Performance enhancement of a computational persistent homology package

Alan Hylton; Janche Sang; Greg Henselman-Petrusek; Robert Short

doi:10.1109/PCCC.2017.8280468

Performance enhancement of a computational persistent homology package

Alan Hylton
, Janche Sang
, Greg Henselman-Petrusek
, Robert Short

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

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.

Original language	English
Title of host publication	2017 IEEE 36th International Performance Computing and Communications Conference, IPCCC 2017
Place of Publication	usa
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-8
Number of pages	8
Volume	2018-January
ISBN (Electronic)	9781509064687
DOIs	https://doi.org/10.1109/PCCC.2017.8280468
State	Published - Jul 2 2017
Event	36th IEEE International Performance Computing and Communications Conference, IPCCC 2017 - San Diego, United States Duration: Dec 10 2017 → Dec 12 2017

Conference

Conference	36th IEEE International Performance Computing and Communications Conference, IPCCC 2017
Country/Territory	United States
City	San Diego
Period	12/10/17 → 12/12/17

Keywords

Multicore/Manycore Computing
Performance Optimization
Persistent Homology
Profiling

Access to Document

10.1109/PCCC.2017.8280468

Cite this

@inproceedings{54e0d56c27e642c1be81ca46a18f462f,

title = "Performance enhancement of a computational persistent homology package",

abstract = "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.",

keywords = "Multicore/Manycore Computing, Performance Optimization, Persistent Homology, Profiling",

author = "Alan Hylton and Janche Sang and Greg Henselman-Petrusek and Robert Short",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/PCCC.2017.8280468",

language = "English",

volume = "2018-January",

pages = "1--8",

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

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "36th IEEE International Performance Computing and Communications Conference, IPCCC 2017 ; Conference date: 10-12-2017 Through 12-12-2017",

}

Hylton, A, Sang, J, Henselman-Petrusek, G & Short, R 2017, Performance enhancement of a computational persistent homology package. in 2017 IEEE 36th International Performance Computing and Communications Conference, IPCCC 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., usa, pp. 1-8, 36th IEEE International Performance Computing and Communications Conference, IPCCC 2017, San Diego, United States, 12/10/17. https://doi.org/10.1109/PCCC.2017.8280468

Performance enhancement of a computational persistent homology package. / Hylton, Alan; Sang, Janche; Henselman-Petrusek, Greg et al.
2017 IEEE 36th International Performance Computing and Communications Conference, IPCCC 2017. Vol. 2018-January usa: Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-8.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Performance enhancement of a computational persistent homology package

AU - Hylton, Alan

AU - Sang, Janche

AU - Henselman-Petrusek, Greg

AU - Short, Robert

PY - 2017/7/2

Y1 - 2017/7/2

N2 - 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.

AB - 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.

KW - Multicore/Manycore Computing

KW - Performance Optimization

KW - Persistent Homology

KW - Profiling

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85047421572&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85047421572&origin=inward

U2 - 10.1109/PCCC.2017.8280468

DO - 10.1109/PCCC.2017.8280468

M3 - Conference contribution

VL - 2018-January

SP - 1

EP - 8

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

PB - Institute of Electrical and Electronics Engineers Inc.

CY - usa

T2 - 36th IEEE International Performance Computing and Communications Conference, IPCCC 2017

Y2 - 10 December 2017 through 12 December 2017

ER -

Performance enhancement of a computational persistent homology package

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this