shareSee - Dynamic Sharing of Large-Scale Visualization

 

Driven by needs of SciDAC applications for large user groups to collaborate across geographical distances, visualization must now also serve as an effective means to share concrete data as well as abstract ideas over the Internet. Yet there is simply no expeditious and practical way for users collaborating in this wide area to share large visualizations in a dynamic fashion. Current users cannot dynamically interact with and tweak a visualization to answer questions formed spontaenously in his or her mind. We propose to use free, unscheduled, and unreserved resources on remote networked computers in an innovative way to visualize large datasets. We have shown that fault tolerance as well as scalability can be achieved. The latency perceived by the user can be as low as when the entire dataset is in the local area network. Run-time fault could happen without hampering time-critical on-demand volume visualization. Distributed collaboration of up to 10 concurrent users visualizing a total of 300 GB (1 TB with replication for fault resilience) have been shown to be interactive using completely distributed computing resources during live experiments.

'Visualization Viewpoints: Dynamic Sharing of Large-Scale Visualization', Jian Huang, Huadong Liu, Jinzhu Gao, Andrew Gaston, Micah Beck and Terry Moore, IEEE Computer Graphics and Applications, 27(1), pp. 20-25, 2007.

Time Critical Distributed Visualization with Fault Tolerance', Jinzhu Gao, Huadong Liu, Jian Huang, Micah Beck, Qishi Wu, Terry Moore and James Kohl, Proc. of Eurographics Symposium on Parallel Graphics and Visualization, Crete, Greece, April 2008.

'Scalable Distributed Execution Environment for Large Data Visualization', Micah Beck, Huadong Liu, Jian Huang and Terry Moore, IEEE International Parallel and Distributed Processing Symposium (IPDPS), March 2007, Long Beach, CA.

'Dynamic Co-Scheduling of Distributed Computation and Replication', Huadong Liu, Micah Beck and Jian Huang, Ó, Proc. of IEEE/ACM CCGrid (International Symposium on Cluster Computing and the Grid), May 2006, Singapore.

Distributed Data Management for Large Volume Visualization', Jinzhu Gao, Jian Huang, C. Ryan Johnson, Scott Atchley and James Kohl, Proc. of IEEE Visualization Conference, October 2005, Minneapolis, MN.

Remote Visualization by Browsing Image-Based Databases with Logistical Networking', Jin Ding, Jian Huang, Micah Beck, Shaotao Liu, Terry Moore, Stephen Soltesz, Proc. of SC Conference (IEEE/ACM Supercomputing Conference), Nov. 2003, Pheonix, AZ.