Printable View
info ist just bull:banana::banana::banana::banana:, come on guys. We have already seen the tesselation performance on slides, it's 2times 5870 in most cases, but maybe you can tell me how they get 4 times better performance out of two times better tesselation performance?
http://h-3.abload.de/img/fot_014vedr.jpg
I think i've to go to some forums and also write my performance estimates and write i've sources at amd, looks like most here would believe it.
Its 6970 not 6990.;) And yes, I can speak Russian, and translation is accurate enough to understand it.Quote:
Originally Posted by Dezmen
Concerning trustworthiness of that info, maybe something is exaggerated, but IMHO not all is BS.
I don't say it's true or not, but the big problem of the Cypress for Tesselation was one of data-flow: ( I will quote Beyond3D article ):Quote:
Originally Posted by AffenJack
they try to keep some data in shared memory (as far as we can see, they try to keep HS-DS pairs resident on the same SIMD, with hull shaders being significantly more expensive then domain shaders) but data to and from the tessellator needs to go through the GDS. There's also the need to serialise access to the tessellator, since it's an unique resource,.
Ok now with 2 GPE ( one for each Group of SIMD ), this cycle can be executed in parrallel, speeding the process to at least 2-3x ...
But this not all... this remove too a bad bottleneck who was completely slow down Cypress in some particular tesselation case .
I quote again Beyond3D article:
This hints at Cypress having to go through a slow path in this particular case (or rather, it hints at the existence of a small dedicated cache/buffer for system values,
that gets thrashed with larger triangle sizes as the bottleneck shifts towards the last stage of rasterisation).
As it seems they have solve those problems, the result can end pretty high in some situation ... where the gpu no more face this.
The slide you have put, don't show how fast will be the 6970 vs 5870 in a game with tesselation, just how much faster is the 6900 for calculate 8-10-12-32 pixel/triangle vs Cypress .
A case where the performance of the cypress was completely killed by the problems find by Beyond3D, will see a bigger performance jump, as the gpu will now work with his full potential in those case and
not only cause the tesselation is 2-2.5x faster).
You can compare it of what happen in the case of a CPU bottlenecking your GPU, you decrease the resolution and the fps don't move, you OC your CPU, and the fps will now make a jump..
But i m right with you, i don't really believe the numbers given on this russian forum...
(excuse my english, not my first language )
20% over 5970 might be in the realm of possibility, but since those 2.5x and 3-4x tessellation performance was mentioned I'm more inclined to believe this is just some random bs. Of course those numbers are possible in certain scenarios, like when 1GB isn't enough, but then it doesn't really matter, the perf difference is meaningful in playable limits only.
My bet would be about the same perf as 5970 for 6970. Kinda like 6870 is almost the same perf as 5870.
Do you see tesselation not utilized in games and underperform?Quote:
Originally Posted by AffenJack
Do we need more tesselation performance in current gen cards?
Yes it's nice to have, but its just another marketing checkpoint that dosent really matter. Maybe next year when new consoles come out tesselation will get more utilization, but I still doubt that we will see anything comperable to Heaven extreme mode in the upcoming years, which again is only a syntetic test.
Furthermore when we get to that tesselation levels used in games todays graphic cards wont be enough to run them anyway. To sum up tesselation is currently not a buying decission factor IMHO.
Like Lanek wrote, 2x better in tesselation synthetics doesn't mean it can only be 2x faster in real world gamesQuote:
Originally Posted by AffenJack
For instance, consider games where the GTX580 is far faster than Cypress - we know that the 580 is typically 40% faster, but in some games where tesselation is maximized, the GTX580 is in playable fps ranges (say ~30fps) whereas Cypress is brought down to 10fps. It's not at all impossible to be 3-4x that for the 6970 if tesselation was what was brigning Cypress to its knees, and now tesselation is done differently and so the rest of the GPU can still process the rest of the game.
