Adaptive Optimization of Sparse Matrix-Vector Multiplication on Emerging Many-Core Architectures

Sparse matrix vector multiplication (SpMV) is one of the most common operations in scientific and high-performance applications, and is often responsible for the application performance bottleneck. While the sparse matrix representation has a significant impact on the resulting application performan...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS) pp. 649 - 658
Main Authors Chen, Shizhao, Fang, Jianbin, Chen, Donglin, Xu, Chuanfu, Wang, Zheng
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Arrays
Many-Cores
Performance analysis
Performance optimization
Predictive models
Random access memory
Sparse matrices
Sparse matrix vector multiplication
Two dimensional displays
Online AccessGet full text

Cover

More Information
Summary:Sparse matrix vector multiplication (SpMV) is one of the most common operations in scientific and high-performance applications, and is often responsible for the application performance bottleneck. While the sparse matrix representation has a significant impact on the resulting application performance, choosing the right representation typically relies on expert knowledge and trial and error. This paper provides the first comprehensive study on the impact of sparse matrix representations on two emerging many-core architectures: the Intel's Knights Landing (KNL) XeonPhi and the ARM-based FT-2000Plus (FTP). Our large-scale experiments involved over 9,500 distinct profiling runs performed on 956 sparse datasets and five mainstream SpMV representations. We show that the best sparse matrix representation depends on the underlying architecture and the program input. To help developers to choose the optimal matrix representation, we employ machine learning to develop a predictive model. Our model is first trained offline using a set of training examples. The learned model can be used to predict the best matrix representation for any unseen input for a given architecture. We show that our model delivers on average 95% and 91% of the best available performance on KNL and FTP respectively, and it achieves this with no runtime profiling overhead.
DOI:10.1109/HPCC/SmartCity/DSS.2018.00116