RmdnCache: Dual-Space Prefetching Neural Network for Large-Scale Volume Visualization
- 5 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (9) , 4560-4575
Abstract
Volume visualization plays a significant role in revealing important intrinsic patterns of 3D scientific datasets. However, these datasets are often large, making it challenging for interactive visualization systems to deliver a seamless user experience because of high input latency that arises from I/O bottlenecks and limited fast memory resources with high miss rates. To address this issue, we have proposed a deep learning-based prefetching method called RmdnCache, which optimizes the data flow across the memory hierarchy to reduce the input latency of large-scale volume visualization. Our approach accurately prefetches the content of the next view to fast memory using learning-based prediction while rendering the current view. The proposed deep learning architecture consists of two networks, RNN and MDN in respective spaces, which work together to predict both the location and likelihood distribution of the next view for defining an optimal prefetching range. Our method outperforms existing state-of-the-art prefetching algorithms in reducing overall input latency for visualizing real-world large-scale volumetric datasets.Keywords
Funding Information
- National Science Foundation (IIS-1652846)
- Advanced Scientific Computing Research, Office of Science, U.S. Department of Energy (DE-AC02-06CH11357)
This publication has 53 references indexed in Scilit:
- MFA-DVR: direct volume rendering of MFA modelsJournal of Visualization, 2023
- Intelligent Warehouse Robot Path Planning Based on Improved Ant Colony AlgorithmIEEE Access, 2023
- Path planning optimization of indoor mobile robot based on adaptive ant colony algorithmComputers & Industrial Engineering, 2021
- Representative Views and Paths for Volume Models2008
- Advanced techniques for high-quality multi-resolution volume renderingComputers & Graphics, 2004
- Out-of-core rendering of large, unstructured gridsIEEE Computer Graphics and Applications, 2001
- Accelerated isosurface extraction in time-varying fieldsIEEE Transactions on Visualization and Computer Graphics, 2000
- Approximation theory of the MLP model in neural networksActa Numerica, 1999
- Out-of-core streamline visualization on large unstructured meshesIEEE Transactions on Visualization and Computer Graphics, 1997
- Multi-resolution 3D approximations for rendering complex scenes1993