Comparing GPU and CPU in OLAP cubes creation

Authors:
Krzysztof Kaczmarski
Affiliations:
Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
Venue:
SOFSEM'11 Proceedings of the 37th international conference on Current trends in theory and practice of computer science
Year:
2011

Citing 7
Cited 6

Iceberg-cube computation with PC clusters

SIGMOD '01 Proceedings of the 2001 ACM SIGMOD international conference on Management of data
Parallelizing the Data Cube

ICDT '01 Proceedings of the 8th International Conference on Database Theory
Fast computation of database operations using graphics processors

SIGMOD '04 Proceedings of the 2004 ACM SIGMOD international conference on Management of data
GPUTeraSort: high performance graphics co-processor sorting for large database management

Proceedings of the 2006 ACM SIGMOD international conference on Management of data
Relational joins on graphics processors

Proceedings of the 2008 ACM SIGMOD international conference on Management of data
Accelerating SQL database operations on a GPU with CUDA

Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units
Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU

Proceedings of the 37th annual international symposium on Computer architecture

MOLAP cube based on parallel scan algorithm

ADBIS'11 Proceedings of the 15th international conference on Advances in databases and information systems
Real-time computation of advanced rules in OLAP databases

ADBIS'11 Proceedings of the 15th international conference on Advances in databases and information systems
Task scheduling for GPU accelerated OLAP systems

Proceedings of the 2011 Conference of the Center for Advanced Studies on Collaborative Research
High-performance online spatial and temporal aggregations on multi-core CPUs and many-core GPUs

Proceedings of the fifteenth international workshop on Data warehousing and OLAP
Why it is time for a HyPE: a hybrid query processing engine for efficient GPU coprocessing in DBMS

Proceedings of the VLDB Endowment
An Adaptive Hybrid OLAP Architecture with optimized memory access patterns

Cluster Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

GPGPU (General Purpose Graphical Processing Unit) programming is receiving more attention recently because of enormous computations speed up offered by this technology. GPGPU is applied in many branches of science and industry not excluding databases, even if this is not the primary field of expected benefits. In this paper a typical time consuming database algorithm, i.e. OLAP cube creation, implemented on GPU is compared to its CPU counterpart by analysis of performance, scalability, programming and optimisation ease. Results are discussed formulating roadmap for future GPGPU applications in databases.