Doesn't mean the 6970's numbers aren't fake, or that the numbers are when the game is unplayable as is (4fps -> 16fps is 4x faster, but irrelevant in the real world), but 2x faster in tesselation doesn't mean in game can't be more than 2x faster since a GPU is doing a lot more than just tesselation in a game, and being free from doing tesselation may speed up the rest of the game as well
2 weeks to go.
start your engines.
ready to rumble.
Place your bets.
gloves off.
driver on its way out to partners, cards to follow.
I think that example is invalid since 580's pure tessellation capability IS, in fact, a couple times that of Cypress'. A 10x tessellation advantage might not translate to games unless there is a pure tessellation bottleneck.Quote:
Originally Posted by zerazax
But that's the focus on the example - it's that Cypress being worse can hit a bottleneck a lot earlier and may cripple the rest of the card's performance, whereas being faster in capability may make the card many times faster than the tessellation performance aloneQuote:
Originally Posted by hurrdurr
omg this thread is ridic, when will it end :p
it will never end!
it's a vicious cycle of rumors and rants.
all we need is a single news release from AMD to end this madness.
No, actually it will. 7-13 December ;)
If it doesn't get delayed again.
great! 6900 is faster in tesselation! now show me some games that use tesselation properly and i might buy one, what do you say? there arent any? but... but... then whats the point? :p:
I'd love to see a game thats a proper poster child for DX11 but as far as I'm concerned such a game has yet to surface. I'm mostly worried about performance in titles today personally. Sure it will be nice when more DX11 content makes its way to the market (summer next year perhaps... ) to have solid hardware available but I remember with both my 8800GTX and later on 8800GTS 512s that I never felt there was a DX10 title worth its salt in those cards lifetime ( ie one that didnt incure a large performance penalty or being worth the hit visually ) It wasn't until I had my 4870x2 that felt running most DX10 games were playable.
I'd love to see this 3 - 4 times increase but odds are this is best case market speak. Even 2x would make it competitive so anything beyond that is just gravy.
Exactly what I was saying! :rolleyes:Quote:
Originally Posted by saaya
Current games hardly use the hardware that's already on the market including tessellation.
that's because almost all of them are made for consoles with its 2 (or more) year old hardware.
sorry for off-topic.
With the possible exception of Crysis 2 expect DX11 games when PC GPU's are at DX13/14 level and consoles have DX11 capable GPU's in them.Quote:
Originally Posted by Chickenfeed
Generally speaking and with very few possible exceptions, (none come to mind at the moment) PC games are not developed any more. Console games are developed and then ported to the PC, sometimes a DX10/11 code path is tagged on as an after thought.
Back to topic.
2x HD6850 have 1920 SPs as well as rumored for HD 6970.
However, tests show, that 2xHD6850 are on a par with HD 5970.
So, we can conclude that in case HD 6970 has 1920SPs, it will perform as HD 5970, or even better(don't forget higher clocks ;) )
2x HD6850 have much higher VRAM bandwidth, though.
And we don't know for sure whether everything gets doubled or not.
It's all speculation...
Not only clocks. Donīt forget new 4d architecture, more TMUs, 2 tesselation units, more VRAM.Quote:
Originally Posted by SpuTnicK
If it perform's like xfire 6850's. I am pretty sure they would have released it already. Paper launch or not, it would have put a pretty strong damper on the gtx 580 launch in addition to raise the 6xxx namesake, to increase sales of the 68xx cards even further.Quote:
Originally Posted by SpuTnicK
They are not going to double everything unless they want the card to consume 300 watts + be 500mm in size.Quote:
Originally Posted by Dami3n
I think the 3-4 tesselation performance is bull:banana::banana::banana::banana:. Synthetics show the greatest difference in tessellation performance. People rationalizing that Cayman could be 2-3 faster in synthetics and even faster in games by the vagueness in the rumors shows how misplaced their rationality is.
Synthetics are coded to specialize in showing maximum prowess of a certain aspects. Drivers are specifically coded for them to maximize performance, hence why Nvidia kept on bragging about unigine heaven.
We won't see faster tessellation in games compared to synthetics. Be rational people.
