Bridging the Gap between Deep Learning and Sparse Matrix Format Selection

被引：75

作者：

Zhao, Yue ^{[1
]}

Li, Jiajia ^{[2
]}

Liao, Chunhua ^{[3
]}

Shen, Xipeng ^{[1
]}

机构：

[1] North Carolina State Univ, Comp Sci, Raleigh, NC 27695 USA

[2] Georgia Inst Technol, CSE, Atlanta, GA 30332 USA

[3] Lawrence Livermore Natl Lab, CASC, Livermore, CA USA

来源：

ACM SIGPLAN NOTICES | 2018年 / 53卷 / 01期

基金：

美国国家科学基金会;

关键词：

SpMV; Sparse matrix; Format selection; Convolutional neural network; Deep learning;

D O I：

10.1145/3200691.3178495

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

This work presents a systematic exploration on the promise and special challenges of deep learning for sparse matrix format selection-a problem of determining the best storage format for a matrix to maximize the performance of Sparse Matrix Vector Multiplication (SpMV). It describes how to effectively bridge the gap between deep learning and the special needs of the pillar HPC problem through a set of techniques on matrix representations, deep learning structure, and cross-architecture model migrations. The new solution cuts format selection errors by two thirds, and improves SpMV performance by 1.73x on average over the state of the art.

引用

页码：94 / 108

页数：15

共 50 条

[31] Integrated step selection analysis: bridging the gap between resource selection and animal movement
Avgar, Tal
Potts, Jonathan R.
Lewis, Mark A.
Boyce, Mark S.
[J]. METHODS IN ECOLOGY AND EVOLUTION, 2016, 7 (05): : 619 - 630
[32] Cell Selection with Deep Reinforcement Learning in Sparse Mobile Crowdsensing
Wang, Leye
Liu, Wenbin
Zhang, Daqing
Wang, Yasha
Wang, En
Yang, Yongjian
[J]. 2018 IEEE 38TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS), 2018, : 1543 - 1546
[33] Bridging the Gap Between Value and Policy Based Reinforcement Learning
Nachum, Ofir
Norouzi, Mohammad
Xu, Kelvin
Schuurmans, Dale
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[34] Correction to: Bridging the Gap Between RCTs and RWE Through Endpoint Selection
Robert J. LoCasale
Chris L. Pashos
Ben Gutierrez
Nancy A. Dreyer
Toby Collins
Alan Calleja
Michael J. Seewald
Jonathan M. Plumb
Johan Liwing
Maurille Feudjo Tepie
Sajan Khosla
[J]. Therapeutic Innovation & Regulatory Science, 2021, 55 : 97 - 97
[35] Bridging the gap between elementary and advanced approaches to teaching adverse selection
Rigall-I-Torrent, Ricard
[J]. INTERNATIONAL REVIEW OF ECONOMICS EDUCATION, 2013, 12 : 12 - 19
[36] Towards Bridging the Gap between Machine Learning Researchers and Practitioners
Assem, Haytham
O'Sullivan, Declan
[J]. 2015 IEEE INTERNATIONAL CONFERENCE ON SMART CITY/SOCIALCOM/SUSTAINCOM (SMARTCITY), 2015, : 702 - 708
[37] Bridging the Gap between Digital Libraries and e-Learning
Dobreva, Milena
Angelova, Galia
Agre, Gennady
[J]. CYBERNETICS AND INFORMATION TECHNOLOGIES, 2015, 15 (04) : 92 - 110
[38] Bridging the Gap between LMS and Social Network Learning Analytics in Online Learning
Hernandez-Garcia, Angel
Angel Conde, Miguel
[J]. JOURNAL OF INFORMATION TECHNOLOGY RESEARCH, 2016, 9 (04) : 1 - 15
[39] Bridging the gap between Natural and Medical Images through Deep Colorization
Morra, Lia
Piano, Luca
Lamberti, Fabrizio
Tommasi, Tatiana
[J]. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 835 - 842
[40] An Overview of Deep Learning Applications in Groundwater Level Modeling: Bridging the Gap between Academic Research and Industry Applications
Ali, Ahmed Shakir Ali
Jazaei, Farhad
Babakhani, Peyman
Ashiq, Muhammad Masood
Bakhshaee, Alireza
Waldron, Brian
[J]. APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING, 2024, 2024

← 1 2 3 4 5 →