Picture of AMD ''Cayman'' Prototype Surfaces

[Atom_Anti]

Originally Posted by _JP_

Have I made myself clear?
And because it is FUD, your sentence backfires. As in, how do you know it won't have 512-bit bus width?

Because the 512bit would drive the cost up significantly and nobody wants that to happen. It is already makes 204,8 GB/s bandwith with 256bit bus and 1600Mhz GDDR5. That is pretty awesome, isn't it? or need more?

[JATownes]

Bring on Cayman. My bank account is waiting to liquidate some cash.

[Phxprovost]

ohh boy a side shot of a blank cooler covered in watermarks, color me excited

maybe if this was a board scan....but really?

[inferKNOX]

Originally Posted by _JP_

According to Wiki, 2GB of RAM seems to start being implemented on high-end cards with still few games being able to fill 1GB. They seem to want this standardized.
Also, nice to see possible 512-bit memory buses. Last time I saw one of those was on a 2900XT (wow, long time ago).
Good thing is that the new HD 6870 is only going to consume 10W more than the current one, supposedly from the extra RAM.
But all of this hasn't been confirmed yet so it's FUD...It'll be be good if it happens...I'll patiently wait anyway...


Start messing with the Search feature.
See here and here.

I think that if that is the case, it's to get better AA performance in Eyefinity setups. The memory becomes the limiting factor with Eyefinity's higher resolutions, so it would make sense for them to add more. I was looking for a 2GB 5870 to run 24/7 Eyefinity on 3x 1920x1200, but found the cards costing relatively silly prices.
I'll be very glad if the 6850 has 2GB and that DP->DVI adapter that AMD has just released; it'll be perfectly ready for Eyefinity out of the box!
It's making me drool for it so bad!

[LAN_deRf_HA]

I think you'll still be out of luck even if it does come with 2 GBs. I'm betting the 6870 will launch at $400 and very quickly get jacked up to $450-500. AMD will have no competition for a long time, and just with the 5000 series they're going to take advantage of it. The 5850 cards are still not down to the original launch price. Those first buyers got one hell of a deal.

[BazookaJoe]

I thought AMD had retired the"ATI" Brand.

If this is a new card would it still be branded "ATI" ?

[crazyeyesreaper]

indeed i did woot woot and yea love the pictures with 50k watermarks lol i should photoshop them out for shits and giggles

[_JP_]

Originally Posted by Atom_Anti

Because the 512bit would drive the cost up significantly and nobody wants that to happen. It is already makes 204,8 GB/s bandwith with 256bit bus and 1600Mhz GDDR5. That is pretty awesome, isn't it? or need more?

By "nobody" you must be referring to the consumers, because the manufacturers don't care how much it costs, as long as it translates in profit (the HD 5970s go up to $1.2k, so m'eh).
And every generation of graphic cards improve on one aspect or another, but mainly to increase the total performance, compared to a previous gen. So to answer your questions, yes it is pretty awesome and NEEDZ MOAR!!

[WarEagleAU]

Sweet, some specs and eventual reviews will be lovely.

[DrPepper]

Wow these pictures give me a semi

[overclocking101]

Originally Posted by DrPepper

Wow these pictures give me a semi

http://www.spacecraftmfg.com/images/...erior%20MH.jpg

thats thebest post in the entire thread! to me it just seems odd. with the size just and all from 4XX to 5XX but having it the same for 6XX?? these pics to me are nothing but photoshopped pics. ut chiphell was the first with leaked photos of the 5XXX cards. but amd going back to RED pcb?? yuck.

RED PCB? yuck! i hope not.

[mtosev]

Originally Posted by btarunr

There is no 512-bit memory interface. It's 256-bit, but making use of 7 GT/s memory chips (so one can expect 30~35% increase in memory bandwidth over Cypress). Don't refer to Wikipedia for unannounced products without any citations. They're usually some fanboy's wetdreams.

are the launch dates on wikipedia correct or are they also inaccurate?

