R420 on .11?

The Baron said:
After .13u, the next process that uses low-k is .09u, correct?

From TSMC, yes. There will not be non low-k variants of 90nm though (at least, at this point in time).
 
The Baron said:
After .13u, the next process that uses low-k is .09u, correct?

Yup, according to TSMC's website...

Although, i'm not sure why you can't do low-K in 0.11u if .13 u already supports it. In principle many steps of the non-shrink process are also used in the shrink version.
 
loekf2 said:
Although, i'm not sure why you can't do low-K in 0.11u if .13 u already supports it. In principle many steps of the non-shrink process are also used in the shrink version.

Because TSMC doesn't offer it. 110nm is purely a "Value" line from TSMC and not a performance line.
 
DaveBaumann said:
loekf2 said:
Although, i'm not sure why you can't do low-K in 0.11u if .13 u already supports it. In principle many steps of the non-shrink process are also used in the shrink version.

Because TSMC doesn't offer it. 110nm is purely a "Value" line from TSMC and not a performance line.

Which is sort of interesting, if I'm recalling the history correctly. Doesn't this make TSMC and ATI somewhat out of phase, strategy-wise? Wasn't the first ATI card to use TSMC's "performance" 130nm low-K the "value" RV360?
 
It s not being out of phase to test a new process with a less complex chip :)

But if R500 is ATI next highend pc card chip, it seems from dave post that it will be on 0.09 so. And of course no way to be ready before 2005 as it seems Tsmc will not be ready before that time.
 
geo said:
DaveBaumann said:
loekf2 said:
Although, i'm not sure why you can't do low-K in 0.11u if .13 u already supports it. In principle many steps of the non-shrink process are also used in the shrink version.

Because TSMC doesn't offer it. 110nm is purely a "Value" line from TSMC and not a performance line.

Which is sort of interesting, if I'm recalling the history correctly. Doesn't this make TSMC and ATI somewhat out of phase, strategy-wise? Wasn't the first ATI card to use TSMC's "performance" 130nm low-K the "value" RV360?
Yeah, but .11u wasn't ready when RV360 was designed/launched. It's brand new, I think, and the .13u low-k in the RV360 gave them experience with the nuances of the process at TSMC. I'd expect ATI's higher-level mainstream cards to keep progressing with more advanced "performance" processes, and the experience gained from that will be used in the next generation's high-end card.
 
The Baron said:
Yeah, but .11u wasn't ready when RV360 was designed/launched. It's brand new, I think, and the .13u low-k in the RV360 gave them experience with the nuances of the process at TSMC. I'd expect ATI's higher-level mainstream cards to keep progressing with more advanced "performance" processes, and the experience gained from that will be used in the next generation's high-end card.

Oh, I think there's a lot to be said for ATI's strategy in this regard, particularly from an experience and risk-reduction pov. It just seems to me that TSMC thwarted them a bit in pursuing it with the way they (TSMC) decided to handle 110nm. This is assuming that Dave is hinting that the Inquirer article is full-of-it.
 
anaqer said:
DaveBaumann said:
PCB probably seems busy because theres fewer layers.

What I meant was, it's just teeming with SMD components.

Well off-die termination involves quite a bit of PCB clutter for starters (lots of little resistor packs). Plus, low end boards are often designed to allow AIBMs the option of using different component configurations for cost reasons.

MuFu.
 
DaveBaumann said:
The Baron said:
After .13u, the next process that uses low-k is .09u, correct?

From TSMC, yes. There will not be non low-k variants of 90nm though (at least, at this point in time).
Ding Dong. You're wrong.
http://www.reed-electronics.com/ele...413350?industryid=22108&industry=Business
All the more reason for the industry to make cooperative efforts in the form of licensing IP and in non-competitive R&D through consortia, Newberry said. He noted that it has taken five years to implement true low k dielectric films, and even at the 90nm node it's not clear that the industry has been successful, he added. Many here suggest the bulk of interconnect dielectric films used in production will once again be fluorinated silicon glass at the 90nm node.
 
loekf2 said:
bloodbob said:
DaveBaumann said:
1.) 110nm is just a cost optimised optical shrink of 130nm, so a transisor on a 110nm die has the same properties as a transistor on 130nm

I some how rather doubt the properties of the two transistors are the same. Anyone who is in ASIC developement feel free to tell me I'm right and dave is wrong. Espically in such a complex part as the R420 and I dunno how analog circuits fair being optically shrunk ( I really dunno they might not give damn ).

As I'm working in the semi business, normally it's just a geometry shrink (so in X and Y by some factor) meaning the properties of the standard cells and transistors remain the same. Nonetheless normally fabs do some tweaks in the diffusion (so what's before doing the metal layers) which are different from the original no-shrink process.

Yes analog can be shrunken as well. If... the design is prepared....

Personally I think it's a bold move to go 0.11 already. However, quite smar. From what I hear Nvidia's NV40 is a 300 mm2 (????) design, which sounds horrible to me ... looking at yields and costs. Even more if they plan to sell the same die in three or four configurations.

Agree
he nailed it
I know Micron dose the same thing and about all of the mem is on .11. Know the layout has to be layouted to do this first.
 
radar1200gs said:
Ding Dong. You're wrong.
Talk to TSMC. At the moment they are only offering low-k 90nm and their research says that no other manufacturers are offering an FSG node.
 
radar1200gs said:
DaveBaumann said:
The Baron said:
After .13u, the next process that uses low-k is .09u, correct?

From TSMC, yes. There will not be non low-k variants of 90nm though (at least, at this point in time).
Ding Dong. You're wrong.

hmmm, well this cant be right then....

TSMC established the Nexsys brand for its next-generation SoC process technology platform. The company's 90-nm technology is the first TSMC process to adopt this brand. Nexsys offers a unique triple gate oxide option that facilitates three different oxide thicknesses on a single chip. The triple gate oxide feature removes design restrictions caused by various core/IO combination requirements and should lead to more innovative SoC designs. With 70-75% linear shrinkage and a two-times performance improvement, compared to TSMC's 0.13-Micron technology, Nexsys is poised to become the de-facto SoC process technology platform standard.

The 90-nm process technology features:

* Core supply voltage ranging from 1.0V to 1.2V
* I/O and analog blocks ranging from 1.8V to 3.3V
* Multiple threshold voltage (Vt) option for optimized transistor speed and power consumption trade-offs
* Extremely tight process control for 50-nanometer gate length - the high speed process
* Ni-salicide for better sheet resistance (Rs) in narrow line widths
* Nine-layer copper interconnect, with an extra redistribution layer optional for flip-chip package
* Low-k dielectrics with k less than 2.9 for the lowest RC delay and power consumption

That last point sure looks like Low-k to me :rolleyes:
 
Wasn't the first ATI card to use TSMC's "performance" 130nm low-K the "value" RV360?

One, possibly quite big, reason for the RV360 being .13u low-k was to help in risk mitigation for the R420.
 
TSMC is only one fab, and as I showed in a previous link they are having ongoing Low-K troubles at 0.13 microns, let alone 0.09 microns.

I don't have any proof to hand, but my theory for the ongoing popularity of FGS vs other Low-K solutions is that it provides greater physical strength that better resists the attempts of copper the deform and change shape (glass is essentially inflexible, compared to polymers - most advanced Low-K solutions are polymer based and thus quite fragile).
 
Back
Top