[trinibwoy]

Originally Posted by neliz

First, they will downclock a handful of cards and introduce a completely new "Green" product line

http://www.tweak.dk/nyheder2.php?id=22674

Related? 20% lower TDP GTS 250. Same clocks though.

[Arun]

Originally Posted by neliz

First, they will downclock a handful of cards and introduce a completely new "Green" product line (guess how much they cost compared to the original products) and then, the big bang of the show Will be a revelatION.

You seem to be forgetting about Tegra2

[trinibwoy]

Originally Posted by Bouncing Zabaglione Bros.

It's a shame you're asking for us to accept that as standard operating procedure.

Not telling you what to accept but unless your complaining actually has a chance of changing something I just don't see the point. OEM's obviously don't mind peddling the products and they are more informed than anybody else. They would be the frontline in any pushback.

With respect to other industries many products are brought forward into lower price segments (in a different guise sometimes but identical specs). Car manufacturers are notorious for this. Same thing goes for stuff like audio receivers - compare the specs of the flagship two years ago to the mainstream stuff today. It seems that it's only the 3D community that goes batshit crazy over it though.

[John Reynolds]

Originally Posted by trinibwoy

(i.e the people who actually care what graphics card is in their laptop are going to know the deal).

I've told this story before, but I guess you had to be there, listening to me trying to convince a GS-13 engineer in 2002 that his GF4 MX was far closer to a GF2 than a real GF4. The fact that it was branded a GF4 boggled his mind and it took quite a bit of arguing with him to convince him otherwise. So, no, I don't agree with that line of thinking at all. I believe your typical consumer thinks more along the lines of the SKU or product line: It's a high-end laptop or desktop, all parts should be quality items. Wait, what's integrated graphics? Wait, this laptop has a fast CPU and gobs of RAM, but its video is how many generations old?

[Kaotik]

Originally Posted by neliz

It's on the level of selling G92 as a gt200mobile.

Originally Posted by Sontin

Or selling Juniper as 58xx mobile.

Not quite the same, if RV770 would be sold as 58xx mobile, it would be same as selling G92 as GT200 mobile (or GT215 as GTS300 Mobile). Juniper is same gen as Cypress, G92 isn't same gen as GT200 and GT215 isn't same gen as GTx300

[Sontin]

Originally Posted by Kaotik

Not quite the same, if RV770 would be sold as 58xx mobile, it would be same as selling G92 as GT200 mobile (or GT215 as GTS300 Mobile). Juniper is same gen as Cypress, G92 isn't same gen as GT200 and GT215 isn't same gen as GTx300

The only real difference is that both - juniper and g92 - have no dp function. Other things like more threads and more SM per cluster are not really must have features for the GT200 cards.
So we have juniper which is 1/2 cypress and we have g92 which is a litte less than 1/2 of GT200. At the end it's the same.

[trinibwoy]

Originally Posted by John Reynolds

I've told this story before, but I guess you had to be there, listening to me trying to convince a GS-13 engineer in 2002 that his GF4 MX was far closer to a GF2 than a real GF4.

Yeah but that's desktop discrete and that was even more of a niche than it is now. We're talking about OEM built laptops here where consumers buy a laptop based on how big the screen is and how much RAM it has. You seem to be alluding to a segment of the market that is aware, yet ignorant. I haven't met many people like that myself though.

Originally Posted by Kaotik

Not quite the same, if RV770 would be sold as 58xx mobile, it would be same as selling G92 as GT200 mobile (or GT215 as GTS300 Mobile). Juniper is same gen as Cypress, G92 isn't same gen as GT200 and GT215 isn't same gen as GTx300

The distinction you're making is pretty irrelevant. The chip used, its die-size, manufacturing node and "generation" are only interesting to technology geeks. Price, performance, features and power consumption are the only things that matter. If those targets can be hit with a die shrunk chip from 4 years ago, so what?

[Silent_Buddha]

Originally Posted by Sontin

Or selling Juniper as 58xx mobile.

Except that Juniper is at the very least from the same generation of products.