According to latest slides (from Nov. 22nd). 4d is similar to 5d performance. Number of ROP number has not changed. TMU number for HD 6850 is 48. HD 6970 will have more than 80 (according to slide.) which is almost double. Double the vram (2Gb), but less likely not memory bandwidth:D
That's only going to matter if the bandwidth is necessaryQuote:
Originally Posted by zalbard
didnt the scaling of the 6870 depend mostly on bandwidth? cause it was given some cheap stuff, and i know we cant speculate on how 4D reacts to bandwidth based on 5D numbers.
not if they need a complete driver rewrite to show it at it's best, they get one shot at a launch most sites don't review a second time for new driversQuote:
Originally Posted by tajoh111
6850 is extremely inefficient in terms of mem BW usage (mem BW scaling is better than on cypress), i bet that Cayman will have a significantly more efficient memory controller like cypress did and will make up for the rest with a higher mem BWQuote:
Originally Posted by zalbard
They only need the driver rewrite if it doesn't performs as high as they wanted. That is, beating a gtx 580.Quote:
Originally Posted by bill_d
From a hardware perspective, I think the 6970 has the innards of a card that can beat a gtx 580. But it isn't going to be super easy and I think the delayed launch meant that it might have not won that battle and drivers are going through heavy revisions to get it to that level.
From how a few reliable rumors leakers from AMD side were going on, it seemed like AMD could have released the 6970 the same week as NV released the gtx 580. Something tells me AMD delayed it because the card probably beat a gtx 480 but not a gtx 580.
I'm confused here. Is a 4D arrangement with 1600 SP (with 400 per section) or one with 1280 SP (with 320 per section same as 5870) perform similar to a 5D like the 5870 that has 1600 SP (with 320 per section)?Quote:
Originally Posted by SpuTnicK
320x4 would perform similar to 320x5. So, 400x4 would be ~25% faster. Now shader performance isn't everything so unless other parts are beefed up these 25% is in best case.Quote:
Originally Posted by xBanzai89
Ok thanks for clearing that up. I've just been a bit confused, since I have seen people on forums saying that.Quote:
Originally Posted by -Boris-
The only official thing I've seen regarding 4D performance is "the same performance as 5D while using 10% smaller sized die".
Why do people keep insisting its performance? First people think they can juts change BIOS and clocks within 3 weeks, now people think drivers are going to give a significant boost in 3 weeks rather than over the course of months? Those would have to be a hell of a driver change to get the card from 480 to 580 levelsQuote:
Originally Posted by tajoh111
Far and away the most likely issue is components or manufacturing delays for the timeframe we are talking about at this point.
They've said that Barts used Redwood's mem controller. Cypress is significantly more complexQuote:
Originally Posted by generics_user
I'm with you here. If driver improvements that magical were possible in mere weeks, i'd think they've been holding out on performance intentionally.Quote:
Originally Posted by zerazax
Hopefully we get a clear and honest answer when launch time comes.
Right on. I think beating the GTX 580 is AMD last concern right now, plus they still have the world's fastest graphics card HD 5970Quote:
Originally Posted by zerazax
AMD strategy is to make smaller and cheaper chips and get the top performance card with dual GPU, if they beat the GTX 580 with smaller chip it would be just a bonus and something Nvidia would have to worry more about.
Shouldn't AMD's upcoming parts be designed to compete against what nv would have had on the market if they wouldn't have screwed the pooch? 580 is basically what AMD planned on competing with last generation. so what will nv have to compete with AMD's next gen, ie Cayman?
Not really one hell of a driver, but more like rewriting the driver to use the new architecture.Quote:
Originally Posted by zerazax
I actually agree with you on this.Quote:
Originally Posted by cegras
There's been no tech news of note recently, the forums have grown so stagnant ... even Engadget is quite the zzz.
The software and hardware teams works together from day one when designimg new architecture, there is no such thing like rewriting to driver in last minute and getting some huge improvements like from faster than GTX 480, after rewrite faster than GTX 580 as somebody said, that is complete nonsense.Quote:
Originally Posted by cegras
I believe more the zerazax argument in post #1633 this thread, after all there were few rumor post about it.
