Chinese semiconductor thread II
- Thread starter vincent
- Start date
Metal-Core-Specific Screening with Machine Learning: Accelerating the Discovery of Metal Oxide Clusters for Enhanced EUV Lithography Resolution
Obtaining effective extreme ultraviolet lithography (EUVL) materials for pragmatic applications remains challenging. The experimental design and conventional theoretical prediction are time-consuming and costly and hardly affordable to accelerate the discovery of commercial EUVL materials. In this work, we employed the machine learning (ML) technique to predict the ionization potential of promising EUVL materials, which is closely related to the photoresists’ solubility switch. The developed ML model presents a strong generalization ability and can predict new EUVL materials containing different metals (i.e., Mg, Cu, Ca, Cd, Ni). Furthermore, feature analysis indicates that the number of hydrogen bond donors in a compound plays a vital role in determining the ionization potential of EUVL materials. The work provides not only an effective ML model to predict EUVL materials but also crucial insights into the correlation between the structure and properties. Finally, the developed ML model has been integrated into an online platform (), allowing users to quickly evaluate their designed materials and develop a comprehensive scheme for discovering promising EUVL compounds based on our platform.
Different rendering?
It says 9.6
I think that refers to the pin speed. If so, then it is normal. The advertised value for Micron HBM3E is 9.2 and the maximum allowed by the spec is 9.8 for HBM3E and 6.4 for HBM3
Last edited:
Selected domestic advanced packaging achievements: 12nm domestically produced AI chip equipped with HBM3E (9.6Gbps) storage and computing, 8x8cm ultra-large size/power/density high-bandwidth supercomputing chip, domestically produced LP DDR5 packaging solution, 6840-pin FPGA, etc
It is the data transmission speed, which is too fast.
Huawei low end phones will also use 5G Kirin chips with satcom and support apps using Xiaoyi AI model. So basically since there are basically just Kirin 8000 and 9000 line of chips and everything is basically on Kirin chips going forward, even the low end phones will have pretty good chip and AI support.