If you notice, this is a theme AMD has been doing for a while, only the top of the line x8xx and x9xx gets a architectural upgrade each generation, while cards below gets one every other time.
57xx became 67xx(With the exception of 6790 which was a cutdown 68xx) from 56xx to 66xx we saw the upgrade being made to Turks 20% more shaders, UVD3 etc.
This time around the 67xx gets an 28nm upgrade to 77xx while 76xx is left behind. I don't like the fact that they change the name and don't add like the most basic of things, like a die shrink(One would think that it could improve their margins?) I think it's because the market these chips cater to work on a different wavelength than the high end does, that being said, it would be better if they didn't rename them, it sucks a little.
>If you notice, this is a theme [s]AMD[/s] nVidia has been doing for a while, only the >top of the line x8xx and x9xx gets a architectural upgrade each generation, while >cards below gets one every other time.
AMD has gone downhill in this respect. It's the same hill NVIDIA went down before, but maybe it's even worse. The rumours about the 7xx0 family has the 7890 card use the same chip as the 7950/70 and 7790 use the same chip as the 78x0, making it even harder to know from the name what the underlying tech is.
uh, Nvidia and AMD have gone down the exact same hill. I'm not happy about it (personally, rebrands are just bad and misleading period), but it's no different.
Precisely. The marketing department and the power the OEMs have annoy us all. The naming schemes have to go. We should protest by buying VIA chips. No, not really.
Agreed. If its an updated 6k series card, name it as such. The 7k name should only be given to the new graphics core. I vote tech sites boycott market names and just call these cards by their core names exclusively ;)
As is AMD, but I don't remember Nvidia ever releasing some GPUs with a new design and some with an old design using the same model numbers. At least they had the decency to increment the numbers.
Well, the Geforce 4 and and 4MX was confusing for a lot of people, since the 4MX was basically a Geforce 2.
The Geforce 4 MX was more like a Geforce 2 on steroids. The Geforce 4 MX advanced over the Geforce 2 in multiple areas like the then-new bandwidth and fill-rate saving technologies and in an improved memory controller. One of the larger issues with the Geforce 2 was how badly it was memory starved. This was evident when it was pitted against the technically inferior Radeon 7500 which had HyperZ to save on Fillrate and Bandwidth.
It was also able to hardware decode video which made nVidia comparable to ATI for the first time in that regard, this is something that the Geforce 4 Ti and Geforce 2 lacked.
ATI was also not immune to the "Re-Branding" issue. Take the Radeon 9600 for instance. It would go on to be the: Mobility Radeon 9600, 9700, Radeon x300, x600, x1050 with all the other variations like the Radeon 9550, SE and XT and others.
Plus... I remember reading awhile ago that 28nm was going to prove more expensive than 40nm for awhile, so with this in mind... The more cost-conscious segments will probably stagnate for awhile.
And nVidia hasn't exactly been competitive in the low end either as of late which doesn't help things, in fact... After the Geforce 240 GT and GTS they took a step backwards in regards to performance with the Geforce 430, 440 and 530.
A complete list to relive the full extent of the chicanery at and around that time. It is even more complex if you include the while 9000 and 9000M series as there's even more overlap.
Radeons have a while to go before they get THAT bad. But they're building up a nice head of steam, with 6970M/6990M parts which arent Cayman-like (i.e. VLIW4) at all, and 68xx parts which are just the same Junipers as 57x0 and 58x0M, and now these "new" 7xxxM parts ...
And I guarantee if Kepler runs late Nvidia will start doing the same thing...
I think that's largely why Nvidia's rebadges were justified in those cases, but not not so much with these AMD parts.
Nvidia has stayed remarkably consistent with their feature sets over a generation of GPUs, perhaps to a stubborn fault. They resisted DX10.1 on the majority of their parts as it would clearly bifurcate their product line and create inconsistencies and market confusion.
