Thesis
Large-scale adaptive mesh simulations through non-volatile byte-addressable memory
Washington State University
Master of Science (MS), Washington State University
2018
Handle:
https://hdl.handle.net/2376/102896
Abstract
Octree-based mesh adaptation has enabled simulations of complex physical phenomena. Existing meshing algorithms were proposed with the assumption that computer memory is volatile. Consequently, for failure recovery, the in-core algorithms need to save memory states as snapshots with slow file I/Os. The out-of-core algorithms store octants on disks for persistence. However, neither of them was designed to leverage unique characteristics of non-volatile byte-addressable memory (NVBM). In this project, a novel data structure Persistent Merged octree (PM-octree) is proposed for both meshing and in-memory storage of persistent octrees using NVBM. It is a multi-version data structure and can recover from failures using its earlier persistent version stored in NVBM. In addition, a feature-directed sampling approach is designed to help dynamically transform the PM-octree layout for reducing NVBM-induced memory write latency. PM-octree has been successfully integrated with Gerris software for simulation of fluid dynamics. The experimental results with real-world scientific workloads show that PM-octree scales up to 1.1 billion mesh elements with 1000 processors on the Titan supercomputer.
Metrics
12 Record Views
Details
- Title
- Large-scale adaptive mesh simulations through non-volatile byte-addressable memory
- Creators
- Bao D. Nguyen
- Contributors
- Xuechen Zhang (Degree Supervisor)
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; [Pullman, Washington] :
- Identifiers
- 99900525027701842
- Language
- English
- Resource Type
- Thesis