R420 and R423 details from HardOCP

[Ostsol]

To my knowledge, no one has their hands on R420.

Huh. Really?

So. . . *wipes drool from face* . . . when does is the NDA to be lifted?

 

[caboosemoose]

I don't know, 600MHz seems like a stretch. If we look at RV360, which uses the same process and has less than half the transistors of R420, ATI was able to clock it to 500MHz. Now, more than doubling the transistors and using the same process, it just doesn't seem like they're going to be able to hit 600MHz on R420. That's just me though

You can't use RV360 as a basis for predicting R420 in this way.

RV360 is designe for much higher volume (and higher yields), and lower power than the R420 will be. RV360 has a much different set of goals than the R420.

For example, what's the "fastest" that the Radeon 9000 is clocked at? 275 Mhz...that's approx 35 million transistors on TSMC's 0.15u process. Now look at the R360: 110 million transistors on the same process....and 400+ Mhz.

That is a very good point, and one all those outside the NDA would do well to remember...

 

[ZoinKs!]

So. . . *wipes drool from face* . . . when does is the NDA to be lifted?

4/20



re. clockspeeds, I'm not even gonna guess this time. For the 9700pro, I thought there was no way it'd be any higher then 315 mhz. Doh!

 

[Pete]

Is this information new?
RV380 = X600
RV370 = X300

Putting it together that way is news to me. So ATi is going to stick with two feature sets (high-end SM2.0+, low-end SM2.0) again, or is this a temporary situation? If nV will only debut mid- and low-end NV4x cards in Q3, they might be in the same situation (their NV3x-based PCX lineup seems to hint at some time before their whole line-up is SM3.0).

 

[Evildeus]

So. . . *wipes drool from face* . . . when does is the NDA to be lifted?

4/20

I thought that the NDA was postponed of 1 week so beginning of may?

 

[Unknown Soldier]

So how much faster do you think the R42x should be with 16 pipes and 600Mhz GDDR3 and 600Mhz clock.

Sure the NV40 is clocked a bit slower and the memory is a bit down.. but it all comes down to what the engine can really do. The engine is what makes everything tick. So how good can the R42x engine be against the mighty NV40's parallel engine?

US

 

[Andrew]

So how much faster do you think the R42x should be with 16 pipes and 600Mhz GDDR3 and 600Mhz clock.

Sure the NV40 is clocked a bit slower and the memory is a bit down.. but it all comes down to what the engine can really do. The engine is what makes everything tick. So how good can the R42x engine be against the mighty NV40's parallel engine?

US

600mhs core? I highly doubt it will be that fast.

 

[MadMaxtrox]

600mhz is the target, it is and will be a yield issue. Process, layout, and design enhance or inhibit core speeds. NV's and Ati's are TRULY different. 8)

 

[Andrew]

600mhz is the target, it is and will be a yield issue. Process, layout, and design enhance or inhibit core speeds. NV's and Ati's are TRULY different. 8)

Sounds like the Hellbinder rumor mill.

Thats almost a 200mhz core speed increase on a .13 process... hmm...

My money is on 525mhz and around 475 for the pro. Considering the increase from 12 pipes on the pro to 16 pipes on the XT, the 50mhz increase would make it a much faster card.

 

[Unknown Soldier]

Talking about rumour mills .. no news from TheInq. They've been very quiet lately.

US

 

[ANova]

To my knowledge, no one has their hands on R420.

Huh. Really?

So....what are your opinions on the NV40 vs R420? 8)