Fast Mesh-to-Mesh Remaps Using Hash Algorithms

Journal Article · Tue Jul 10 00:00:00 EDT 2018 · SIAM Journal on Scientific Computing

DOI:https://doi.org/10.1137/16M109140X· OSTI ID:1473793

Collom, Gerald ^[1]; Redman, Colin ^[2]; Robey, Robert W. ^[3]

---

1. Univ. of Washington, Seattle, WA (United States); Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
2. Arizona State Univ., Tempe, AZ (United States); Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
3. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of New Mexico, Albuquerque, NM (United States)

Here, we explore the potential uses of hash-based algorithms in the remap operation, mapping one computational mesh onto another. We implement and test optimizations designed to reduce memory operations and compare these optimizations in order to evaluate the performance impact across different meshes. In particular, we created a new remap method that creates a structured hierarchy of hashes. Tests were run on 2D meshes on up to 14 levels of mesh refinement and hundreds of millions of cells to measure the algorithms' relative speeds under differing circumstances. We show that our methods perform two orders of magnitude better than the standard kD-tree algorithm and that on different meshes different hash methods can be optimal. We explore these algorithms on serial CPUs, GPUs using OpenCL, and multi-core CPUs using OpenMP.

• Research Organization: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE National Nuclear Security Administration (NNSA)
• Contributing Organization: Univ. of Cambridge (United Kingdom). Darwin Cluster
• Grant/Contract Number: AC52-06NA25396
• OSTI ID: 1473793
• Report Number(s): LA-UR--16-26798
• Journal Information: SIAM Journal on Scientific Computing, Journal Name: SIAM Journal on Scientific Computing Journal Issue: 4 Vol. 40; ISSN 1064-8275
• Publisher: SIAM
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
AMR
Hashing
N-body
algorithms
parallel
remap