Not to mention their shader architecture today is also largely the same as G80. No small feat considering AMD is going on its 3rd major change in 2 years. So for the most part, the feature set and compatibility on Nvidia parts has remained the same while the price and performance regardless of rebrand has remained intact.
8800GT to 9800GT was a die shrink from 65nm to 55nm.
The other two parts were OEM only for the short-lived and incomplete 300 series. Technically the rebrand was justified as these were Nvidia's only DX10.1 parts and also the first to support limited HD audio and probably fit better in a 300 series rather than being lumped into the DX10-based 200 series.
I think that in old releases the low end cards were suposed to be usin oler vliw architecture. The reason is to allow crossfire between AMD APU chips and these new GPUs. The APUs use older vliv tecnology. GCN is coming to AMD APUs maybe in the next year (2013) if everything goes well, so AMD has to keep those old vliw cards in production at least as lon time... (actually longer, because they have to hava a crossfire option of those older APU's that are made today. We can only hope that these are 28nm... There seems not to be any information of that at this moment. If not, we have to stick 7700 series to 7900 series cards if we want to have upgrade of anykind. The only reason why they would use 40nm production is that TSMC don't have enough 28nm production capacity (it is possible) or that 40 nm are so much cheaper to produce (allso possible, but not in long run) One thing is sure. Even AMD 80xx series have some GPUs that are vliw based, because of the need for APU crossfire!
I can understand in this case the point of emphasis:
"The following is a list of some the important attributes and major features being introduced with Southern Islands. None of which will be available with the Turks based 7670."
That's a pretty big bullet list of missing features. In the past these kind of rebrands were understandable because the features and relative price and performance fell in line with newer generational offerings. Turks just really looks out of place in that 7-series stack mainly because AMD made so many changes with SI.
Another concern is they usually bump the rebrand parts or equivalent shader count parts down one hundred spots in their naming convention, but not this time. Are the % gains of SI already spread so thin at the top that there's nothing left to shave? Probably less complaints if this was a 7570 instead of a 7670, but as it is it'll be the same performance as last year's model with none of the new features while filling the same market position.
Rebrands are fine and all, but I want a 28nm mobile midrange. Something that seems unlikely to happen in the near future. I don't care if they simply shrink their VLIW5 or VLIW4 designs or update them with GCN. I just want better power consumption for light-mid range gaming....
This reminds me of the rash of rebrandings in the mid 2000s. The tech support forums for the latest games would fill up with people who couldn't get the game to run correctly on their "new" video card. The game listed support for their series of cards, but since the card they had was really from the previous(or older) series, the game didn't work. What's even more mind blowing though, is the people would get mad at the game developers for not supporting their gimpy, half-assed rebranded card and not at the manufacturer/OEM who actually screwed them over. Threats of game returns, developer boycots and lawsuits followed...
That debacle mostly taught devs to stop requiring a "series" of cards and start explicitly certifying DX or OGL version whatever, or very specific card numbers. Much harder on clueless consumers, but the devs have their asses covered from this kind of BS.
How annoying that AMD announced months ago that only the top tier Tahiti series cards would feature the new GCN architecture.... The re branding of the old chip sets is par for the course with NVDA and AMD. I'don't like it but I can live with it. Pretending that this is all a big shock and that all the other 7 series cards would feature the new architecture as well as a die shrink however, is disingenuous.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
33 Comments
Back to Article
Samus - Thursday, January 5, 2012 - link
talk about market fragmentation. its the nVidia 9000-series all over again...Medallish - Thursday, January 5, 2012 - link
If you notice, this is a theme AMD has been doing for a while, only the top of the line x8xx and x9xx gets a architectural upgrade each generation, while cards below gets one every other time.57xx became 67xx(With the exception of 6790 which was a cutdown 68xx)
from 56xx to 66xx we saw the upgrade being made to Turks 20% more shaders, UVD3 etc.