TV's manage to brand based on same generation. Printers manage to brand based on same generation. PSU's seem to brand based on same generation. Cars generally brand based on same generation.

Features and performance will vary within that generation obviously but the branding is almost universally limited to products of the same generation.

Yet Nvidia can't do this very simplest of things. Rather instead they would prefer to mislead and bilk the end consumer by taking a past generation product and advertising it as a new generation product.

Even snake oil salesmen and Used car salesmen don't stoop down to that level usually.

Regards,
SB

[Florin]

The selective outrage is once again quite revealing.

[OpenGL guy]

Originally Posted by Sontin

The only real difference is that both - juniper and g92 - have no dp function. Other things like more threads and more SM per cluster are not really must have features for the GT200 cards.
So we have juniper which is 1/2 cypress and we have g92 which is a litte less than 1/2 of GT200. At the end it's the same.

The real difference is that Juniper has DX11, don't you think?

[Silent_Buddha]

Originally Posted by Florin

The selective outrage is once again quite revealing.

What? That I don't ding Nvidia for marketing same gen products but lower performance as higher branded for mobile parts? Or ATI for that matter?

Oh wait, nm, Nvidia couldn't even get that right for the mobile GT2xx branded parts.

I'm not sure where I said it was peachy. Just because I was pointing out that it is not the same, does not automatically equate to this is good.

But at least even in that case, it's consistent with the highest performant mobile part getting the highest performance nomenclature. Although I'd certainly prefer that the naming was more consistent with the desktop counterparts.

Regards,
SB

[Florin]

Originally Posted by OpenGL guy

The real difference is that Juniper has DX11, don't you think?

Nah, that's not the point. The G92 and GT200 share the same feature set too, certainly for their DX version compatibility.

Like the mobile 58xx and Cypress do.

[Bouncing Zabaglione Bros.]

Originally Posted by trinibwoy

Not telling you what to accept but unless your complaining actually has a chance of changing something I just don't see the point. OEM's obviously don't mind peddling the products and they are more informed than anybody else. They would be the frontline in any pushback.

I am constantly surprised by the amount of slack you are prepared to cut Nvidia for what are pretty dishonest practices - something we've seen and heard of from insiders for years now that are Nvidia's standard operating procedures.

Pointing it out (or "complaining" if you prefer) does change things. It gets the message out there, it gives people an understanding of how they are being conned by dubious business practices, and it helps people make informed choices to spend their money elsewhere on better products and with companies that don't treat their customers with such a level of disrespect.

I used to buy Nvidia products, but by learning directly from customer's experiences (both here and elsewhere), as well as my own, I now steer clear of them. When I build PCs for friends and relatives, when I advise people on what to buy, I use the same knowledge to tell them to get other products. Spreading knowledge always changes things, especially when it's about dishonest company practices that those companies would rather brush under the carpet, but that they can no longer do in the age of the internet.

You may shrug your shoulders and say "why bother complaining, nothing changes", whereas I am living proof that it does. Customers do care, and those customers do make a difference. Maybe not all of them, but enough of them.

[Squilliam]

Originally Posted by Silent_Buddha

What? That I don't ding Nvidia for marketing same gen products but lower performance as higher branded for mobile parts? Or ATI for that matter?

Actually I remember we had a discussion about rebranding ATI products as lower level next generation parts and you were opposed to it, even if the parts were refresh parts on a lower process node. You are consistant and I do commend you for it.

[Sontin]

Originally Posted by Silent_Buddha

Except that Juniper is at the very least from the same generation of products.

G92b and GT200b are from the same generation, too.

[Squilliam]

Originally Posted by Sontin

G92b and GT200b are from the same generation, too.

Since when? They don't share the same architecture. You wouldn't say that Sandy Bridge is the same generation of CPU as Donkey chip even though some of them will be produced on the same process node, would you?

[Sontin]

Originally Posted by Squilliam

Since when? They don't share the same architecture.

Juniper has no DP, too. So it is not the same architecture. There is no other real difference between g92 and gt200.

