Using Machine Learning to Optimize Graph Execution on NUMA Machines

被引：4

作者：

Rocha, Hiago Mayk G. de A. ^{[1
]}

Schwarzrock, Janaina ^{[1
]}

Lorenzon, Arthur F. ^{[2
]}

Beck, Antonio Carlos S. ^{[1
]}

机构：

[1] Univ Fed Rio Grande do Sul, Inst Informat, Porto Alegre, RS, Brazil

[2] Fed Univ Pampa, Lab Optimizat Syst, Alegrete, Brazil

来源：

PROCEEDINGS OF THE 59TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC 2022 | 2022年

关键词：

Graphs' Features; Graph Processing; Thread and Data Placement; NUMA Systems; Machine Learning; COMMUNICATION;

D O I：

10.1145/3489517.3530581

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes PredG, a Machine Learning framework to enhance the graph processing performance by finding the ideal thread and data mapping on NUMA systems. PredG is agnostic to the input graph: it uses the available graphs' features to train an ANN to perform predictions as new graphs arrive - without any application execution after being trained. When evaluating PredG over representative graphs and algorithms on three NUMA systems, its solutions are up to 41% faster than the Linux OS Default and the Best Static - on average 2% far from the Oracle -, and it presents lower energy consumption.

引用

页码：1027 / 1032

页数：6

共 50 条

[1] Optimizing Single-Source Graph Execution on NUMA Machines
Rocha, Hiago Mayk G. de A.
Querol, Vicenc Beltran
Lorenzon, Arthur F.
Beck, Antonio Carlos S.
[J]. 2023 XIII BRAZILIAN SYMPOSIUM ON COMPUTING SYSTEMS ENGINEERING, SBESC, 2023,
[2] Machine Learning to Optimize Permanent Magnet Synchronous Machines
Ma, Zhuoren
Arteaga, Ryan
Wang, Muxuan
Silveira, Christine
[J]. PROCEEDINGS OF 2020 IEEE 2ND INTERNATIONAL CONFERENCE ON CIVIL AVIATION SAFETY AND INFORMATION TECHNOLOGY (ICCASIT), 2020, : 579 - 584
[3] Machine Learning and Graph Theory to Optimize Drinking Water
Amali, Said
EL Faddouli, Nour-eddine
Boutoulout, Ali
[J]. PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING IN DATA SCIENCES (ICDS2017), 2018, 127 : 310 - 319
[4] Scale-Free Graph Processing on a NUMA Machine
Aasawat, Tanuj Kr
Reza, Tahsin
Ripeanu, Matei
[J]. PROCEEDINGS OF IA3 2018: 2018 IEEE/ACM 8TH WORKSHOP ON IRREGULAR APPLICATIONS: ARCHITECTURES AND ALGORITHMS, 2018, : 28 - 36
[5] Using machine learning to optimize the search for biosignatures
Warren-Rhodes, Kim
Cabrol, Nathalie A.
Phillips, Michael
[J]. NATURE ASTRONOMY, 2023, 7 (04) : 378 - 379
[6] Using machine learning to optimize the search for biosignatures
[J]. Nature Astronomy, 2023, 7 : 378 - 379
[7] CongraPlus: Towards Efficient Processing of Concurrent Graph Queries on NUMA Machines
Pan, Peitian
Li, Chao
Guo, Minyi
[J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2019, 30 (09) : 1990 - 2002
[8] Memory Bandwidth Prediction in NUMA Architecture Using Supervised Machine Learning
Salehian, Solmaz
Lu, Lunjin
[J]. 2019 6TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE (CSCI 2019), 2019, : 1517 - 1522
[9] Learning Intermediate Representations using Graph Neural Networks for NUMA and Prefetchers Optimization
TehraniJamsaz, Ali
Popov, Mihail
Dutta, Akash
Saillard, Emmanuelle
Jannesari, Ali
[J]. 2022 IEEE 36TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2022), 2022, : 1206 - 1216
[10] Graph Anonymization using Machine Learning
Maag, Maria Laura
Denoyer, Ludovic
Gallinari, Patrick
[J]. 2014 IEEE 28TH INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS (AINA), 2014, : 1111 - 1118

← 1 2 3 4 5 →