[_xxx_]

I think it's time to officially begin speculating

I say both will have unified shaders, decoupled tex units, advanced memory controller and scheduler along the lines of R520 and at least 24 "pipes". HDR+AA and correct AF will be there as well. G80 will of course feature multiple clock domains, R600 maybe as well.

I also think we'll see a replay of this year (business-wise). G80 in late summer, R600 a few months later. I do expect ATI to have parts which are actually available this time around, but nV doing the same trick they did this year.

All just IMHO. What do you people think?

EDIT: to make it perfect, I think they'll both feature some physics calculations capabilities, too

[AlphaWolf]

If G80 has unified shaders I'd expect it to be after R600. They seemed to be fighting the notion while ATI was pushing for it.

[Matasar]

R600 supposed to hit late Q4 2006 or early 2007 ?

[Karma Police]

Originally Posted by _xxx_

I think it's time to officially begin speculating

I say both will have unified shaders, decoupled tex units, advanced memory controller and scheduler along the lines of R520 and at least 24 "pipes". HDR+AA and correct AF will be there as well. G80 will of course feature multiple clock domains, R600 maybe as well.

I also think we'll see a replay of this year (business-wise). G80 in late summer, R600 a few months later. I do expect ATI to have parts which are actually available this time around, but nV doing the same trick they did this year.

All just IMHO. What do you people think?

Triple-slot cooling!!!!!!!

[_xxx_]

Originally Posted by AlphaWolf

If G80 has unified shaders I'd expect it to be after R600. They seemed to be fighting the notion while ATI was pushing for it.

Nah, that's just politics like ATI downplaying SM3.0 until they had SM3.0 parts themselves, where it suddenly became the best thing since sliced bread.

[Fodder]

Are we still expecting G80 to be a multi-core (and not just duplicates) GPU?

[Kaizer]

Originally Posted by _xxx_

Nah, that's just politics like ATI downplaying SM3.0 until they had SM3.0 parts themselves, where it suddenly became the best thing since sliced bread.

As far as I can remember, ATi said they wouldn't do 3.0 until it could be done right, whereas nV didn't see the usefullness of unified shaders just yet (or something of the sort). In too much of a hurry, though.

_
K

[N00b]

Originally Posted by Matasar

R600 supposed to hit late Q4 2006 or early 2007 ?

Since it will most probably be a DX 10 part and DX 10 will be introduced with Vista, it will be available shortly before the Vista launch (probably at least one or two month earlier). Vista is supposed to launch mid-2006, but will probably be a bit late since Beta 2 has slipped to january or february.

[_xxx_]

Originally Posted by Kaizer

As far as I can remember, ATi said they wouldn't do 3.0 until it could be done right, whereas nV didn't see the usefullness of unified shaders just yet (or something of the sort). In too much of a hurry, though.

_
K

Well yeah, it's valid for both sides. But frankly, do you think nV did SM3.0 wrong in some way? Seeing the current bunch of benchmarks, I somehow can't see nV's SM3 being useless, neither I think that unified shaders are useless.

[Ailuros]

From what it looks like unified shader cores cannot be avoided in the longrun; whether NVIDIA will arrive with such a sollution at least for it's first DX10 incarnation is another story. I personally wouldn't bet my money on it.

[Radeon600]

Aw, well I love to speculate also


WGF - 2.0
Unified Approach
GDDR-4 (Same Ring Bus Technology)

[DemoCoder]

I wouldn't trust what NV says in public PR as a guide to what they are doing internally. I think it's a smokescreen.

[Dave Baumann]

An analyst contaced me a little while back saying that some the Wall Street guys that are in contact with them are now of the opinion that G80 will be unified. I suspect that this could well be the case now, but I don't think it was the initial plan.

[Ailuros]

Interesting....

[Jawed]

:drool: <-insert drool smiley

Jawed

[CMAN]

I'm waiting for the ExGPU. My vision of this will be a crazy CrossFire/SLI config where it connects to a master card through an external cable (ala CrossFire) and is a self contained rendering box. External GPU! With all the one upmanship recently, I wouldn't be surprised.

Are we expecting more of a performance based upgrade in R600 and G80 or more emphasis on features?

[nAo]

Originally Posted by Dave Baumann

An analyst contaced me a little while back saying that some the Wall Street guys that are in contact with them are now of the opinion that G80 will be unified. I suspect that this could well be the case now, but I don't think it was the initial plan.

Even if we know it could mean anything we should remember nvidia has actually patented some unified shading tech..

[Matasar]

Someone said that R600 cant be released until 1 year after xbox launch because they signed some contract with MS ?

[DemoCoder]

I think it was probably in the roadmap. But I think NVidia PR is divorced from NVidia engineering.

