Exploring GPU architectures to accelerate semantic comparison for intention-based search

Authors:
Ozgur Gonen;Sonali Mahapatra;Jaskirat Batra;J. C. Liu
Affiliations:
Texas A&M University;Texas A&M University;Texas A&M University College Station, TX;Texas A&M University
Venue:
Proceedings of the 6th Workshop on General Purpose Processor Using Graphics Processing Units
Year:
2013

Citing 13
Cited 0

Web Search for a Planet: The Google Cluster Architecture

IEEE Micro
MapReduce: simplified data processing on large clusters

Communications of the ACM - 50th anniversary issue: 1958 - 2008
NVIDIA Tesla: A Unified Graphics and Computing Architecture

IEEE Micro
Representation of Complex Concepts for Semantic Routed Network

ICDCN '09 Proceedings of the 10th International Conference on Distributed Computing and Networking
Reducing Query Latencies in Web Search Using Fine-Grained Parallelism

World Wide Web
Semantic Key for Meaning Based Searching

ICSC '09 Proceedings of the 2009 IEEE International Conference on Semantic Computing
Natural Language Processing with Python

Natural Language Processing with Python
The GPU Computing Era

IEEE Micro
Massively parallel acceleration of a document-similarity classifier to detect web attacks

Journal of Parallel and Distributed Computing
Fermi GF100 GPU Architecture

IEEE Micro
Optimizing a Semantic Comparator Using CUDA-enabled Graphics Hardware

ICSC '11 Proceedings of the 2011 IEEE Fifth International Conference on Semantic Computing
GPU Computing Gems Jade Edition

GPU Computing Gems Jade Edition
GigaTensor: scaling tensor analysis up by 100 times - algorithms and discoveries

Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining

Quantified Score

Hi-index	0.00

Visualization

Abstract

Semantic comparison is the basic computational task behind meaningful search techniques being deployed by most of the new search engines. This report presents performance comparison among three GPU architectures implementing semantic comparison. We have used both linear and binary search approaches along with Bloom filter while implementing semantic comparison. The Kepler, Fermi and Tesla show 250, 200 and 100 times speedup respectively compared to an Intel's i7 processor with varying workloads. We determine that binary search based Bloom filter approach reduces semantic comparison time by factor up to 100 compared to linear search based Bloom filter on real dataset.