This time around the 67xx gets an 28nm upgrade to 77xx while 76xx is left behind. I don't like the fact that they change the name and don't add like the most basic of things, like a die shrink(One would think that it could improve their margins?) I think it's because the market these chips cater to work on a different wavelength than the high end does, that being said, it would be better if they didn't rename them, it sucks a little.
Sahrin - Friday, January 6, 2012 - link
>If you notice, this is a theme [s]AMD[/s] nVidia has been doing for a while, only the >top of the line x8xx and x9xx gets a architectural upgrade each generation, while >cards below gets one every other time.FTFY
MySchizoBuddy - Thursday, January 5, 2012 - link
so this is VLIW instead of the new architecture.thanks for creating confusion
MrSpadge - Thursday, January 5, 2012 - link
It's not even VLIW4, it's the same old VLIW5 we've known since years.ET - Thursday, January 5, 2012 - link
AMD has gone downhill in this respect. It's the same hill NVIDIA went down before, but maybe it's even worse. The rumours about the 7xx0 family has the 7890 card use the same chip as the 7950/70 and 7790 use the same chip as the 78x0, making it even harder to know from the name what the underlying tech is.designerfx - Thursday, January 5, 2012 - link
uh, Nvidia and AMD have gone down the exact same hill. I'm not happy about it (personally, rebrands are just bad and misleading period), but it's no different.JonnyDough - Thursday, January 5, 2012 - link
Precisely. The marketing department and the power the OEMs have annoy us all. The naming schemes have to go. We should protest by buying VIA chips. No, not really.tipoo - Friday, January 6, 2012 - link
Agreed. If its an updated 6k series card, name it as such. The 7k name should only be given to the new graphics core. I vote tech sites boycott market names and just call these cards by their core names exclusively ;)piroroadkill - Thursday, January 5, 2012 - link
Please don't do this junk. It's getting as low as NVIDIA...piroroadkill - Thursday, January 5, 2012 - link
Just to clarify, this isn't a fanboy comment. I don't care what card people buy.. I don't understand why anyone would.I'm simply saying that NVIDIA is infamous for rebranding the same cards over and over.
Wolfpup - Thursday, January 5, 2012 - link
As is AMD, but I don't remember Nvidia ever releasing some GPUs with a new design and some with an old design using the same model numbers. At least they had the decency to increment the numbers.Well, the Geforce 4 and and 4MX was confusing for a lot of people, since the 4MX was basically a Geforce 2.
StevoLincolnite - Friday, January 6, 2012 - link
Basically the same isn't the same.The Geforce 4 MX was more like a Geforce 2 on steroids.
The Geforce 4 MX advanced over the Geforce 2 in multiple areas like the then-new bandwidth and fill-rate saving technologies and in an improved memory controller.
One of the larger issues with the Geforce 2 was how badly it was memory starved.
This was evident when it was pitted against the technically inferior Radeon 7500 which had HyperZ to save on Fillrate and Bandwidth.
It was also able to hardware decode video which made nVidia comparable to ATI for the first time in that regard, this is something that the Geforce 4 Ti and Geforce 2 lacked.
ATI was also not immune to the "Re-Branding" issue.
Take the Radeon 9600 for instance. It would go on to be the:
Mobility Radeon 9600, 9700, Radeon x300, x600, x1050 with all the other variations like the Radeon 9550, SE and XT and others.
Plus... I remember reading awhile ago that 28nm was going to prove more expensive than 40nm for awhile, so with this in mind... The more cost-conscious segments will probably stagnate for awhile.
And nVidia hasn't exactly been competitive in the low end either as of late which doesn't help things, in fact... After the Geforce 240 GT and GTS they took a step backwards in regards to performance with the Geforce 430, 440 and 530.
Mortius - Friday, January 6, 2012 - link
The Geforce 200 series comes to mind. It was a mixture of G9x and GT2xx based parts For example:GTX280 - GT200
GTS250 - G92b
GTX280M -G92b
GTS250M - GT215
Not only that, the capabilities differed. GT21x parts supported DX10.1, everything else only supported DX10.
