B3D & THG: Interviews with ATI's Dave Orton

[GTaudiophile]

Certainly thinking long term!

 

[KpocAlypse]

Just after the introduction of R300 you talked about R400, however shortly afterwards that appeared to go off the roadmap and R420 appeared ? what happened during that period?

internal changes was the cause and the outcome was that we decided the best way to go forward was to do ?this? with the PC roadmap and take ?that? and use it with X-Box.

ummm, Dropping a hint?

Also note in the Beyond3d review, they mentioned that the r400 was "Hence it appears that the performance estimations of R400 would be under-powered for its proposed introduction period, while its feature capabilities may have been beyond the current DirectX specification"


interesting.....

 

[Regs]

I also heard the stories that they're beefing up their engineering staff for the new RV core.

 

[Dman877]

I read somewhere a while ago that nvidia has development teams working on products up to 5 years away from release (this was back after they bought 3dfx). I'm sure they plan stuff even farther then that. It doesn't surprise me that the ATI guy mentions R800.

 

[Sid59]

link not work anymore =\?

 

[GTaudiophile]

Originally posted by: Sid59
link not work anymore =\?

Works for me.

 

[Wolfsraider]

very good read , thank you and the link works fine for me too?

mike

 

[Regs]

His explanation for not supporting PS 3.0 and FP32 is that there would of been a trade off for performance and would not target the main volume of upcoming games. Even though, he said it himself, "hopefully". I guess if they would of took the Nvidia route, they would of ended up with a higher transistor rate, increased power draw, and more heat. So I think they made the right decision in their angle of attack.

The die would of increased in size and may of not made good yields. They want to wait until 90nm apparently so they don't use up much die space.

 

[GTaudiophile]

Originally posted by: Regs
His explanation for not supporting PS 3.0 and FP32 is that there would of been a trade off for performance and would not target the main volume of upcoming games. Even though, he said it himself, "hopefully". I guess if they would of took the Nvidia route, they would of ended up with a higher transistor rate, increased power draw, and more heat. So I think they made the right decision in their angle of attack.

The die would of increased in size and may of not made good yields. They want to wait until 90nm apparently so they don't use up much die space.

I think what he's saying is that there is a time and season for PS3.0, and that time is not now.

I have no doubt, that by the time PS3.0 really matters, ATi will be there with their .09mu R500 core.

 

[GTaudiophile]

Elite Bastards Interviews ATI's Huddy.

 

[GTaudiophile]

Beautiful stuff here:

DW: The whole "8 extreme pipelines" and all the "extreme pipeline" talk was just a smokescreen to give the rumor mill something to chew on, right? Could you elucidate a bit on it? (BTW-It worked great, you have no idea how many nights I spent trying to figure out what that means....but I forgive ya.)

Richard Huddy: It was always a smokescreen. It takes so long to build this hardware that you'd amazed it managed to fool anyone. There are people who believe that we cut and paste the extra 4 pipelines in about a month ago. They're wrong - by many months!

It was very important to us that NVIDIA did not know exactly where to aim. As a result they seem to have over-engineered in some aspects creating a power-hungry monster which is going to be very expensive for them to manufacture. We have a beautifully balanced piece of hardware that beats them on pure performance, cost, scalability, future mobile relevance, etc. That's all because they didn't know what to aim at.

 

[bluemax]

Originally posted by: GTaudiophile
Beautiful stuff here:

DW: The whole "8 extreme pipelines" and all the "extreme pipeline" talk was just a smokescreen to give the rumor mill something to chew on, right? Could you elucidate a bit on it? (BTW-It worked great, you have no idea how many nights I spent trying to figure out what that means....but I forgive ya.)

Richard Huddy: It was always a smokescreen. It takes so long to build this hardware that you'd amazed it managed to fool anyone. There are people who believe that we cut and paste the extra 4 pipelines in about a month ago. They're wrong - by many months!

It was very important to us that NVIDIA did not know exactly where to aim. As a result they seem to have over-engineered in some aspects creating a power-hungry monster which is going to be very expensive for them to manufacture. We have a beautifully balanced piece of hardware that beats them on pure performance, cost, scalability, future mobile relevance, etc. That's all because they didn't know what to aim at.

Holy smeg! That's cool beans! :Q Can't wait to see the new product lineup!!

 

[Regs]

Well, any company could say what they want but commen sense awhile ago should of told us that there was no way in hell they could just add on an extra 4 pipes in the core in less than a few months.

 

[GTaudiophile]

THG Interviews Orton...

Actually, when we announced the 9700 in 2002, it also was huge in terms of innovation and performance. We brought cinema quality rendering to the PC. But if we look right after the X800, the next 18 months probably will show more innovation than the past 18 months. That is a fair statement.

 

[RussianSensation]

Originally posted by: GTaudiophile
THG Interviews Orton...

Actually, when we announced the 9700 in 2002, it also was huge in terms of innovation and performance. We brought cinema quality rendering to the PC. But if we look right after the X800, the next 18 months probably will show more innovation than the past 18 months. That is a fair statement.

Ok, sounds like the R500 will be a card to look forward to.