AMD has nothing to gain to hold back the cards if the product was ready.
I blame Dr.Mos :bananal:
Well if the GTX 580 was ready last year (actualy it was supposed to be GTX 380) AMD had the HD 5970 to compete and they still do.Quote:
Originally Posted by flippin_waffles
That's not how the software side of things gets developed, unless AMD is really that bad with their development. Again, these things don't get rewritten with just 3 weeks to go, when the product has been in development for over a year. This isn't some phone application...Quote:
Originally Posted by cegras
And It`s multi-GPU card . In one place of game you've got 80% scaling that in the second place fell to 30% scaling + .Quote:
Originally Posted by Heinz68
The gameplay is smoother on the GTX480 than on the HD5970, there is no FPS drops
I hear for about half year how great the Nvidia cards are in tessellation and how the AMD cards sucks and now when the AMD improved the tessellation performance it's all about synthetics, what a waste AMD.Quote:
Originally Posted by tajoh111
The fact is AMD had to improve the performance because Nvidia is getting more benchmark and now even game benchmarks. LINK
Anyway 3-4 faster tessellation was somebody post on some Russian forum and everybody knows that is baloney since the AMD slides show 2-3 faster.
I'm not going to comment on the rest of the post since it was already discussed in this thread, no need to repeat.
Sure it is much smoother at least untill Nvidia gets the dual GPU card, maybe you should tell all the people how Crossfire and SLI sucks, I bet most of the real users want agree with you.Quote:
Originally Posted by Maxforces
:rolleyes: The 5970 minimum frame rate is still on par with the 580GTX. The 5970 is still the best single slot card out there. The 580GTX is last year's news. For those of that have had the 5970 for a full year the 580GTX is too little too late. You can make a 5970 run at 5870 speeds no problem with a clock and voltage bump.Quote:
Originally Posted by Maxforces
Few more weeks and we will know if Cayman has a good bite:D
I could not wait to play all the new console ports that are out so I opt out for 460.
Considering nvidia's supposed 20-30% gains over their driver releases, I'd say things aren't as perfect as you think, physical silicon being different from simulation being a key factor.Quote:
Originally Posted by zerazax
Yes.... OVER their driver releases. Meaning, this is often over many many months + working with developers to optimize their codeQuote:
Originally Posted by cegras
Not a three week project
yeah but its quite possible that there was a delay in their driver work...Quote:
Originally Posted by zerazax
it actually would make sense if the driver isnt showing the full 4d potential yet, but the performance of the 6800 cards was good enough already, so they went ahead with the launch, but the perf of the 6900 isnt where it should be just yet, so they delayed it...
that WOULD mean that once the 6900 launches, 6800 cards will actually see a notable boost as well, probably 5-10% i guess?
its just a theory...
No, 6800 is a 5d design. If drivers would be optimized for 4d then 6800 would see no benefit.Quote:
Originally Posted by saaya
Absolutely agree. 5970 owners need to wait until Anthilles/595 come out, in the next year. 580 is good choice for single-gpu owners (5870/480).Quote:
Originally Posted by safan80
Forget that, 5970 owners need to wait until 28nm or 7xxx or gtx 6xx cards before they want to upgrade.Quote:
Originally Posted by Kimofil
The 5970 is underutilized in most games and is overkill for anything that is not an eyefinity setup.
But if your making a new card purchase now, most if not all reviewers are giving the nod to the gtx 580 over the 5970(even with a 500 dollar price) because future support is going to be much better and their are still erratic games as f1 2010 demonstrate in the hardwareheaven and Hardocp review show. This should be extremely embarrassing considering this is an AMD branded game and the game has been out for 3 months.
The gtx 580 is not that crazy good. Its good enough for this generation and so is the level of performance offered by the 5970. Cards that are alot faster are not needed for anything other than eyefinity and maybe crysis 2.
erratic ? F1 2010 ? No problem with CFX support there.. 2x 5870 1920x1080 8xAA - DX11 fully enabled and max settings..... 97fps average min 86fps ... work with 10.10>10.10e and 10.11 driver ( last CAP ofc).