Then there is the GT230. It shipped had G92b and G94b variants. The former having twice as many shaders.
It isn't completely dead. The entry level G210 lives on as the G310 and the G405.
bennyg - Friday, January 6, 2012 - link
A complete list to relive the full extent of the chicanery at and around that time. It is even more complex if you include the while 9000 and 9000M series as there's even more overlap.GT230 - mix of 48 shader G94b and 96 shader G92b
GT230M - GT216
GT240 - GT215
GT240M - GT216
GTS240 - OEM only G92 based
GTS250 - G92b
GTS250M - GT215
GTX260 - GT200
GTX260 "Core 216" - mix of 55nm/65nm GT200a/b
GTX260M - G92b
GTX280 - GT200
GTX280M - G92b
GTX285 - GT200b
GTX285M - G92b
GT215 lived on in GT335M/GTS350M/GTS360M.
Radeons have a while to go before they get THAT bad. But they're building up a nice head of steam, with 6970M/6990M parts which arent Cayman-like (i.e. VLIW4) at all, and 68xx parts which are just the same Junipers as 57x0 and 58x0M, and now these "new" 7xxxM parts ...
And I guarantee if Kepler runs late Nvidia will start doing the same thing...
Dribble - Friday, January 6, 2012 - link
In none of those examples did nvidia do an exact replacement at the same model number like 6770 to 7670. That is perhaps a new low.Mortius - Friday, January 6, 2012 - link
What about the following pairings?8800GT/9800GT
GT240 (GDD5)/ GT340
G210/G310
The last one was indeed mentioned earlier.
coldpower27 - Friday, January 6, 2012 - link
Yeah the renaming game is getting annoying I don't mind though if it's only DX10.1 -> DX10DX11 parts though should be named as such..
There is also the 9800GTX+ -> GTS 250
GTX 200 (GT200) Series was still largely the same tech G92 based parts which is still largely the same as G80..
It wasn't until Fermi and it's derivatives that we got a major architectural change...DX11 with GTX 400/500 Series based parts.
I miss the days of clear nomenclature..
Geforce 5 was pure Direct X 9.0 Shader Model 2.0a
Geforce 6/7 was Shader Model 3.0 w/Direct X9.0c
the Direct X 10 gen was too many cards
Geforce 8, 9 and the 200 Series and even some 300 Series for the low end.. WAY too spread out.
At least we have a cleaner break with the Geforce 400/500 Series with Direct X11 Support.
chizow - Saturday, January 7, 2012 - link
I think that's largely why Nvidia's rebadges were justified in those cases, but not not so much with these AMD parts.Nvidia has stayed remarkably consistent with their feature sets over a generation of GPUs, perhaps to a stubborn fault. They resisted DX10.1 on the majority of their parts as it would clearly bifurcate their product line and create inconsistencies and market confusion.
Not to mention their shader architecture today is also largely the same as G80. No small feat considering AMD is going on its 3rd major change in 2 years. So for the most part, the feature set and compatibility on Nvidia parts has remained the same while the price and performance regardless of rebrand has remained intact.
chizow - Saturday, January 7, 2012 - link
8800GT to 9800GT was a die shrink from 65nm to 55nm.The other two parts were OEM only for the short-lived and incomplete 300 series. Technically the rebrand was justified as these were Nvidia's only DX10.1 parts and also the first to support limited HD audio and probably fit better in a 300 series rather than being lumped into the DX10-based 200 series.
coldpower27 - Friday, January 6, 2012 - link
It's tolerable consider the jump is DirectX 11-> 11.1 which isn't that significant of a difference.As always Caveat Emptor I guess.
MrSpadge - Thursday, January 5, 2012 - link
Agreed.Although AMD probably does it, because the OEMs want to put higher numbers on their products.. which is what regular customers buy.
