Exploiting SIMD instructions in current processors to improve classical string algorithms
ADBIS'12 Proceedings of the 16th East European conference on Advances in Databases and Information Systems
Hi-index | 0.00 |
The rapidly increasing amount of data available for real-time analysis (i.e., so-called operational business intelligence) is creating an interesting opportunity for creative approaches to speeding up data processing algorithms. One such approach that is starting to become more common is using hardware accelerators for stream processing. Typically these accelerators are implemented on top of reconfigurable hardware, known as field-programmable gate arrays (FPGAs). Though the value of FPGAs for data warehouses is gradually recognized by the database community, their true potential for various business analytic tasks is yet unexplored. In this line of research, we investigate FPGA technology in the context of extreme data processing looking for opportunities where FPGAs can be exploited to improve over classical CPU-based architectures. We introduce a framework for FPGA-accelerated (real-time) analytics including a query-to-hardware compiler for static complex event detection, an XPath engine for dynamic query workloads, and templates for high-speed data mining operators in hardware.