Never got any problem with CFX + F1 2010 .. I don't have any visible bug due to GPU /driver( ofc with the patch DX11, before, by modding the registry to DX11, they was the light+texture in some race, nothing to do with driver, just the game was not ready ).
The only thing i can suggest to them and to all peoples who have got problem after have use a modded config file for DX11 settings ( and a lot have got this problem ) the fix is easy.... Delete the config files, launch the game, let the game create a new one, reapply the patch DX11.
CFX was even working before the DX11 patch, in DX9 or with DX11 modded files, the bugs was come from Codemaster who have not finish to debug completely the DX11 ( it's why the game was not released with DX11 enabled )
Quote:
Originally Posted by tajoh111
While I agree that 5970 owners can wait (at least those running 1920x1200), I disagree about faster cards not being needed. 1920x1200 is cpu limited in most cases these days, but 2560x1600 is not. Check the performance of BF2:BC and Metro at 2560x1600, in most reviews the frame rates are a joke even with SLI 580s. Not only do we still need faster cards, but we also need more video memory. At my res (2560x1600) 1GB or 1.5GB per gpu just is not enough we need 2GB of video memory. Games at 2560x1600 in a lot cases minus direct console ports are fully loading the 5970 no problem, even playing the new Need for speed: HP I've experienced the Need for more video memory and it runs both gpus at 98-99%. For the 5970 user the GTX580 is a lateral move not an upgrade.
edit: As for F1 2010 it's made by Codemasters, not known for testing everything out before they ship. However, they do make patches.
This 5970 has served me well for about a year now and I am ready to play with something even better. "Need" hardly factors into the equation. If it did an honest appraisal of my needs I would conclude that I don't even need a desktop computer. But what I WANT to do is some serious 3d image z-stack deconvolution, fold some proteins, and murder lots of virtual people in as much gory detail as possible - and I want to do it on the best hardware I can afford.
I had 5970 for a couple of months. Honestly I must say that CF/SLI setups' FPS numbers shouldn't be compared to single card FPS numbers. In a lot of games I couldn't believe the FPS FRAPS was showing me. It felt like 30 FPS but it said 50-60 FPS. This happens much less frequently with single card setups. I guess it has to do with frame time synchronization between two GPUs. So, between 5970 and 580, I'd take a 580 ANY day over 5970 unless the latter is substantially cheaper.
I am cpu limited at 3.2ghz in BC2, I gain 30fps at average going to 4.2ghz.Quote:
Originally Posted by safan80
Playing at 5760x1080.
i highly doubt this, 5870 doesn't show any difference at all between a phenom II 1055T and Core i7 980X in almost every review out there...Quote:
Originally Posted by flopper
i also fail to see a significant difference between my overclocked CPU (4050core/3000nb) vs a stock 1055t (2800/2000)
BF:BC2 is highly multi-threaded and supports up to 8 threads AFAIK (one side effect of being a console ports, PS3 has 6 SPEs + PPC core and 360 supports 6 threads!
3 weeks is almost a month, and in time for perhaps an incremental driver upgrade.Quote:
Originally Posted by zerazax
must not be a lot of mmo players here, quite a few cards choke with the eye candy turned up even at 1920x1200 with 0x-4x AA and 8x AF, and they are fairly sensitive to processor speed.
You play on 5760X1080 with a HD6850 1 GB ?Quote:
Originally Posted by flopper
BC2 does like fast cores, but it's not the end of the story. 12 cores at 2.4 GHz did fine for me, but 6 cores at 4.4 GHz did a LOT better in terms of responsiveness when I played under dry ice. Video card wise, I found eyefinity unplayable at 4800x1200 even with two 5850s and a 1090T at 4.1 GHz.
few days left and still no info god damn it what kinda nda is this anyway
The normal type?Quote:
Originally Posted by eric66
amd nda is serious business
Way too serious, not many leaks. The only good news is that we wont have many people in China jumping from the windows. j/kQuote:
Originally Posted by Loque
yeah, despite the fact that we're 2 weeks over the original launch date all we know for sure is that it's going to have a 256bit bus and a 4d shader design...Quote:
Originally Posted by Loque
Yeah but its still modifyed arch compared to HD5 series.Quote:
Originally Posted by -Boris-
Compared to HD5870, HD6870 is about same in tesselation due it can do more per-clock than HD5870 with lower stream processor amount due its tweaked arch, this benefit is clearly seen in tesselation.
