Visualizing the Topology and Data Traffic of Multi-Dimensional Torus Interconnect Networks
Torus networks are an attractive topology in supercomputing, balancing the tradeoff between network diameter and hardware costs. The nodes in a torus network are connected in a k-dimensional wrap-around mesh where each node has 2k neighbors. Effectively utilizing these networks can significantly dec...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8473686/ |
| _version_ | 1818927828916240384 |
|---|---|
| author | Shenghui Cheng Wen Zhong Katherine E. Isaacs Klaus Mueller |
| author_facet | Shenghui Cheng Wen Zhong Katherine E. Isaacs Klaus Mueller |
| author_sort | Shenghui Cheng |
| collection | DOAJ |
| description | Torus networks are an attractive topology in supercomputing, balancing the tradeoff between network diameter and hardware costs. The nodes in a torus network are connected in a k-dimensional wrap-around mesh where each node has 2k neighbors. Effectively utilizing these networks can significantly decrease parallel communication overhead and in turn the time necessary to run large parallel scientific and data analysis applications. The potential gains are considerable -5-D torus networks are used in the majority of the top 10 machines in the November 2017 Graph 500 list. However, the multi-dimensionality of these networks makes it difficult for analysts to diagnose ill-formed communication patterns and poor network utilization since human spatial understanding is by and large limited to 3-Ds. We propose a method based on a space-filling Hilbert curve to linearize and embed the network into a ring structure, visualizing the data traffic as flowlines in the ring interior. We compare our method with traditional 2-D embedding techniques designed for high-dimensional data, such as MDS and RadViz, and show that they are inferior to ours in this application. As a demonstration of our approach, we visualize the data flow of a massively parallel scientific code on a 5-D torus network. |
| first_indexed | 2024-12-20T03:19:13Z |
| format | Article |
| id | doaj.art-c26934a6573340d896645da404ea0edb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T03:19:13Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c26934a6573340d896645da404ea0edb2022-12-21T19:55:16ZengIEEEIEEE Access2169-35362018-01-016571915720410.1109/ACCESS.2018.28723448473686Visualizing the Topology and Data Traffic of Multi-Dimensional Torus Interconnect NetworksShenghui Cheng0https://orcid.org/0000-0002-3767-8371Wen Zhong1Katherine E. Isaacs2Klaus Mueller3Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, ChinaGoogle, Inc., Mountain View, CA, USAComputer Science Department, The University of Arizona, Tucson, AZ, USAComputer Science Department, Visual Analytics and Imaging Lab, Stony Brook University, Stony Brook, NY, USATorus networks are an attractive topology in supercomputing, balancing the tradeoff between network diameter and hardware costs. The nodes in a torus network are connected in a k-dimensional wrap-around mesh where each node has 2k neighbors. Effectively utilizing these networks can significantly decrease parallel communication overhead and in turn the time necessary to run large parallel scientific and data analysis applications. The potential gains are considerable -5-D torus networks are used in the majority of the top 10 machines in the November 2017 Graph 500 list. However, the multi-dimensionality of these networks makes it difficult for analysts to diagnose ill-formed communication patterns and poor network utilization since human spatial understanding is by and large limited to 3-Ds. We propose a method based on a space-filling Hilbert curve to linearize and embed the network into a ring structure, visualizing the data traffic as flowlines in the ring interior. We compare our method with traditional 2-D embedding techniques designed for high-dimensional data, such as MDS and RadViz, and show that they are inferior to ours in this application. As a demonstration of our approach, we visualize the data flow of a massively parallel scientific code on a 5-D torus network.https://ieeexplore.ieee.org/document/8473686/Torussupercomputingnetworksmulti-dimensional data |
| spellingShingle | Shenghui Cheng Wen Zhong Katherine E. Isaacs Klaus Mueller Visualizing the Topology and Data Traffic of Multi-Dimensional Torus Interconnect Networks IEEE Access Torus supercomputing networks multi-dimensional data |
| title | Visualizing the Topology and Data Traffic of Multi-Dimensional Torus Interconnect Networks |
| title_full | Visualizing the Topology and Data Traffic of Multi-Dimensional Torus Interconnect Networks |
| title_fullStr | Visualizing the Topology and Data Traffic of Multi-Dimensional Torus Interconnect Networks |
| title_full_unstemmed | Visualizing the Topology and Data Traffic of Multi-Dimensional Torus Interconnect Networks |
| title_short | Visualizing the Topology and Data Traffic of Multi-Dimensional Torus Interconnect Networks |
| title_sort | visualizing the topology and data traffic of multi dimensional torus interconnect networks |
| topic | Torus supercomputing networks multi-dimensional data |
| url | https://ieeexplore.ieee.org/document/8473686/ |
| work_keys_str_mv | AT shenghuicheng visualizingthetopologyanddatatrafficofmultidimensionaltorusinterconnectnetworks AT wenzhong visualizingthetopologyanddatatrafficofmultidimensionaltorusinterconnectnetworks AT katherineeisaacs visualizingthetopologyanddatatrafficofmultidimensionaltorusinterconnectnetworks AT klausmueller visualizingthetopologyanddatatrafficofmultidimensionaltorusinterconnectnetworks |