ITR: Hardware Acceleration of Database Operations

提出了一种基于硬件的方法来加速非标准数据库应用中出现的CPU密集型操作。 两种硬件技术，即现成的图形卡和内容可寻址存储器（CAM），用于在现代网络路由器非常快速的查找被确定。图形功能设计主要用于显示应用程序可以被开发为多边形相交空间数据库和基于距离的查询处理。内容可寻址存储器（CAM）可以有效地用于加速数据库中的连接操作。在新的数据库应用程序的上下文中，通常基于等式的连接约束正在扩展以包含其他条件，如集合包含。 本研究的主要目标是开发一个通用的框架，使细粒度的硬件加速在商业DBM

Hardware-based approaches to accelerate CPU intensive operations thatarise in the context of non-standard database applications areproposed. Two hardware technologies, namely, off-the-shelf graphicscards and content addressable memories (CAM) that are used incontemporary Network Routers for very fast lookups are identified.The graphics functionality designed primarily for display applicationscan be exploited for polygon intersection in spatial databases and fordistance-based query processing. Content addressable memories (CAM)can be gainfully deployed for accelerating join operations indatabases. In the context of new database applications, the joinconstraint which is generally based on equality is being expanded toencompass other conditions such as set-containment. The major goal ofthis research is to develop a general framework for enablingfine-grained hardware acceleration within a commercial DBM