Moor threads-U: The company's next generation "Hua Gang" architecture is currently under normal development.

At the performance conference, Moore Thread-U stated that the company's next-generation "Huagang" architecture is under normal development, and the team is fully engaged in advancing related work. The specific listing time will be determined as soon as possible based on the final test and verification results. Compared to S5000, the company's new generation full-function GPU architecture "Huagang" has increased its computational power density by 50%, while achieving a 10-fold increase in energy efficiency. The Huagang architecture supports full-precision calculations from FP4 to FP64, integrating AI computing acceleration and physical simulation functions on a single chip, allowing the company's GPU products to meet complex demands ranging from large model training to physical intelligence, digital twins, and other composite scenarios.