Turn Tesselation off and HD6870 will only see HD5870's tail lights.
Soon coming HD69xx is 4d desing.
i keep clicking on the "last page" hoping it would be the "last rumor" :)
http://translate.google.it/translate...n&hl=&ie=UTF-8
AMD has had a fine year on the graphics card market but in autumn it has lost some of its moments, not least by far more competitive solutions from rival NVIDIA. Now, the new performance series Radeon HD 6900 just around the corner, but according to sources at NordicHardware, it is slow.
AMD has already delayed the launch on one occasion , on 21 November was dumped in favor of some time during week 50. The reason for the somewhat vague release date is according to our sources to be the top model Radeon H 6970th AMD has just not been sure when to get the card ready for launch, and as recently as today - 1 December - there is no recognized launch date for the two graphics cards to be launched within two weeks.
The positive news we have reached is that the little brother, the Radeon HD 6950, started to find out from AMD and shipped to its partners. Which means that at least the entry model in the manufacturer's new series looks to be on the right track.
Big Brother Radeon HD 6970 is said, however, be a more uncertain short-and according to credible sources, we will immediately be excited about the launch actually takes place this year - and be prepared to wait until next year to see the cards in some form of reasonable availability. Radeon HD 6950 is said therefore to be in slightly better shape, but AMD will not carry any at the launch of the Cayman series until the Radeon HD 6970 is ready for the limelight.
While NVIDIA December 7 will launch its second performance card for this fall - the GeForce GTX 570th Although AMD has a broad and stable supply of graphics card you can see out to get a heavy end of the year in which, at worst, not getting any new performance cards on store shelves before Christmas. We follow the course development and will provide more information as soon as we receive it.
Disappointing if true. But remember that Nordichardware thought that Barts would have 960 shaders too. They could have some details right and some details wrong, just as with Barts.
To be completely honest, NH hasn't been on top of things for a long while. I also have a hard time believing that 6950 would be ready but not 6970, what would cause such issues? If it is the chips then it would have to be a yield issue which would take a lot longer to sort out. The boards should have been ready quite some time ago plus wouldn't have to take that much time to alter if they could use the already manufactured boards... Well, time will tell, only a week or so left.
If it doesnt match a 580 or better it in some benchmarks then why were they even bothering to launch a new product considering 580 is only around 20% faster than a 480, :(
AMD needs to do something for a refresh because TMSC royally screwed up with the next process node. So rather it being a revolutionary step it has become an evolutionary one. If that makes any sense.Quote:
Originally Posted by thebanik
GPU-Z SPs error or wavefront is still 80 (20 x 4) :confused:
http://www.dinoxpc.com/public/images...c55f3_6900.jpg
5870 (fillrates):
http://www.geeks3d.com/public/jegx/2...5870-gpu-z.jpg
AMD's own Fermi launch. Yikes pls tell me this isn't true.
GPU-Z is just a database, it doesn't know its actual units or any of that stuff. It can tell you clocks and that's about it - the rest needs to be filled in by w1z to calculate things properly
Quote:
Originally Posted by Gilgamesh
Quote:
Originally Posted by kadozer
They're just rehashing what other sites are saying - some of it outdated - so I'm not sure where they're getting their info from
I read a bit swedish, and it was translated badly in google translator.
What it actually says is:
6900 is just around the corner, but sources at NordicHardware says AMD's making slow progress.
580 has a die size of an elephant, I wouldn't expect 6970 to match it in performance but come close to it.Quote:
Originally Posted by thebanik
While on the other hand HD 6990 will take the performance crown from HD 5970.
