中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Accelerating Graph Processing With Lightweight Learning-Based Data Reordering

文献类型：期刊论文

作者Zou, Mo1,3; Zhang, Mingzhe4; Wang, Rujia2; Sun, Xian-He2; Ye, Xiaochun3; Fan, Dongrui3; Tang, Zhimin3
刊名IEEE COMPUTER ARCHITECTURE LETTERS
出版日期2022
卷号21期号:1页码:5-8
ISSN号1556-6056
关键词Instruction sets Computational modeling Predictive models Big Data applications Software Optimization Graph processing reordering technique learning-based prediction model
DOI10.1109/LCA.2022.3151087
英文摘要Graph processing is a vital component in various application domains. However, a good graph processing performance is hard to achieve due to its intensive irregular data accesses. Noticing that in real-world graphs, a small portion of vertices occupy most connections, several techniques are proposed to reorder vertices based on their access frequency for better data access locality. However, these approaches can be further improved by identifying reordered data more effectively, which will reduce reordering overhead and improve overall performance. In this letter, we propose Learning-Based Reordering (LBR), a novel lightweight framework that identifies and reorders hot data adaptively for given graphs, algorithms, and threads. Our experimental evaluation indicates that LBR decreases reordering overhead by 24.7% while improves performance by 9.9% compared to the best-performing existing scheme.
资助项目National Science Foundation[CCF-2008907] ; National Science Foundation[CCF-2029014] ; National Natural Science Foundation of China[61732018] ; National Natural Science Foundation of China[61872335] ; National Natural Science Foundation of China[61802367] ; Austrian-Chinese Cooperative RD Project (FFG)[171111KYSB20200002] ; Austrian-Chinese Cooperative RD Project (CAS)[171111KYSB20200002]
WOS研究方向Computer Science
语种英语
出版者IEEE COMPUTER SOC
WOS记录号WOS:000764757400001
源URL[http://119.78.100.204/handle/2XEOYT63/18950]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zou, Mo
作者单位1.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
2.IIT, Chicago, IL 60616 USA
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China
4.Chinese Acad Sci, Inst Informat Engn, Beijing 100045, Peoples R China
推荐引用方式
GB/T 7714		 Zou, Mo,Zhang, Mingzhe,Wang, Rujia,et al. Accelerating Graph Processing With Lightweight Learning-Based Data Reordering[J]. IEEE COMPUTER ARCHITECTURE LETTERS,2022,21(1):5-8.
APA Zou, Mo.,Zhang, Mingzhe.,Wang, Rujia.,Sun, Xian-He.,Ye, Xiaochun.,...&Tang, Zhimin.(2022).Accelerating Graph Processing With Lightweight Learning-Based Data Reordering.IEEE COMPUTER ARCHITECTURE LETTERS,21(1),5-8.
MLA Zou, Mo,et al."Accelerating Graph Processing With Lightweight Learning-Based Data Reordering".IEEE COMPUTER ARCHITECTURE LETTERS 21.1(2022):5-8.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。