ShenTu: Processing multi-trillion edge graphs on millions of cores in seconds

Heng Lin, Xiaowei Zhu, Bowen Yu, Xiongchao Tang, Wei Xue, Wenguang Chen, Lufei Zhang, Torsten Hoefler, Xiaosong Ma, Xin Liu, Weimin Zheng, Jingfang Xu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Graphs are an important abstraction used in many scientific fields. With the magnitude of graph-structured data constantly increasing, effective data analytics requires efficient and scalable graph processing systems. Although HPC systems have long been used for scientific computing, people have only recently started to assess their potential for graph processing, a workload with inherent load imbalance, lack of locality, and access irregularity. We propose ShenTu 8 the first general-purpose graph processing framework that can efficiently utilize an entire Petascale system to process multi-trillion edge graphs in seconds. ShenTu embodies four key innovations: hardware specialization, supernode routing, on-chip sorting, and degree-aware messaging, which together enable its unprecedented performance and scalability. It can traverse a record-size 70-trillion-edge graph in seconds. Furthermore, ShenTu enables the processing of a spam detection problem on a 12-trillion edge Internet graph, making it possible to identify trustworthy and spam webpages directly at the fine-grained page level.

Original languageEnglish
Title of host publicationProceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages706-716
Number of pages11
ISBN (Electronic)9781538683842
DOIs
Publication statusPublished - 11 Mar 2019
Event2018 International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018 - Dallas, United States
Duration: 11 Nov 201816 Nov 2018

Publication series

NameProceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018

Conference

Conference2018 International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018
CountryUnited States
CityDallas
Period11/11/1816/11/18

Fingerprint

Multiprocessing
Graph in graph theory
Processing
Natural sciences computing
Spam
Sorting
Scalability
Innovation
Internet
Hardware
Scientific Computing
Irregularity
Specialization
Locality
Workload
Routing
Chip
Entire

Keywords

  • Application programming interfaces
  • Big data applications
  • Data analysis
  • Graph theory
  • Supercomputers

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Hardware and Architecture
  • Theoretical Computer Science

Cite this

Lin, H., Zhu, X., Yu, B., Tang, X., Xue, W., Chen, W., ... Xu, J. (2019). ShenTu: Processing multi-trillion edge graphs on millions of cores in seconds. In Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018 (pp. 706-716). [8665798] (Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SC.2018.00059

ShenTu : Processing multi-trillion edge graphs on millions of cores in seconds. / Lin, Heng; Zhu, Xiaowei; Yu, Bowen; Tang, Xiongchao; Xue, Wei; Chen, Wenguang; Zhang, Lufei; Hoefler, Torsten; Ma, Xiaosong; Liu, Xin; Zheng, Weimin; Xu, Jingfang.

Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 706-716 8665798 (Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lin, H, Zhu, X, Yu, B, Tang, X, Xue, W, Chen, W, Zhang, L, Hoefler, T, Ma, X, Liu, X, Zheng, W & Xu, J 2019, ShenTu: Processing multi-trillion edge graphs on millions of cores in seconds. in Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018., 8665798, Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 706-716, 2018 International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018, Dallas, United States, 11/11/18. https://doi.org/10.1109/SC.2018.00059
Lin H, Zhu X, Yu B, Tang X, Xue W, Chen W et al. ShenTu: Processing multi-trillion edge graphs on millions of cores in seconds. In Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 706-716. 8665798. (Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018). https://doi.org/10.1109/SC.2018.00059
Lin, Heng ; Zhu, Xiaowei ; Yu, Bowen ; Tang, Xiongchao ; Xue, Wei ; Chen, Wenguang ; Zhang, Lufei ; Hoefler, Torsten ; Ma, Xiaosong ; Liu, Xin ; Zheng, Weimin ; Xu, Jingfang. / ShenTu : Processing multi-trillion edge graphs on millions of cores in seconds. Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 706-716 (Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018).
@inproceedings{a9b9bb021efd4286b23fb68704bdbf37,
title = "ShenTu: Processing multi-trillion edge graphs on millions of cores in seconds",
abstract = "Graphs are an important abstraction used in many scientific fields. With the magnitude of graph-structured data constantly increasing, effective data analytics requires efficient and scalable graph processing systems. Although HPC systems have long been used for scientific computing, people have only recently started to assess their potential for graph processing, a workload with inherent load imbalance, lack of locality, and access irregularity. We propose ShenTu 8 the first general-purpose graph processing framework that can efficiently utilize an entire Petascale system to process multi-trillion edge graphs in seconds. ShenTu embodies four key innovations: hardware specialization, supernode routing, on-chip sorting, and degree-aware messaging, which together enable its unprecedented performance and scalability. It can traverse a record-size 70-trillion-edge graph in seconds. Furthermore, ShenTu enables the processing of a spam detection problem on a 12-trillion edge Internet graph, making it possible to identify trustworthy and spam webpages directly at the fine-grained page level.",
keywords = "Application programming interfaces, Big data applications, Data analysis, Graph theory, Supercomputers",
author = "Heng Lin and Xiaowei Zhu and Bowen Yu and Xiongchao Tang and Wei Xue and Wenguang Chen and Lufei Zhang and Torsten Hoefler and Xiaosong Ma and Xin Liu and Weimin Zheng and Jingfang Xu",
year = "2019",
month = "3",
day = "11",
doi = "10.1109/SC.2018.00059",
language = "English",
series = "Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "706--716",
booktitle = "Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018",

