NV40 clock speed

In response to Hellbinder's usual negative remarks:

Consider for a moment the statements by Team Ferrari or Team Porche that they "completely redesigned a new engine for their car this year." You'd look at it and say, "Hey! They have the same amount of cylinders! They're still using the same fuel and oil! They still have cams and pistons and the transmission is functionally the same!"

When you redesign something, you don't necessarily discard every previous good idea you've had. Often you take the best ideas from before and improve upon them with new techniques and processes. Yes, the end result is going to look markedly similar to your previous engines when you're basing yourself upon a generational, evolutionary model.

So, in sum, I'm letting you know that your remarks are rather pointless in this case. Which, considering history, is unsurprising.
 
Uttar said:
The NV40 is what the NV30 *should* have been ( that is, the very initial design plans of the NV30, which I even think included a PPP - not for long though ) + full shaders 3.0. compliancy and loads of optimizations/fixes.

Uttar, is this what you have heard from your source - or is it your educated guess on the NV40 features?
 
I think there's a reasonable line you can draw....Look at the block diagrams for NV20 and NV25, very similar. NV25 and NV30 however, obviously different cores.
 
flf said:
In response to Hellbinder's usual negative remarks:

Consider for a moment the statements by Team Ferrari or Team Porche that they "completely redesigned a new engine for their car this year." You'd look at it and say, "Hey! They have the same amount of cylinders! They're still using the same fuel and oil! They still have cams and pistons and the transmission is functionally the same!"

When you redesign something, you don't necessarily discard every previous good idea you've had. Often you take the best ideas from before and improve upon them with new techniques and processes. Yes, the end result is going to look markedly similar to your previous engines when you're basing yourself upon a generational, evolutionary model.

So, in sum, I'm letting you know that your remarks are rather pointless in this case. Which, considering history, is unsurprising.

how can you "completely redesign a new engine"? wouldnt that by default, become the new engine? :D
 
Pardon me but I´m a bit tired of hearing that chip X2 is what chip X1 should have been and the likes and that goes for any IHV. It is my understanding that each IHV tries to do what they themselves think is the best they can with all possible restrictions within a specific timeframe.

Pardon me also if I think that an IHV cannot succeed 100% and in each and every occassion (likewise for all IHV´s).

Question: can anyone estimate what 256MB of DDR3 would cost more or less?

As for the predicted/targeted/speculated (pick whatever suits you best) specifications; on paper they all look great to me, prior to release. One thing though I have to agree with is that NVIDIA is in no way in a position to allow itself any further mistakes.
 
Ailuros said:
Pardon me but I´m a bit tired of hearing that chip X2 is what chip X1 should have been and the likes and that goes for any IHV. It is my understanding that each IHV tries to do what they themselves think is the best they can with all possible restrictions within a specific timeframe.

Exactly. Nvidia has a number of development teams working in parallel. There is no reason to believe they could have come out with NV40 any quicker if they had not produced NV3x in the meantime. Apparently "what should have been" is that the Ti4600 should have been Nvidia's highest-end part currently available. (Not that this is very far from the truth...)
 
What sort of API support does everyone figure the PPP will require? I'd assume quite a bit, meaning it is unlikely to be supported, beyond a proprietary OpenGL extension, until DX10. Thoughts?
 
Dave H said:
What sort of API support does everyone figure the PPP will require? I'd assume quite a bit, meaning it is unlikely to be supported, beyond a proprietary OpenGL extension, until DX10. Thoughts?

DX10; which I don´t expect prior to 2005. Why they would add something that isn´t an absolute need right now, especially since die space and transistor count is a limiting factor on that kind of chip complexity is beyond me. But then again stranger things have happened.

I´ll never say never, never again (I like pleonasms :D )
 
Microsoft has previously updated DirectX upon the release of new hardware (Radeon 8500, for example).
 
overclocked said:
Can´t some of you hardcore tech guy´s please explain to me what a supposed PPP is and what it can do for games!?

Well, we want on-the-fly tesselated subdivision surfaces, don't we? ;)

(I mean if PPP can't do that then I see absolutely no point of it.)
 
NV40 is a completely new core built by the team behind NV2x. So, I suppose, it's more an NV2x "heavily updated version" (if you can say so considering all the shaders 3.0 and PPP and 8x1 and DDR2 and new FSAA and all the other stuff that are supposedly in NV40) than NV3x "how it would have been"...

All new designs from ATI & NV are now based on previous chips. R300 is no exeption. NV10 was no exeption too.
 
Hm i'm partially confused now. Now i hear someone mention that the Nv40 is what the NV30 was supposed to have been. :?: :?:
Then what would chipx really have been. I'm really totally lost in all this supposed talk. I think i'll just discard all talk regarding chipx is what chipz would've been from now on
 
Unit01 said:
Hm i'm partially confused now. Now i hear someone mention that the Nv40 is what the NV30 was supposed to have been. :?: :?:

I think it's widely acknowledged that NV35 is what NV30 should have been, but to say that NV40 is what NV30 should have been seems a little far-fetched. At a very early stage of design perhaps, but I can't imagine the product that NV40 is (as we know it now) could have had any chance of becoming NV30.

By the way Unit01, check your PMs on Rage3D. :)
 
Feh. That Mach64 was barely what the 32 was supposed to have done. (And they cheated on the prevailing benchmark of the time!)

(well, they did. :p )
 
Back
Top