Abstract
Parallel implementation of the sparse grid combination technique in high dimensions presents many complexity challenges. We enumerate these challenges, classifying them respectively as computational, algorithmic, and software complexity. We discuss strategies for overcoming the individual complexity barriers. We describe our architecture for a software framework that will allow its users to build complex multiple grid solver applications.
Original language | English |
---|---|
Pages (from-to) | 593-602 |
Number of pages | 10 |
Journal | Advances in Parallel Computing |
Volume | 25 |
DOIs | |
Publication status | Published - 2014 |
Externally published | Yes |
Keywords
- Fault-tolerance
- High-dimensional Systems
- MapReduce
- Parallel Computing
- Partial Differential Equations