MrS
marraco - Friday, January 6, 2012 - link
In other words, OEMs want to lie, cheat, and mislead customers to take his money.And AMD is fine with that.
chiddy - Friday, January 6, 2012 - link
Well, AMD do need to sell their GPUs!Wreckage - Friday, January 6, 2012 - link
At least the NVIDIA products were worth buying. Not like these.haukionkannel - Thursday, January 5, 2012 - link
I think that in old releases the low end cards were suposed to be usin oler vliw architecture. The reason is to allow crossfire between AMD APU chips and these new GPUs. The APUs use older vliv tecnology. GCN is coming to AMD APUs maybe in the next year (2013) if everything goes well, so AMD has to keep those old vliw cards in production at least as lon time... (actually longer, because they have to hava a crossfire option of those older APU's that are made today.We can only hope that these are 28nm... There seems not to be any information of that at this moment. If not, we have to stick 7700 series to 7900 series cards if we want to have upgrade of anykind. The only reason why they would use 40nm production is that TSMC don't have enough 28nm production capacity (it is possible) or that 40 nm are so much cheaper to produce (allso possible, but not in long run)
One thing is sure. Even AMD 80xx series have some GPUs that are vliw based, because of the need for APU crossfire!
chizow - Thursday, January 5, 2012 - link
I can understand in this case the point of emphasis:"The following is a list of some the important attributes and major features being introduced with Southern Islands. None of which will be available with the Turks based 7670."
That's a pretty big bullet list of missing features. In the past these kind of rebrands were understandable because the features and relative price and performance fell in line with newer generational offerings. Turks just really looks out of place in that 7-series stack mainly because AMD made so many changes with SI.
Another concern is they usually bump the rebrand parts or equivalent shader count parts down one hundred spots in their naming convention, but not this time. Are the % gains of SI already spread so thin at the top that there's nothing left to shave? Probably less complaints if this was a 7570 instead of a 7670, but as it is it'll be the same performance as last year's model with none of the new features while filling the same market position.
Natfly - Thursday, January 5, 2012 - link
Rebrands are fine and all, but I want a 28nm mobile midrange. Something that seems unlikely to happen in the near future. I don't care if they simply shrink their VLIW5 or VLIW4 designs or update them with GCN. I just want better power consumption for light-mid range gaming....Mr Perfect - Thursday, January 5, 2012 - link
This reminds me of the rash of rebrandings in the mid 2000s. The tech support forums for the latest games would fill up with people who couldn't get the game to run correctly on their "new" video card. The game listed support for their series of cards, but since the card they had was really from the previous(or older) series, the game didn't work. What's even more mind blowing though, is the people would get mad at the game developers for not supporting their gimpy, half-assed rebranded card and not at the manufacturer/OEM who actually screwed them over. Threats of game returns, developer boycots and lawsuits followed...foxyshadis - Thursday, January 5, 2012 - link
That debacle mostly taught devs to stop requiring a "series" of cards and start explicitly certifying DX or OGL version whatever, or very specific card numbers. Much harder on clueless consumers, but the devs have their asses covered from this kind of BS.Will Robinson - Friday, January 6, 2012 - link
How annoying that AMD announced months ago that only the top tier Tahiti series cards would feature the new GCN architecture....The re branding of the old chip sets is par for the course with NVDA and AMD.
I'don't like it but I can live with it.
Pretending that this is all a big shock and that all the other 7 series cards would feature the new architecture as well as a die shrink however, is disingenuous.
Wreckage - Friday, January 6, 2012 - link
I agree, AMD has been disingenuous.ClagMaster - Friday, January 6, 2012 - link
Why is AMD shooting themselves in the foot rebadging a 6000 series product to a 7000 series product using the same 40nm GPUs.This is stupid and disingenous. And it really does not impress either the OEMs and the consumers.