Analyzing GCN Aggregation on GPU
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Inje | - |
dc.contributor.author | Jeong, Jonghyun | - |
dc.contributor.author | Oh, Yunho | - |
dc.contributor.author | Yoon, Myung Kuk | - |
dc.contributor.author | Koo, Gunjae | - |
dc.date.accessioned | 2022-11-16T07:40:44Z | - |
dc.date.available | 2022-11-16T07:40:44Z | - |
dc.date.created | 2022-11-15 | - |
dc.date.issued | 2022 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/145592 | - |
dc.description.abstract | Graph convolutional neural networks (GCNs) are emerging neural networks for graph structures that include large features associated with each vertex. The operations of GCN can be divided into two phases - aggregation and combination. While the combination just performs matrix multiplications using trained weights and aggregated features, the aggregation phase requires graph traversal to collect features from adjacent vertices. Even though neural network applications rely on GPU's massively parallel processing, GCN aggregation kernels exhibit rather low performance since graph processing using compressed graph structures provokes frequent irregular accesses in GPUs. In order to investigate the performance hurdles of GCN aggregation on GPU, we perform an in-depth analysis of the aggregation kernels using real GPU hardware and a cycle-accurate GPU simulator. We first analyze the characteristics of the popular graph datasets used for GCN studies. We reveal the fractions of non-zero elements in feature vectors are diverse among datasets. Based on the observation, we build two types of aggregation kernels that handle uncompressed and compressed feature vectors. Our evaluation exhibits the performance of aggregation can be significantly influenced by kernel design approaches and feature density. We also analyze the individual loads that access the data arrays of the aggregation kernels to specify critical loads. Our analysis reveals the performance of GPU memory hierarchy is influenced by access patterns and feature size of graph datasets. Based on our observations we discuss possible kernel design approaches and architectural ideas that can improve the performance of GCN aggregation. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Analyzing GCN Aggregation on GPU | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Koo, Gunjae | - |
dc.identifier.doi | 10.1109/ACCESS.2022.3217222 | - |
dc.identifier.scopusid | 2-s2.0-85141539262 | - |
dc.identifier.wosid | 000878114700001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.10, pp.113046 - 113060 | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 10 | - |
dc.citation.startPage | 113046 | - |
dc.citation.endPage | 113060 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordAuthor | Graphics processing units | - |
dc.subject.keywordAuthor | Kernel | - |
dc.subject.keywordAuthor | Convolutional neural networks | - |
dc.subject.keywordAuthor | Neural networks | - |
dc.subject.keywordAuthor | Mathematical models | - |
dc.subject.keywordAuthor | Hardware | - |
dc.subject.keywordAuthor | Data models | - |
dc.subject.keywordAuthor | Graph neural networks | - |
dc.subject.keywordAuthor | GCN | - |
dc.subject.keywordAuthor | aggregation kernel | - |
dc.subject.keywordAuthor | GPU | - |
dc.subject.keywordAuthor | characteristics | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.