Tribeca: A Stream Database Manager for Network Traffic Analysis
VLDB '96 Proceedings of the 22th International Conference on Very Large Data Bases
Gigascope: a stream database for network applications
Proceedings of the 2003 ACM SIGMOD international conference on Management of data
Aurora: a new model and architecture for data stream management
The VLDB Journal — The International Journal on Very Large Data Bases
Fast computation of database operations using graphics processors
SIGMOD '04 Proceedings of the 2004 ACM SIGMOD international conference on Management of data
Brook for GPUs: stream computing on graphics hardware
ACM SIGGRAPH 2004 Papers
GPUTeraSort: high performance graphics co-processor sorting for large database management
Proceedings of the 2006 ACM SIGMOD international conference on Management of data
Query languages and data models for database sequences and data streams
VLDB '04 Proceedings of the Thirtieth international conference on Very large data bases - Volume 30
Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow
Proceedings of the 40th Annual IEEE/ACM International Symposium on Microarchitecture
The HELLS-join: a heterogeneous stream join for extremely large windows
Proceedings of the Ninth International Workshop on Data Management on New Hardware
| Hi-index | 0.01 |
Software development kits (SDKs) and supporting tools for Graphics Processor Units (GPUs) have matured and they now enable the implementation of complex middleware that takes advantage of the additional processing power. Working in synergy with CPUs, GPUs are suitable for executing highly parallelized tasks on streams of data. In this paper, we investigate the realization of effective operations on streams of data using GPU resources. We suggest a model for computing basic SQL-like queries that include unary/binary logical operators, membership queries as well as joins based on nested-loops. We also propose a framework that exploits the above core operations to offer a generalized computing environment for managing streams of data. Through experimentation with the NVIDIA CUDA SDK, we show sizable benefits in obtaining shorter response times not only for simple operations but also for more complex queries on streams.