Core Viewpoint - The company Dalian Xinlian Microelectronics has been selected as the supplier for the Intelligent Computing Cluster Project by Yixin Intelligent Manufacturing (Hubei) Electronic Information Technology Co., Ltd, marking a significant contract win for the company [1] Group 1 - Dalian Xinlian Microelectronics is a wholly-owned subsidiary of Nongshang Environment [1] - The contract signed includes the provision of integrated hardware and software solutions for computing power clusters, which encompasses computer servers, high-performance computing modules, and hardware after-sales services [1] - The total contract value is 132 million yuan, including tax [1]

Company Performance - Moore Threads' stock rose over 3% on Monday [1] - Moore Threads released its new generation GPU architecture "Hua Gang" [1][2] Technological Advancement - The new architecture features a new generation instruction set [2] - The new architecture achieves a 50% increase in computing density [2] - The new architecture achieves a 10x increase in energy efficiency [2] - The new architecture integrates full-precision end-to-end acceleration technology and a new generation asynchronous programming model [2] - The new architecture supports intelligent computing clusters with a scale of over 100 thousand cards [2]

Core Insights - The article discusses the emergence of high-performance computing clusters, specifically the scaleX ultra-cluster developed by Sugon, which integrates 16 scaleX640 supernodes to achieve over 5 EFlops of computing power, marking a significant advancement in domestic AI computing infrastructure [4][5]. Group 1: Ultra-Cluster Development - The scaleX ultra-cluster is the world's first single-cabinet 640-card supernode, utilizing advanced technologies such as high-density blade servers and immersion cooling, resulting in a 20-fold increase in computing density and a PUE value as low as 1.04 [1][4]. - The scaleX ultra-cluster represents a shift from traditional scattered server deployments to a more integrated and efficient computing unit, showcasing the progress of domestic computing infrastructure from conceptual designs to tangible products [1][5]. Group 2: Demand for Computing Power - As mainstream AI models transition from hundreds of billions to trillions of parameters, the demand for computing power has surged, necessitating the development of EFLOPS-level and ten-thousand-card high-performance clusters as standard configurations for large models [2][3]. - The supernode architecture is becoming a preferred choice for new ten-thousand-card clusters due to its density and performance advantages, allowing for significant optimization in computing capabilities [3]. Group 3: Networking and Scalability - The scaleX ultra-cluster employs the scaleFabric high-speed network, which utilizes the first domestic 400G-class InfiniBand RDMA network cards, achieving 400 Gb/s bandwidth and under 1 microsecond communication latency, enhancing scalability to over 100,000 cards [7]. - The architecture allows for both Scale-up (vertical expansion) and Scale-out (horizontal expansion), addressing traditional communication bottlenecks and enabling the construction of large-scale intelligent computing clusters [6]. Group 4: Challenges and Considerations - The deployment of supernodes introduces systemic challenges, including heat dissipation from numerous chips, stability issues from mixed optical and copper interconnects, and reliability concerns from long-term operation of multiple components [8]. - As the scale of intelligent computing clusters expands, key challenges include ensuring scalability, reliability, and energy efficiency, necessitating breakthroughs in power supply technology and advanced software management for sustainable operation [8].

Group 1 - The company has launched a super node server that supports 64 GPUs per unit, indicating a significant advancement in its product offerings [1] - The new server supports both Scale-Up and Scale-Out expansion modes, showcasing its versatility and adaptability in various computing environments [1] - The server is designed to create large-scale intelligent computing clusters, capable of handling millions to hundreds of thousands of tasks efficiently and stably [1]