You are currently viewing SemiWiki as a guest which gives you limited access to the site. To view blog comments and experience other SemiWiki features you must be a registered member. Registration is fast, simple, and absolutely free so please, join our community today!
Actually TSMC N7 to N5 M2 pitch shrink (40 nm to 35 nm) wasn't enough by itself to justify a node change. Gate pitch shrink was also significant for transistor density. You might say, SMIC lagged in gate pitch too much from N+2. Yet, the patterning for gate pitch won't change, so that is not the...
TSMC N6 changed diffusion break from double to single, that in itself is enough to put it above 100 MTr/mm2. So it is a noticeable jump in density from earlier 7nm. The design rules were (supposedly) the same as N7 though I think gate pitch shrunk to 54 nm to get the number below.
I had...
This article explained that some discrepancies may arise, depending on the layout assumptions, such as the ratio of NAND to Flip-Flop: https://www.angstronomics.com/p/the-truth-of-tsmc-5nm
I used the formula in that article, but actually I applied it wrongly for the 7nm generation nodes since...
Yeah, I remembered the gate pitch had been "abnormally" large, but actually it's just that SMIC density < Samsung density < TSMC density for a given process family or cluster.
My objection to TechInsights' or Jukan's spin is that the difference between TSMC's and Samsung's 5nm densities is more than the difference (or ratio) between Samsung and SMIC.
I think this characterization by TechInsights is off. The author provided me some key details. I posted only a rough version on X:
Maybe a few % is already significant in this context?
They had to go beyond the double patterning of N+2. The metal pitches are close to TSMC N5.
TechInsights has completed an exploratory teardown and process analysis of the Huawei Kirin 9030 application processor used in the new Mate 80 Pro Max. Our structural and dimensional analysis confirms that the chip is manufactured using SMIC’s N+3 process, a scaled evolution of its 7nm-class...
The Great AI Reallocation
By Pablo Valerio 12.01.2025
November 2025 marked a pivotal turning point in U.S. economic history, signaling a significant shift driven by an unprecedented alignment between federal power and private investment, which could provoke geopolitical tensions and influence...
Their mission statement is here: https://www.xdxct.com/newinfo/188
"In September 2023, Xiangdi first held the Intelligent Industry Conference in Shanghai and grandly launched the Tianjun 2 GPU graphics card, which is mainly aimed at industrial control, embedded, edge computing and other fields...
It looks like they improved N3 from 34 to 38 Mb/mm2, which is same as N2 currently. That's impressive using N3 design rules. Could the same be applied to N2, or is it already applied? 🤔
8nm appears to be the sweet spot among (at least Samsung's) foundry processes, particularly for automotive applications, even with stitched quadruple patterning!
https://ieeexplore.ieee.org/document/7998156
