存储与计算的分离  

The Separation between Storage and Computation

作　　者：马一力[1] 傅湘林[1] 韩晓明[1] 许鲁[1] 

机构地区：[1]中国科学院计算技术研究所国家高性能计算机工程技术中心,北京100080

出　　处：《计算机研究与发展》2005年第3期520-530,共11页Journal of Computer Research and Development

基　　金：国家"八六三"高技术研究发展计划基金项目(2002AA112010)国家自然科学基金项目(60373045)

摘　　要：当前计算应用的发展对传统计算机体系结构提出了挑战.由计算资源和存储资源固定连接形成的系统已经不能适应动态计算的需求.从应用出发,提出计算资源和存储资源物理分离和逻辑分离的概念,并以此为基础,构造三维可重构计算环境可以解决这些问题.在这种环境中,用户程序、计算资源和存储资源可以根据应用的需求动态组合.由于摆脱了资源的地理位置和操作环境等方面的限制,计算过程将呈现出数据驱动的特点,从而实现按需计算,使计算系统可以在更大范围内为用户提供服务.Classical computer architecture is challenged by the development of current computing application. Systems constructed by fix-linked computation and storage can not satisfy the demand of dynamic computing. To resolve this problem, the concept of physical separation and logic separation between storage and computation is introduced, and a three-dimensional reconstructed computing environment is constructed based on this concept. In this case, user program, storage and computation can be assembled dynamically to satisfy the demand of application. Without the restriction of resource location and operating environment, the computing process presents the feature of being data-driven, and computing on demand is realized as well. Therefore, the computing system can provide the user with more wide service.

关 键 词：存储 计算 物理分离 逻辑分离 可重构计算环境 

分 类 号：TP302.1[自动化与计算机技术—计算机系统结构]