the clock differential was theo's wishful thinking?
Eitherway, I'd personally like to see those shaders running at 2x core speed instead of just 200mhz higher, that's what they need to do to spank g92 imo
I dont think we will see 1000+ Mhz on GPU's until they shrink to 45 nm tbh.
My birthday is in 9 days and I wanted a 4870 :(
as for an IOU?
do your birsthday when you can buy one then ;)Quote:
Originally Posted by bhavv
Nono, just the +1GHz GPU frequency, but nothing is set in stone.Quote:
Originally Posted by AliG
//Andreas
hmm, I wonder what ati will be doing about the shader clock issue the r600. To be honest I'd rather see the old 320 shaders with something like a 1:2 alu:text ratio and the shaders running at least 2x core speed rather than 480 shaders. Of course many can argue that's copying g80's design, and of course it is, you implement what works into your own design, why else did intel bring 64 bit computing to their cpus?Quote:
Originally Posted by NH|Delph1
That, and don't forget, no matter how shaders the rv770 has, unless if the game can make use of them, they're just about useless, the 9600gt proved this by being very competitive with the 3870 with only 1/5th the shaders
Ok... so I am confused by your post...Quote:
Originally Posted by AliG
First you say that ATi needs an independent shader domain.
The you proceed to talk about how "inefficient" ATi's shaders are by comparing across a different architecture?
My main question is why does everyone think they need to implement an independent shader domain when R600/RV670 has shown that the "bottleneck" is elsewhere. An independent shader domain would not only hinder the architecture IMO, implementing it now would basically null the point of RV770.
Computex 2008 AMD won't display RV770 at Computex :
http://my.ocworkbench.com/bbs/showth...981#post430981
:shakes: .
Don't the shaders do AA? Therefore, the more shaders the better!
I'm not a huge fan of the poor AA performance on my 3870.
hype hype hype...
That's weird, I thought the cards were going to be released at the end of May. Now they won't even have them ready to show the first week of June? Maybe this is going to be more like a July launch.Quote:
Originally Posted by whocaresbg
R600 launch all over again, uh ohhh :D
Are they hiding something (bad) like with R600? :rolleyes:
Another flop? :(
Turn off AF, you should see a nice boost. I believe its been agreed on that AA wasn't the big issue, AF was due to the very small texture powerQuote:
Originally Posted by roadie
Why would it reduce performance? I mean look at how well the 96gt performs, and it only has 64 shaders. I pretty sure unless games are coded to make use of all those shaders, no matter how good the drivers are we probably won't see as much as a boost as we'd like.Quote:
Originally Posted by LordEC911
Nah I highly doubt it, more likely than not gddr5 is the reason for the delay, besides fuad has posted I believe 3 times now that the rv770 will see the return of the r600's ringbus so that means there's a possibility of a gddr3 4870 with a 512 bit memoy bus. I generally don't trust the really shaky things fuad says, but when he posts the samething multiple times it generally turns out to be rightQuote:
Originally Posted by Calmatory
4870 will be a boost about 30 to 50% over 3870
Quite likely. Even though the rumours float around and the speculations vary from theoretical ~6+% boost to +100% boost, in practise this is going to be somewhere near 30-50 % average.Quote:
Originally Posted by madcho
Because it would be lowering the core clockspeed, aka the ROP and TMU speed.Quote:
Originally Posted by AliG
Again... comparing across different architectures.Quote:
Originally Posted by AliG
Do you understand how ALUs work?Quote:
Originally Posted by AliG
The game doesn't need to be "coded" for the shaders, at least the way you are thinking about it.
GDDR5 is good and ready to go.Quote:
Originally Posted by AliG
RV770 IS a 256bit GPU. Seeing as how they will be using the RV670 PCB with some slight component changes.
Maybe the GPU was disigned to 512bit, because you can't know when you create the ship if the GDDR5 will be ready or not.Quote:
Originally Posted by LordEC911
Maybe it's a 512bits GPU with 256bits GDDR5.
But i heard that the GPU could get out with GDDR3/4 memory if the GDDR5 is not ready, and the GPU will be a 4850, the 4870 may wait the GDDR5 about one month.
i think the GPU is ready, the GDDR5 not, and AMD is waiting for RAM.
I suport AMD/ATI, i'm gonna buy a 4870, the 3870 is a great videocard and even if i don't need more 3D power, i'm gonna buy it. And if AMD do only a dual GPU in High end and a 4870 cheap it's going to be very interesting ;)
What would the problem be then? I can't see the die having issues at this point considering its just an upgraded rv670 as you said and taped out months ago. Gddr5 remains the logical explanation, probably there isn't much volume yet, which is one reason why nvidia went with 512bit for gt200 (also the 32 ROPs remains as a big reason)Quote:
Originally Posted by LordEC911
Very very unlikely, this is because the upgrade to a 512 bits external memory bus ads quite a bit of transistors that would be put to waste when you are primarily planning on using it for a 256 bit to GDDR5. This would be a bit of a problem as pretty much all current rumours point towards a relatively small die, not too much more transistors in other words and the smaller die will make it harder to get all the pin-outs for a 512-bit bus on there.Quote:
Originally Posted by madcho
I think they mean 512-bit internal... IIRC R600 was 1024-bit internal and RV670 was 512 internal but for memory its 256 but I could be wrong.
