Data Management

Self-Tuning Distribution of DB-Operations on Hybrid CPU/GPU Platforms

Date Added: May 2012
Format: PDF

A current research trend focuses on accelerating database operations with the help of GPUs (Graphics Processing Units). Since GPU algorithms are not necessarily faster than their CPU counterparts, it is important to use them only if they outperform their CPU counterparts. In this paper, the authors address this problem by constructing a decision model for a framework that is able to distribute database operations response time minimal on CPUs and GPUs. Furthermore, they discuss necessary quality measures for evaluating their model.