Bifröst: Visualization Services Framework

 We are interested in the deployment of visualization and analysis services within a bridge framework that uses the functionality provided by middleware to efficiently orchestrate the movement of data.
The advantages in this approach is that it creates a clear modularization of both data management and visualization/analysis technologies, and allows both sides of the interface to grow and expand independently. Visualization and analysis tasks have traditionally been I/O bound, and we expect this trend to continue in the exascale. If these services are designed to be interoperable, and use a bridging layer to coordinate with the middleware and runtime systems, there are opportunities to efficiently use the deeper memory and storage hierarchies that will be introduced to combat the I/O problem.
Publications:
  • D. Pugmire, J. Kress, J. Choi, S. Klasky, T. Kurc, R. Churchill, M. Wolf, G. Eisenhauer, H. Childs, K. Wu, A. Sim, J. Gu, J. Low, “Visualization and Analysis for Near-Real-Time Decision Making in Distributed Workflows”,  To appear: High Performance Data Analysis and Visualization (HPDAV), IPDPS 2016, Chicago, IL. May 2016.
  • J. Kress, D. Pugmire, H. Childs, S. Klasky, N. Podhorzski, J. Choi, “Loosely Coupled In Situ Visualization: A Perspective on Why it’s Here to Stay”, In-Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization, Supercomputing 2015, Austin TX.
  • Jong Choi, Yuan Tian, Gary Liu, Norbert Podhorszki, David Pugmire, Scott Klasky, Eun-Kyu Byun, Soonwook Hwang, Alex Sim, Lingfei Wu, John Wu, Mehmet Aktas, Manish Parashar, Michael Churchill, C.S. Chang, Tahsin Kurc, Xinyan Yan, Matthew Wolf,. “ICEE: Enabling Data Stream Processing For Remote Data Analysis Over Wide Area Networks,” In Supercomputing Frontiers, 2015.
  • D. Pugmire, J. Kress, J. Meredith, N. Podhorszki, J. Choi, S. Klasky, “Towards Scalable Visualization Plugins for Data Staging Workflows”, 5th International Workshop on Big Data Analytics: Challenges, and Opportunities (BDAC-14), Nov. 2014.

Vtk-m

VTK-m is a toolkit of scientific visualization algorithms for emerging processor architectures. VTK-m supports the fine-grained concurrency for data analysis and visualization algorithms required to drive extreme scale computing by providing abstract models for data and execution that can be applied to a variety of algorithms across many different processor architectures.
VTK-m is a merging of three prior research projects, EAVL, Dax, and PISTON.
Publications:
  • K. Moreland, R. Maynard, B. Geveci, J. Meredith, D. Pugmire, C. Sewell, L. Lo, J. Ahrens, H. Childs, K. Ma, “VTK-m: Accelerating the Visualization Toolkit for Massively Threaded Architectures”, To appear: IEEE Computer Graphics and Applications, June 2016.
  • J.S. Meredith,  S. Ahern, D. Pugmire, R. Sisneros, “EAVL: The Extreme-scale Analysis and Visualization Library”, Eurographics Symposium on Parallel Graphics and Visualization (EGPGV) in association with Eurographics, 2012.
  • J.S. Meredith, R. Sisneros, D. Pugmire, S. Ahern, “A Distributed Data-Parallel Framework for Analysis and Visualization Algorithm Development” , Fifth Workshop on General Purpose Processing on Graphics Processing Units (GPGPU5), 2012.