Increasing Scientific Data Insights about Exascale Class Simulations under Power and Storage Constraints
暂无分享,去创建一个
Creating the next-generation high-performance simulation and analysis environment will be a significant challenge because of power and storage technology trends. Responding to these challenges will require rethinking and reframing how we approach visualization and analysis. A key difference is the need to keep track of a cost per insight in terms of power and storage used. To reduce power and storage costs, an emerging community consensus is that significantly more visualization and analysis should occur in situ--that is, during the simulation run while the data is resident in memory. Using this approach, we need to consider what scientific insights are sought, balanced by power and storage constraints, and then output only the minimal analysis data needed during the simulation run. Emerging research challenges include exploring what types of analysis questions can be answered during postprocessing with compact data products that are generated in situ and what mathematical or statistical techniques will best support this process.
[1] James P. Ahrens,et al. In‐situ Sampling of a Large‐Scale Particle Simulation for Interactive Visualization and Analysis , 2011, Comput. Graph. Forum.
[2] James P. Ahrens,et al. ADR visualization: A generalized framework for ranking large-scale scientific data using Analysis-Driven Refinement , 2014, 2014 IEEE 4th Symposium on Large Data Analysis and Visualization (LDAV).
[3] John Shalf,et al. Exascale Computing Technology Challenges , 2010, VECPAR.