[cheezburger]

Originally Posted by btarunr

There is no 512-bit memory interface. It's 256-bit, but making use of 7 GT/s memory chips (so one can expect 30~35% increase in memory bandwidth over Cypress). Don't refer to Wikipedia for unannounced products without any citations. They're usually some fanboy's wetdreams.

last time i heard from some nvidiot reply these kind of comment on hd5xxx spec few years ago(2008?). most of them said "amd is risk in financial trouble, they wouldn't bother add more ROPs on rv870. only thing they would do is add more shader" however these nvidiot end up disappointed as cypress has 32rops rather then from previous prediction of 16 rops. but it ends up these nvidiot criticize cypress was a dual core gpu rather then a completely stand along gpu die...these endless argument continuous even in today

when the architecture change and die shrink process continuing evolve there's no reason to stick with narrow bus. especially there's still plenty of room for 512bit bus in 40nm and most of die area in hd 5000 had been "wasted" by "5D" shader structure as 5D require more hard wiring than 4D. a cypress had 1600 shader pipeline can only form of 320 shader block, which only equal to 320 shader core in 5D architecture but 4D art it would only require 1280 shader pipeline to form 320 shader block and may reduce the die space from unused 320 shader unit(1600-1280=320) and many of unnecessary hardwiring because of bad architecture that descended from r600. as for 512bit bus x2900xt did fall hard when introduce it. but that was 3 years ago while fabrication was still at 90/80 nm. i meant how big can a 512bit ram controller be? 40nm is good enough to contain 512bit bus even with current setup of 5D structure from cypress while still remain within 400mm^2.

so why need to putting 512bit bus? because there is speed limit in GDDR5, also high speed ram comes with greater latency and more unstable which also will reduce the ram chip life cycle. also greater ram timing cause huge performance hit as well. a 7GT GDDR5 dont exist! that means each data rate has to be 1750mhz! the physical limit of single rate ram speed is 1400mhz(according from tom's hardware). unless amd can bring up next gen GDDR6 (octet "x8" data rate) or it will be impossible to make a 7GT ram with exist quad data rate GDDR5.
this is the reason why amd has to move forward from 256bit to 512bit.

[mastrdrver]

Originally Posted by _JP_

By "nobody" you must be referring to the consumers, because the manufacturers don't care how much it costs, as long as it translates in profit (the HD 5970s go up to $1.2k, so m'eh).
And every generation of graphic cards improve on one aspect or another, but mainly to increase the total performance, compared to a previous gen. So to answer your questions, yes it is pretty awesome and NEEDZ MOAR!!

Since manufacturers care about profit, it benefits them if ATI only uses a 256 bus because the board will be less complicated and therefore cheaper to make. So yes, they do care how much it costs. Why do you think low end boards are so cheap if they don't care about costs?

Fwiw why would they need a bus larger than 256? If they do put those 7 Gt/s GDDR5 memory chips on these board then N.I. will have a bus load of bandwidth compared to Fermi. If those GPUz shots are correct, then they increased the bandwidth by ~33% and achieved a bandwidth higher than Fermi with less bus width and probably a cheaper board making the end product we buy at retail cheaper.

[cheezburger]

Originally Posted by Atom_Anti

Because the 512bit would drive the cost up significantly and nobody wants that to happen. It is already makes 204,8 GB/s bandwith with 256bit bus and 1600Mhz GDDR5. That is pretty awesome, isn't it? or need more?

Originally Posted by mastrdrver

Since manufacturers care about profit, it benefits them if ATI only uses a 256 bus because the board will be less complicated and therefore cheaper to make. So yes, they do care how much it costs. Why do you think low end boards are so cheap if they don't care about costs?

Fwiw why would they need a bus larger than 256? If they do put those 7 Gt/s GDDR5 memory chips on these board then N.I. will have a bus load of bandwidth compared to Fermi. If those GPUz shots are correct, then they increased the bandwidth by ~33% and achieved a bandwidth higher than Fermi with less bus width and probably a cheaper board making the end product we buy at retail cheaper.

