Paper Info
Title
Parallel DTFE Surface Density Field Reconstruction
Abstract
We improve the interpolation accuracy and efficiency of the Delaunay tessellation field estimator (DTFE) for surface density field reconstruction by proposing an algorithm that takes advantage of the adaptive triangular mesh for line-of-sight integration. The costly computation of an intermediate 3D grid is completely avoided by our method and only optimally chosen interpolation points are computed, thus, the overall computational cost is significantly reduced. The algorithm is implemented as a parallel shared-memory kernel for large-scale grid rendered field reconstructions in our distributed-memory framework designed for N-body gravitational lensing simulations in large volumes. We also introduce a load balancing scheme to optimize the efficiency of processing a large number of field reconstructions. Our results show our kernel outperforms existing software packages for volume weighted density field reconstruction, achieving <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">~</sub> 10x speedup, and our load balancing algorithm gains an additional <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">~</sub> 3.6x speedup at scales with <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">~</sub> 16k processes.
Year
DOI
Venue
2016
10.1109/CLUSTER.2016.40
2016 IEEE International Conference on Cluster Computing (CLUSTER)
Keywords
Field
DocType
parallel surface density,Delaunay tessellation field estimator
Kernel (linear algebra),Mathematical optimization,Algorithm design,Load balancing (computing),Computer science,Parallel computing,Interpolation,Algorithm,Delaunay tessellation field estimator,Grid,Triangle mesh,Speedup
Conference
ISSN
ISBN
Citations 
1552-5244
978-1-5090-3654-7
0
PageRank 
References 
Authors
0.34
5
7
Name
Order
Citations
PageRank
Esteban Rangel162.40
Nan Li271.17
Salman Habib39815.24
Tom Peterka453149.78
Ankit Agrawal560759.22
Wei-keng Liao6109587.98
Alok N. Choudhary73441326.32