Who says there is a problem?Quote:
Originally Posted by AliG
We are still expecting a June hard launch.
People were hoping for some boards to get out before the end of May but that seems unlikely seeing as how we haven't even got confirmation on almost anything yet.
There's word that ATI won't be displaying it at computex, that's why we're wondering on what the problem isQuote:
Originally Posted by LordEC911
GDDR5 not ready ;)Quote:
Originally Posted by AliG
Which wouldn't explain a lack of 4850 GDDR3 though ;)Quote:
Originally Posted by madcho
The other possibility is that the 4850s could start selling in May...
*ducks*
Why does AMD *HAVE* to showcase them at Computex to be problem-free, I have no idea.
Computex doesn't really draw much attention to glamour GPUs. A private event would KILL Computex 10:1 in coverage. :D
which is what I said, which you would have known if you read my posts and why lord was constantly trying to prove me wrongQuote:
Originally Posted by madcho
It's been very difficult being an ATI fan lately. Well up to the 3870x2 but even then its been hard. But now this? HAHAHA! Nvidea has been on top for so long and ATI nearly got dumped with the AMD merge. Im going to have to replace my Sapphire 3850 1 gigs for one of these babies! YA oh YA! I SO LOVE IT! My Nvidea friends are going to hate me. Im sending them this link as fast as I CAN!:shocked:
Send what ? rumours, speculations ? Nothing is definitive as usual in these threads, we all have to await real benches from trusted sites or reviewers... then spread the word that the green team get's bumped... if I was you lay low and don't make a fool out of yaself...Quote:
Originally Posted by MERC!
Just a troll. =) Fanbois should be muted on forums. But yeah, at this point no one can really say anything, it's all about speculations an rumours.
hard to control that though, that and probably fugger would lose a lot of traffic if he did that which means less ads+sponsors etc
I don't see any adds here do you? I think FUGGER is more concerned about having a proper site with a respectable community than ads and sponsors. But oh well, that's all off-topic.Quote:
Originally Posted by AliG
As for on topic: I don't think any many of us have anything new to ad (or if they could, they're probably under an NDA)
0+0=0
At least nvidiots could be banned...
there have been ads occasionally, but its mainly the hardware sponsors I'm talking about, fugger pays for his own equipment (such as his ln2 pots and what not, although I'm sure he trades hardware with kingpin and shamino etc all the time) but a lot of the hardware he reviews are sent to him by various companiesQuote:
Originally Posted by Helmore
Define nvidiot please. :p:Quote:
Originally Posted by Nuker_
Why are both companies so strict about info this time? Or os there real info out there and people just call it fake? Or are they hiding something? Oh ati, OH ATI! Don't let us down this time plx! :rolleyes:
I hate getting caught up in the hype... Boy, I remember spring '07 when I was waiting for Barcelona in MAY, with a 40% improvement over C2D.
i remember too, but AMD have done mistake with process for barcelona, and ATI made a big mistake with R600, the do a very nice one with the RV670, and i think they changed the design, the RV770 or R770 is just a die schrink with more units ( TMUs and Shaders ).Quote:
Originally Posted by Loser777
If they do a RV770 with same frequency with RV660 and respect the price anounced, there will be no place for nvidia in mid range and mid+ range.
And Maybe more on high end with the dual gpu, that could be very very fast.
GT200 is coming with watercooling ... too much heat.
The process for RV770 is nice, it's a dual die we're going to have very cheap gpus and very fast :up:
I doubt that they will be THAT fast. Otherwise they wouldn't need duals to be fast. :p:
Well, whichever is faster, I don't case as long as the TDP stays below 95W, and price below $150.
Nah bugger that :DQuote:
Originally Posted by Leeghoofd
Lets keep the speculating going, it makes it more interesting and it keeps the threat active and most of all it keeps people wondering. If these website like the Inq and fudzilla didn't post anything but gossip there wouldn't be anything interesting to say on the matter, remember speculate to accumulate.
So here you go:
RV770PRO supports 256bit memory Source: FUDZILLA
"We wrote that RV770XT supports 512bit here and now we have learned that the slower RV770PRO will only support 256 bit and it will use GDDR3.
It looks that the current GDDR5 design sticks with 512 bit memory interface and as RV770PRO will use 256bit GDDR3 memory. The RV770PRO will need a smaller cooler, it is definitely going to end up cheaper of two, and you can bet on a sub-$200 price.
RV770PRO will also end up with a slower clock than RV770XT but we still don’t know what is the current speed plan. It is sampled and it works at least the RV770PRO with 256bit GDDR3 does."
Fud also say:
"We know that some VIP customers have seen and tried GT200. We also know that the card is fast and it is definitely faster than Geforce 9800GTX but we are not sure if it can beat Geforce 9800 GX2.
As we've said on many occasions GT200 based card is a single PCB card with a single chip and a big dual slot cooler. It naturally needs two power connectors but this is something that we are getting used to.
GT200 is something that Nvidia is preparing to show under NDA to many journalists in late May at its headquarters and we wouldn’t be surprised if we see it at Computex 08 as it should be ready to launch around that time."
thats ok peeps your more than welcome :p:
Hoping the RV770Pro is just a lower-binned RV770XT so I can ram some stupid volts through them :up: Cannot wait!!!