TSMC: 32nm in 4Q09, 40nm half-node confirmed

Friday 01st June 2007, 04:17:00 PM, written by Arun

According to Digitimes, TSMC is currently hoping to unveil their 32nm process in Q4 2009, which is approximately 24 months after the 45nm process that will become available in September of this year, and roughly as expected by Moore's Law. This is unlike the 45nm and 65nm transitions, where TSMC reduced the gap with IDMs (Integrated Device Manufacturers) such as Intel, IBM and Texas Instruments.

32nm will be the first node released by TSMC with metal gates and high-k, according to previous reports. This implies that fabless companies will most likely not release products with the technology for about 36 months after Intel, as publicly available products tend to lag behind by at least one year. It is, however, hardly unusual for Intel to lead the industry by one process generation in terms of materials.

It is hard to predict at this point in time when these new processes, including the 40nm half-node, will be used in GPUs and handhelds. Given that the first 65nm GPUs from AMD are being released in July, and that TSMC is unveiling their 45nm process only 16 months after 65nm, it is not impossible that 45nm GPUs will be available before the end of 2008. It seems more likely to us that most of those will be aimed at the first half of 2009, however.

Considering the above, the 55nm half-node might turn out to be a short stopgap for products introduced in late 2007 and in the first half of 2008, while 40nm (if it is universally and rapidly adopted by manufacturers; 80nm wasn't, for example) might last a fair bit longer, as 32nm now looks like a Q4 2010 and beyond node for GPUs. The gap between 45nm and 32nm is no less than 8 months longer than the one between 65nm and 45nm, and that presumably increases the importance of the half-node!

Discuss on the forums

Tagging

tsmc ± 32nm, 40nm, 45nm, 55nm, 65nm


Latest Thread Comments (4 total)
Posted by Geeforcer on Friday, 01-Jun-07 19:32:57 UTC
First, isn't this the wrong forum for this? Seems like a better fit for the "Industry". Second, the gap between foundries and fab'ed IDMs is one of the reasons why AMD can absolutely not afford to go fabless.

Posted by Arun on Friday, 01-Jun-07 19:41:43 UTC
It arguably is more suitable to 3D Industry, but I thought it might be able to start some interesting discussion here (worth a shot...) and that the Industry forum is a bit crowded right now with a bunch of new threads, heh.

Posted by Rangers on Saturday, 02-Jun-07 09:30:01 UTC
Quote
Second, the gap between foundries and fab'ed IDMs is one of the reasons why AMD can absolutely not afford to go fabless.
And why Intel will have a huge advantage when they enter the graphics market.

What I'm wondering is, what the heck the console makers are going to do next time around. Say they launch in 2012, that'll leave what, one die shrink left? How do you reduce costs?

Posted by Arun on Saturday, 02-Jun-07 10:04:08 UTC
Quoting Geeforcer
Second, the gap between foundries and fab'ed IDMs is one of the reasons why AMD can absolutely not afford to go fabless.
I'm not sure there is any intrinsic reason why Chartered couldn't ramp at the same time/rate as AMD though, since they have the same tech sharing agreements. But fabless would be far from desirable from a cost or clockspeed point of view, definitely. You can compete in the value segment by being fabless, but tough luck if you're hoping to compete anywhere else IMO. Well, I guess the exception there might be if your foundry is IBM itself...

Quoting Rangers
And why Intel will have a huge advantage when they enter the graphics market.
Well, the long-term gap between mass-market chips available at TSMC on a given process node and the first Intel chips available tends to be about 12 months nowadays, which could be worse. So what you've really got is the TSMC half-node fighting Intel's next-gen node. A major question also is whether Intel's process would be 'ready enough' for a 250mm2 chip in that timeframe. With proper redundancy mechanisms, I would tend to believe so, however.

Quoting Rangers
What I'm wondering is, what the heck the console makers are going to do next time around. Say they launch in 2012, that'll leave what, one die shrink left? How do you reduce costs?
Let us not presume the death of Moore's Law so soon, shall we? There are plenty of more exotic ways to scale further. The only reason question in my mind is if they can be made economically viable. Also, continuing to scale every 2 years might not be a good long-term strategy, if the R&D costs go up and many current applications wouldn't benefit from 16x+ the number of transistors. GPUs, FPGAs and even many-core DSPs could continue to benefit for decades to come. But many other industries might not benefit as much...


Add your comment in the forums

Related tsmc News

TSMC 40nm: Confusion Ahoy!
TSMC: 45nm ready in September
NVIDIA/ATI: 55nm pilot production now, avaibility in early 2008