[Squilliam]

Originally Posted by Sontin

Juniper has no DP, too. So it is not the same architecture. There is no other real difference between g92 and gt200.

No real difference? Cypress and Juniper share the same baseline architecture and aside from the DP support they are almost exactly the same chips aside from the fact that one is twice the size of the other. Juniper is to Cypress what the G94 is to the G92.

On the other hand GT200 and the G92 are different architectures. G92 has its basis in the G80 whilst the GT200 architecture is something newer again.

[Sontin]

Originally Posted by Squilliam

No real difference? Cypress and Juniper share the same baseline architecture and aside from the DP support they are almost exactly the same chips aside from the fact that one is twice the size of the other. Juniper is to Cypress what the G94 is to the G92.

On the other hand GT200 and the G92 are different architectures. G92 has its basis in the G80 whilst the GT200 architecture is something newer again.

But who cares?
Why don't we compare the other specifications like TMUs, ROPs, shaders and memory interface?
5870 mobile vs 5870 desktop:
40 TMUs <> 80 TMUs = 50% of Cypress
16 ROPs <> 32 ROPs = 50% of Cypress
128bit <> 256bit = 50% of Cypress
800 shader <> 1600 shaders = 50% of Cypress

GTX280m (g92) vs GTX280:
64 TMUs <> 80 TMUs = 80% of GT200
16 ROPs <> 32 ROPs = 50% of GT200
256bit <> 512bit = 50% of GT200
128 shader <> 240 shaders = 53,3% of GT200

Nobody cares about minor changes like threads, better mul, Cuda 2.3 (or so) or three sm per cluster instead of two. The basic architecture is the same: Vec8 ALU, 8 TMUs per Cluster, D3D10, 4 ROPs per partition. I don't see a significant difference between AMD and nVidia.

[digitalwanderer]

Originally Posted by OpenGL guy

The real difference is that Juniper has DX11, don't you think?

I used to think that, but my all my nVidia friends have been explaining to me that DP is much more important now.




( I keed, you really think I have friends at nVidia? )

[neliz]

Charlie spoils nvidia's Ion2 CES Launch

[Florin]

Well, they made enough noise about the fact that they're not allowed to use QPI or DMI, so is anyone surprised?

And hey Pineview is cursed with a GMA chip on board, it's not as if it doesn't need all the help it can get.

[Squilliam]

Originally Posted by Sontin

But who cares?
Why don't we compare the other specifications like TMUs, ROPs, shaders and memory interface?


Nobody cares about minor changes like threads, better mul, Cuda 2.3 (or so) or three sm per cluster instead of two. The basic architecture is the same: Vec8 ALU, 8 TMUs per Cluster, D3D10, 4 ROPs per partition. I don't see a significant difference between AMD and nVidia.

Nobody cares about improved power management in an application where its most important? Nobody cares about programmability when its becoming extremely useful for encoding/decoding as well as photoshop etc. Nobody cares about the differences in the shader architecture of course not.

The major difference between the two is that the AMD chips are from the same generation and share a common feature set. The Nvidia chips are not from the same generation no matter how similar some of their characteristics are. Furthermore the AMD chips follow a consistant naming scheme whereas the Nvidia parts do not. x8xx is always high end, x6xx is always enthusiast and so on.

[Squilliam]

Originally Posted by neliz

Charlie spoils nvidia's Ion2 CES Launch

I have to say that doesn't put a very positive light on it there sir at least as a mobile chipset. As a light weight desktop chipset we'll have to see what AMD comes up with in competition, but I wouldn't suspect that its 100% rosy there either as they can get both the GPU boys and the CPU boys actually co-operating. My overall suspicion is that both Nvidia and Intel would have done a lot better here had they actually worked together.

[stevem]

Originally Posted by Squilliam

My overall suspicion is that both Nvidia and Intel would have done a lot better here had they actually worked together.

Naturally, but that's the whole point. Intel just doesn't see a role for other IHV chipset/GPU logic for these parts.