}

TY - GEN

T1 - ShenTu

T2 - Processing multi-trillion edge graphs on millions of cores in seconds

AU - Lin, Heng

AU - Zhu, Xiaowei

AU - Yu, Bowen

AU - Tang, Xiongchao

AU - Xue, Wei

AU - Chen, Wenguang

AU - Zhang, Lufei

AU - Hoefler, Torsten

AU - Ma, Xiaosong

AU - Liu, Xin

AU - Zheng, Weimin

AU - Xu, Jingfang

PY - 2019/3/11

Y1 - 2019/3/11

N2 - Graphs are an important abstraction used in many scientific fields. With the magnitude of graph-structured data constantly increasing, effective data analytics requires efficient and scalable graph processing systems. Although HPC systems have long been used for scientific computing, people have only recently started to assess their potential for graph processing, a workload with inherent load imbalance, lack of locality, and access irregularity. We propose ShenTu 8 the first general-purpose graph processing framework that can efficiently utilize an entire Petascale system to process multi-trillion edge graphs in seconds. ShenTu embodies four key innovations: hardware specialization, supernode routing, on-chip sorting, and degree-aware messaging, which together enable its unprecedented performance and scalability. It can traverse a record-size 70-trillion-edge graph in seconds. Furthermore, ShenTu enables the processing of a spam detection problem on a 12-trillion edge Internet graph, making it possible to identify trustworthy and spam webpages directly at the fine-grained page level.

AB - Graphs are an important abstraction used in many scientific fields. With the magnitude of graph-structured data constantly increasing, effective data analytics requires efficient and scalable graph processing systems. Although HPC systems have long been used for scientific computing, people have only recently started to assess their potential for graph processing, a workload with inherent load imbalance, lack of locality, and access irregularity. We propose ShenTu 8 the first general-purpose graph processing framework that can efficiently utilize an entire Petascale system to process multi-trillion edge graphs in seconds. ShenTu embodies four key innovations: hardware specialization, supernode routing, on-chip sorting, and degree-aware messaging, which together enable its unprecedented performance and scalability. It can traverse a record-size 70-trillion-edge graph in seconds. Furthermore, ShenTu enables the processing of a spam detection problem on a 12-trillion edge Internet graph, making it possible to identify trustworthy and spam webpages directly at the fine-grained page level.

KW - Application programming interfaces

KW - Big data applications

KW - Data analysis

KW - Graph theory

KW - Supercomputers

UR - http://www.scopus.com/inward/record.url?scp=85064134571&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064134571&partnerID=8YFLogxK

U2 - 10.1109/SC.2018.00059

DO - 10.1109/SC.2018.00059

M3 - Conference contribution

AN - SCOPUS:85064134571

T3 - Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018

SP - 706

EP - 716

BT - Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -