Data Streaming on GPU Clusters

• funded by: ORNL
• funding level: $19,000
• duration: 08/24/2009 - 01/31/2010

This work seeks to construct data streaming abstractions for clusters composed of graphics processing units (GPUs). The proposed work covers development of stream operations, such as abstract split/join operations, demonstrated through concrete text application, such as text search, for massive data processing requirements in clusters of GPUs.

Publications:

• "Large-Scale Multi-Dimensional Document Clustering on GPU Clusters" by Y. Zhang, F. Mueller, X. Cui and T. Potok in Journal of Parallel and Distributed Computing, V ??, No ?, Aug 2010 (accepted), pages ???-???.
• "Large-Scale Multi-Dimensional Document Clustering on GPU Clusters" by Y. Zhang, F. Mueller, X. Cui and T. Potok in International Parallel and Distributed Processing Symposium, Apr 2010.
• "A Programming Model for Massive Data Parallelism with Data Dependencies" by Y. Zhang, F. Mueller, X. Cui and T. Potok in Workshop on Programming Models for Emerging Architectures, Sep 2009.