Performance enhancement of a computational persistent homology package

Author: 

Hylton, A
Sang, J
Henselman-Petrusek, G
Short, R

Publication Date: 

2 February 2018

Journal: 

2017 IEEE 36th International Performance Computing and Communications Conference, IPCCC 2017

Last Updated: 

2021-10-19T13:24:02.673+01:00

Volume: 

2018-January

DOI: 

10.1109/PCCC.2017.8280468

page: 

1-8

abstract: 

© 2017 IEEE. In recent years, persistent homology has become an attractive method for data analysis. It captures topological features, such as connected components, holes, voids, etc., from a point cloud by finding out when these features appear and disappear in the filtration sequence. In this project, we focus on improving the performance of Eirene, a fancy computational persistent homology package. Eirene is a 5000-line open-source software implemented by using the dynamic programming language Julia. We use the Julia profiling tools to identify the performance bottlenecks and develop different methods to manage the bottlenecks, including the parallelization of some time-consuming functions on the multicore/manycore hardware. The empirical results show that the performance can be greatly improved.

Symplectic id: 

1139092

Submitted to ORA: 

Not Submitted

Publication Type: 

Conference Paper

ISBN-13: 

9781509064687