For example, I don't believe NVidia "threw in" a 256-bit bus to the NV35 at the last moment after being "surprised" by the R300. I think they had investigated all the options they had available in terms of # of pipelines and bus size, and I think a 256-bit bus was in the internal roadmap, it was just a question of if they could deliver it in time. They probably deemed the extra complexity as making an already delayed design even further out. Once the decision was made to launch with 128-bits (and 4 ROPs) Just like ATI did with the R400/R420/R520/Xenos, they settled on what was fastest they could deliver to market, by taking baby steps. However, in NVidia's case, their decision to go with a paired down bus for the initial launch of the architecture put them at a PR disadvantage, so that's why you saw all that FUD about "we don't need a 128-bit bus", and then 1 quarter later, they launched a 256-bit bus.

I think NV has been badmouthing unified for fear that ATI would beat them to market with a unified architecture, but I don't think that internally they are forgoing a unified architecture. I think it's in the roadmap, has always been there, the only difference is, the degree to which the roadmap has been compressed by pressure from ATI and the hype around unified.

[obobski]

ever wonder what nVidia did/does with all the 3dfx tech they now own? i've often wondered how different nVidia's products would be w/o 3dfx, if they didn't own all the IP

idk, just thinking maybe we might see a surfacing of some un-used/un-shown 3dfx technology, combined with more engineering, sort of like nVidia seriously showing their teeth, not just competition, but ATi has enough momentum to maintain competition imo

still, i'm wondering what ever happened to tiled gfx (ignoring CrossFire's use of tiles)
the Kyro II used it, 3dfx's roadmap showed a product like 4-5 gens out from Rampage, "Mojo" to use tiled graphics, but nothing else has been published on that...and btw, for what it had in terms of hardware Kyro II was amazing...


but given 3dfx's use of tiles for memory, possibly a rendering solution wherein a small portion of the screen has it's own RAM address range, and portion of rendering power, then again who knows?

as far as G80/R600...i'm thinking GDDR4 for ATi, and XDR or XDR II for G80, with a bias towards XDR II, along with DX10 support, maybe higher FP precision, maybe not, better CrossFire modes for ATi, and possibly version of SLI that allow non-50/50 SMP (ASMP rendering, but w/o tiles?)

[Joe DeFuria]

Originally Posted by DemoCoder

I think it's in the roadmap, has always been there, the only difference is, the degree to which the roadmap has been compressed by pressure from ATI and the hype around unified.

I think it's a little different...I believe the pressure for NV to move to unified "earlier than they would have preferred" is likely due to the final form that DX10 is taking. In other words, DX10 likely pushed chip economics toward a unified solution. ATI was probably more successful in lobbying MS to get DX10 more "unfied friendly", than nVidia was in keeping DX10 "unified averse."

On a related note, I'm sticking to my guns that Vista won't be available to 2007...and that's when the first G80 (assuming unified) / R600 parts will also appear. Nothing but a pure hunch on that.

[DemoCoder]

Even in DX9, VS3.0 and PS3.0 instruction sets were converging. I think regardless of DX10, chip economics are already pushing for a unified approach. Putting so many vertex shaders on the die wastes space (plus now we have geometry shaders), and ILP has been proven not to scale, so if you're going to put as many ALUs on the chip as budget will allow, you need TLP, and TLP+huge numbers of ALUs cry out for unified. I don't think the NV engineers are dumbasses who aren't familar with all of the various architectural advantages and designs out there, just like Intel was blind to dual core, or TLP, they just tried to squeeze as much out of ILP as they possibly could instead of abandoning ship earlier.

I think NVidia PR operates on the "if a competitor is going to beat us to market with X, than downplay important of X" algorithm.

[Joe DeFuria]

Originally Posted by DemoCoder

Even in DX9, VS3.0 and PS3.0 instruction sets were converging.

Right...just not enough in the PC space to push vendors toward a unified hardware environment.

I don't think the NV engineers are dumbasses who aren't familar with all of the various architectural advantages and designs out there...

?? Neither do I...I certainly was not implying that.

I think NVidia PR operates on the "if a competitor is going to beat us to market with X, than downplay important of X" algorithm.

Sure...as does everyone.

[JoshMST]

Originally Posted by DemoCoder

I think NVidia PR operates on the "if a competitor is going to beat us to market with X, than downplay important of X" algorithm.

NVIDIA isn't the only one... I remember Intel saying "We don't see a need for 64 bits on the desktop anytime soon" then Yamhill got leaked and now Pentium 4's are X86-64. I think it is pretty common everywhere in every marketplace.

[Dave Baumann]

Originally Posted by DemoCoder

I think it was probably in the roadmap. But I think NVidia PR is divorced from NVidia engineering.

Well, I can't ever recall NV's PR making any comment about it. The commentry and reaction has stemmed from Kirk and he's not divorced from engineering.