If the performance is close and the price is much nicer then it will be a big win for AMD, again.
They just need to keep following this strategy imo. :yepp:
about NH article, taking in count 6950 follow surely the same path of 5850, with 2SIMD disabled, less clock, AMD knowing the 570 is around the corner,
if the card is ready and perform enough well for AMD in this segment ( 570 = +- 480 perf ), i don't really see why a 6970 with 2 SIMD more + faster clock is not enough. Even if the card is just 5% under the GTX580,
it's not really a problem ..
real reason why you post such a comment? die hard NV fanboy ????Quote:
Originally Posted by kadozer
no performance data known, no price range known, no power consumption known only few weeks delay yet you compare it with a product that was late more then 6 months, consumed way to mcch and was underperforming like hell.... yeah real die hard fanboy. :ROTF:
Thanks for the translation.Quote:
Originally Posted by andos
I bet I can learn quite a few languages just reading gpu rumors:rofl:
Yeah my post history shows I'm a diehard fanboy for NV. I also have a JHH poster.Quote:
Originally Posted by duploxxx
oh... i thought barts was 4d? why did they go 4d for cayman but 5d for barts then? wtf? :confused:Quote:
Originally Posted by -Boris-
I would say Barts was the pipe cleaner for 32 nm and Cayman the completely new architecture.Quote:
Originally Posted by saaya
Since now they are stuck at 40 nm... You get the picture. :rolleyes:
Barts might be a cheap replacement for 5770. A safe chip where only some of Caymans elements were tested, made to be out as soon as possible to battle GTX 460. Cayman being the flagship have a larger budget and a bit longer development time, and most importantly higher goals.Quote:
Originally Posted by saaya
I think GTX 460 gave AMD a headache, they could of course kill it off with 5870 at the same price level and still earn cash for every sold card. But that would undermine the market for 6800. GTX 460 was way to late to change any of AMDs design plans with 6800, but I think AMD knew that they needed the 6800 long before that to fill the gap in the most important price range.
Quote:
Originally Posted by Shadov
Dave Baumann, AMD, on B3DQuote:
Barts did not exist on the roadmap in 32nm. Barts in 40nm turned up before the 32nm cancellation.
Consider barts as cheap replacement for HD5770 and HD5830 card's, for its price its superior compared to HD5850/70 if you check price/performance ratio.Quote:
Originally Posted by saaya
This 5D arch is just optimized one compared to whats seen in HD58XX cards.
Quote:
Originally Posted by kadozer
ok so let me get this straight .. amd announced an announcement of an announcement announcing an announcement of the launch .... that will still get delayed???
and am i forgeting woodscrew gate too ... come on .. it cant be that bad ;)
I wouldn't put it that way. They say there are problems with the 6970 but they don't specify it further than that but they also say that when the card launches the availability will be bad. They also state the obvious by saying Cayman won't launch until 6970 is ready... Somehow though, the 6950 seems to be trickling its way to partners. As I said earlier, NH hasn't been anywhere near accurate anything regarding AMD launches the past year or two.Quote:
Originally Posted by zerazax
Do you feel lucky...punk?
http://lab501.ro/wp-content/uploads/...feellucky2.jpg
Any specific news that was so inaccurate? I remember that they was the only ones that reported about an 800SP RV770.Quote:
Originally Posted by marten_larsson
Well, their Barts stories were quite off. All of them. Also their initial RV870 rumours were off too (they were quite sure about the 2000SPs at first (after RV770 launch) then changed to 1200 before settling on 1600 not until August 2009).Quote:
Originally Posted by -Boris-
I have tried to google for misinformated posts but I just realized that a lot of their articles have been pulled when their info have been criticized by other respectable sites / forum members.
Monstru:
Are those Cayman?!
yes, I feel lucky.Quote:
Originally Posted by Monstru
Give it your best shot
Are those 6970's? If so, why so Accordion?
Well 6870 doesn't have a backplate so at least that's new.