1. cayman is exclusive for high end market so they don't really care about pcb layout
2. 7GT GDDR5 don't exist the highest you can go is 5GT(1250mt per rate)
3. high frequency ram comes with higher latency compare to lower frequency ram and high clockrate will make ram unstable and generate heats.
4: no matter how complicate that 512bit layout would effecting on PCB layout it would make cayman far cheaper than g100 in production due to the difference of die size. (400mm^2 vs 576mm^2) larger die require more layout on pcb board than what bandwidth bus impact in pcb design.

[mastrdrver]

Originally Posted by cheezburger

1. cayman is exclusive for high end market so they don't really care about pcb layout
2. 7GT GDDR5 don't exist the highest you can go is 5GT(1250mt per rate)
3. high frequency ram comes with higher latency compare to lower frequency ram and high clockrate will make ram unstable and generate heats.
4: no matter how complicate that 512bit layout would effecting on PCB layout it would make cayman far cheaper than g100 in production due to the difference of die size. (400mm^2 vs 576mm^2) larger die require more layout on pcb board than what bandwidth bus impact in pcb design.

1. and Barts is exclusive for middle of the market so what? Just because its high end doesn't mean you can blow money on things that are going to go to waste
2. What?!
3. Graphics don't care about latency. Bandwidth matters with gpus not latency.
4. The real question is why make the pcb cost more when you can achieve the same thing with less bus width?

Another reason there is no need for a 512 bus with 7 Gt/s ram is because you have the R500 all over again with excess cost going to something that isn't ever going to be fully utilized. Why not save some money (and die space room) for something that is going to be more beneficial or just pocket the savings all together and relay it to the end user in retail price?

[buggalugs]

Originally Posted by cheezburger

2. 7GT GDDR5 don't exist the highest you can go is 5GT(1250mt per rate)
.

You keep saying that but i dont think its true and it doesnt mesh with the GPUz screenshot. It it were 512 bit theres no way it would be running at 1600Mhz.

I've read GDDR5 can reach 7GT/s but anyway you have your opinion but i think you're wrong and it will be 256bit.

On a different topic with all those connections it looks like we might have eyefinity without the need for active adapters.

EDIT:

Originally Posted by mastrdrver

1.
2. What?!

Thanks, i knew i read that somewhere.

[cheezburger]

Originally Posted by buggalugs

You keep saying that but i dont think its true and it doesnt mesh with the GPUz screenshot. It it were 512 bit theres no way it would be running at 1600Mhz.

I've read GDDR5 can reach 7GT/s but anyway you have your opinion but i think you're wrong and it will be 256bit.

On a different topic with all those connections it looks like we might have eyefinity without the need for active adapters.

it's well known that older gpuz cant utilize newer gpu, I don't need to bring any example. GDDR5 exceed its limit unless you telling me that someone had tweak it to 1.6gt per rate or this is just absurd..

Originally Posted by mastrdrver

1. and Barts is exclusive for middle of the market so what? Just because its high end doesn't mean you can blow money on things that are going to go to waste
2. What?!
3. Graphics don't care about latency. Bandwidth matters with gpus not latency.
4. The real question is why make the pcb cost more when you can achieve the same thing with less bus width?

Another reason there is no need for a 512 bus with 7 Gt/s ram is because you have the R500 all over again with excess cost going to something that isn't ever going to be fully utilized. Why not save some money (and die space room) for something that is going to be more beneficial or just pocket the savings all together and relay it to the end user in retail price?

