An Architecture for Improving the Efficiency of Specialized Vertical Search Engine Based on GPGPUs

In this paper, we propose a new architecture for improving the efficiency of specialized vertical search engine based on GPGPUs (General-purpose Graphics Processing Unit), so that the efficiency of information retrieval can be improved. The advantages of GPGPUs in programmability, high parallel processing ability, and floating-point computing power, etc. are utilizzed in the new architecture. Thus the CPU usage can be reduced and the efficiency of the search engine can be improved. Experiments show that a platform based on the proposed architecture has significantly higher efficiency.

[1]  Wolfgang Lehner,et al.  Exploiting Graphic Card Processor Technology to Accelerate Data Mining Queries in SAP NetWeaver BIA , 2008, 2008 IEEE International Conference on Data Mining Workshops.

[2]  Joel H. Saltz,et al.  The GPU as an indirection engine for a fast information retrieval , 2005, Int. J. Electron. Bus..

[3]  Ji-Bo Wang,et al.  GPU Accelerated Support Vector Machines for Mining High-Throughput Screening Data , 2009, J. Chem. Inf. Model..

[4]  Chuan Wang,et al.  A User Motivation Model for Web Search Engine , 2009, 2009 Ninth International Conference on Hybrid Intelligent Systems.

[5]  Jens H. Krüger,et al.  A Survey of General‐Purpose Computation on Graphics Hardware , 2007, Eurographics.

[6]  Meichun Hsu,et al.  GPU-Accelerated Large Scale Analytics , 2009 .

[7]  He Li,et al.  K-Means on Commodity GPUs with CUDA , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.