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!
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.
During those years, TSMC and Intel were not direct competitors, since Intel did not have IFS and Intel also made its own processors (no chiplets then). From 7nm onwards, they were closer to competing since AMD became a TSMC customer, but by then, Intel and TSMC were already on different paths...
Why's everyone bringing this to country level? It's IP issue between company and ex-employee, could happen anywhere, and internationally recognized everywhere. If TSMC were wrong, WJL could counter-sue.
Chinese memory chip manufacturer Changxin Memory Technologies (CXMT) officially released its latest generation of DDR5 and LPDDR5X products. In response, South Korean media outlet Business Korea pointed out that the technological gap between China and South Korea in the memory chip field is...
Pyeongtaek and Hwaseong are also sites for Samsung Foundry. I had understood DRAM to share with the EUV lines there? They could have expanded DRAM and foundry in that case, if not just DRAM alone.
I don't understand why there would be a good reason to cut down the NAND at the same time...
