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!
I think this characterization by TechInsights is off. The author provided me some key details. I posted only a rough version on X:
https://x.com/DrFrederickChen/status/1999262408448299219?t=XaSHWzWNDN-GFYnGTJHgtA&s=19
Maybe a few % is already significant in this context?
They had to go beyond...
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
Samsung Electronics Foundry (semiconductor contract manufacturing) has received an order for 8nm (nanometer, one billionth of a meter) automotive semiconductors from Hyundai Motor Company, a domestic automaker, and is preparing for full-scale mass production. However, the industry's anticipated...
This chip was taped out domestically earlier this year, following the US-imposed ban last year on GPUs being made by TSMC and Samsung.
Xiangdixian had positioned itself at the beginning of the year as a domestic GPU manufacturer: https://www.xdxct.com/newinfo/188
Huawei probably did not want...
Chinese GPU Maker Demos Its Next-Gen Fuxi A0 GPU Based on Imagination DXD GPU IP: Features 5nm Core, 12 GB VRAM, Ray Tracing & Super-Res Support
Hassan Mujtaba•Nov 30, 2025 at 03:20am EST
The Chinese Fuxi A0 GPU is based on a 5nm Imagination DXD Graphics IP, offering Ray Tracing & Super...
I just reviewed with ChatGPT. Four transistors for cross-coupled inverter is stabler against transistor variation and leakage, while two access transistors provide better margins.
TSMC introduced a 38.1Mb/mm2 SRAM in 2nm-CMOS-nanosheet technology for high-density and energy-efficient compute applications. The design uses a 0.021um2 high-density bitcell, and through DTCO improves the overall SRAM density by 1.1× compared to the previous technology node...
Taipei 2025/12/04 03:18
Winbond Electronics, a global leader in semiconductor memory solutions, today announced the launch of its new 8Gb DDR4 DRAM, powered by Winbond's advanced 16nm process technology, providing higher speed, lower power consumption, and more cost-effective solutions for...
Interesting story from his perspective here: https://semiwiki.com/podcast/podcast-ep153-suk-lees-journey-to-intel-foundry-services-with-a-look-to-the-future/ I assume he had TSMC's blessing to go over to Intel.