1. barts IS provide exclusively for mid range market, if you look on die size and and other spec such as rops/tmu/shader/ram bandwidth/bus. and most important is it support 256bit bus with crazy ram speed of 1.3gt per rate. now you telling me that cayman is also 256bit as well? amd about PCB layout a standard reference 5870 PCB is capable to contain 512bit bus(yes 12 layer! some non reference PCB may made of even 15 layers ) while cost far less than gtx 480's 10 layer PCB. so 512bit controller doesn't going to make more production cost. the only fact is the GPU die and that is why g100 is so screwed in this rate.

2. the 7GT GDDR5...it is not stable. even the news was announce back in 2008. where are they?

3 graphic card dont care latency... hmmm guess you never try nibitor and nvflash...a standard GDDR3 cycle timing is 35. while under the same clockrate i turn it to 50 then interesting things happen. when i test the 3dmark06 it end up having artifact(it wasn't really the hardware issue, ,more like the ram can't keep up with texture fill rate) and spike lag. now you telling me latency is not important?

4 market position, more bus width, more flexibility to encounter the counterpart's next gen. also bigger bus takes advantage on AA/AF/MSAA setting

[crazyeyesreaper]

look no matter what no one really gives a shit cause its all smoke and mirrors with images that have logos plastered all over them everyone just needs to sit down and shut the **** up and wait for more info arguing about specs that don't exist yet for a gpu that isn't available for us to purchase is asinine lets just wait to hear the official info from the source thats not FUD and go from there

[buggalugs]

Originally Posted by cheezburger

it's well known that older gpuz cant utilize newer gpu, I don't need to bring any example. GDDR5 exceed its limit unless you telling me that someone had tweak it to 1.6gt per rate or this is just absurd..

Obviously you dont read links.

"Hynix had announced its plans to introduce 7 GT/s GDDR5 chips back in November 2008. The company is known to commence volume production of the 7 GT/s chip by the end of Q2 2009."

[cheezburger]

Originally Posted by buggalugs

Obviously you dont read links.

"Hynix had announced its plans to introduce 7 GT/s GDDR5 chips back in November 2008. The company is known to commence volume production of the 7 GT/s chip by the end of Q2 2009."

end of Q2 2009. now where are they?

and even if they do have this high speed ram won't nvidia just get the same with their new improved g104? plus they have bigger bus compare to any of amd's current line. don't tell me about the bang for bulk, the high end market don't care about these little money. hell they still buying fermi without caring how many pale bear die each day! main stream market? sound like screaming from amd's cpu that was beaten so bad by intel's line. remember! high end market might see little compare to mainstream, especially after the great depression. but high end product represented the engineering leadership crown that would caught investor's eye. why nvidia is still around after 7 quarter straight loss? because there are many investor still back nvidia up. while amd/ati has completely no support. if they want more fund they better bring the flagship line. like intel with its 980x.

PS: that gpu mark is fake.

[crazyeyesreaper]

uh how does Nvidia have bigger bus nvidias top gpus are already out and the 320bit + bus dosent really slaughter there 256bit competition the 475 and 485 wont be THAT much better then what they have probably more effiecient yes but if the above 2 are way better they cant move old stock fact is any card nvidia comes out with right now wont use the ram because there releasing LOW END CARD to shore up there market share and how does AMD/ati have no support last i checked they now control more of the GPU market then Nvidia meaning there top dog in sales market share everything currently. and the only GF 104 avaible is a 460 and oh wait its only on PAR with a 275/285 in most games and DX11 is still pretty much a joke currently as much as i love the features it offers.

Basically what im saying is your cant win this argument so you dropped it and tried to pick a different way to do the same thing troll elsewhere this is AMD gpu thread lets keep it as such.

but on top of nvidia investors if there so well off why did XFX jump to AMD and decide to say F off to the 400 series why is BFG bankrupt and now gone the way of the dodo those are some seriously losses from what i can see. There still around because ATi is still around takes more then a few losses to cause a company to fail.

example AMD has been in the hole or playing second fiddle since around 2005 there still here ATi has been playing catch up to nvidia for years untill the 4000 series. Point is just cause they have losses dosent mean jack shit. Theres a Thing called credit line and these huge corporations have huge huge lines of credit to keep moving forward and to keep there doors open "You dont get rich saving money" "You cant make money without first spending money"

oh another tid bit last i remember AMDs stock was going up up up and Nvidia was on the decline meaning more investor confidence in ATi/AMD and less in Nvidia

[buggalugs]

Originally Posted by cheezburger

end of Q2 2009. now where are they?

.

The 5XXX series was released in 2009 so it was designed in probably 2008 long before 7GT/s memory was available. Nvidias gpus are much the same.

Add to that the memory company wanting to move old stock first and now we are in late 2010 with 7GT/s memory available and a new design ready to use it.

Originally Posted by cheezburger

the high end market don't care about these little money..
.

Its not so much about money. Its about power consumption and temps. AMD understand we dont want hot and power hungry GPUs. Nvidia havent listened to us yet.

[cheezburger]

Originally Posted by crazyeyesreaper

uh how does Nvidia have bigger bus nvidias top gpus are already out and the 320bit + bus dosent really slaughter there 256bit competition the 475 and 485 wont be THAT much better then what they have probably more effiecient yes but if the above 2 are way better they cant move old stock fact is any card nvidia comes out with right now wont use the ram because there releasing LOW END CARD to shore up there market share and how does AMD/ati have no support last i checked they now control more of the GPU market then Nvidia meaning there top dog in sales market share everything currently. and the only GF 104 avaible is a 460 and oh wait its only on PAR with a 275/285 in most games and DX11 is still pretty much a joke currently as much as i love the features it offers.

Basically what im saying is your cant win this argument so you dropped it and tried to pick a different way to do the same thing troll elsewhere this is AMD gpu thread lets keep it as such.

but on top of nvidia investors if there so well off why did XFX jump to AMD and decide to say F off to the 400 series why is BFG bankrupt and now gone the way of the dodo those are some seriously losses from what i can see. There still around because ATi is still around takes more then a few losses to cause a company to fail.

example AMD has been in the hole or playing second fiddle since around 2005 there still here ATi has been playing catch up to nvidia for years untill the 4000 series. Point is just cause they have losses dosent mean jack shit. Theres a Thing called credit line and these huge corporations have huge huge lines of credit to keep moving forward and to keep there doors open "You dont get rich saving money" "You cant make money without first spending money"

if 275/285 have GDDR5 they will smoke gtx 460. and xfx was kicked by nvidia by violated NDA agreement. not because xfx like amd...

"You cant make money without first spending money" that was what intel was doing while amd enjoy its success that is what happen where it destroy amd in 2006. they wanted to SAVE money on R&D and slow the development and enjoy and stay their success while just try to get the cash from market. until core 2 came up amd merely had any backup plan because the idea of saving money!made them loss both market share and investor. if a company really want to save
money. cut the employee benefit first. amd has long history of lavish treatment to their employee and company spent billions just for lunch... same time intel would forced layoff any based engineer that's over 45 yrs old. no lavish spent and well organized. that is why intel is on the top. like 3dfx in the past these european manage style have to change. if you talking about saving money american style company like intel/nvidia would rather spend all of fund on project development than employee's lunch list...

oh another tid bit last i remember AMDs stock was going up up up and Nvidia was on the decline meaning more investor confidence in ATi/AMD and less in Nvidia

i also remeber they say these to ati back in fx era...but nvidia back up and slam ati really hard with nv40 and g72.

Its not so much about money. Its about power consumption and temps. AMD understand we dont want hot and power hungry GPUs. Nvidia havent listened to us yet.

how do you define the term of "power consumption"? and how hot can a 400mm^2 gpu be? well it is still far better than gtx200 and fermi's 576mm^2 (even in extreme case cayman would have 2/3 smaller than g100 and still have 512bit bus)a 64 rops 80 tmu and 1280 shader cayman will comsume more power than cypress indeed but will still be far better than gtx 480