STM-Multifrontal QR: Streaming Task Mapping Multifrontal QR Factorization Empowered by GCN

Multifrontal QR algorithm, which consists of symbolic analysis and numerical factorization, is a high-performance algorithm for orthogonal factorizing sparse matrix. In this work, a graph convolutional network (GCN) for adaptively selecting the optimal reordering algorithm is proposed in symbolic an...

Full description

Saved in:
Bibliographic Details
Published in:SC21: International Conference for High Performance Computing, Networking, Storage and Analysis pp. 01 - 14
Main Authors: Lin, Shengle, Yang, Wangdong, Wang, Haotian, Tsai, Qinyun, Li, Kenli
Format: Conference Proceeding
Language:English
Published: ACM 14.11.2021
Subjects:
Approximation algorithms
Classification algorithms
Computer architecture
Graph Convolutional Network
High performance computing
Multicore processing
Multifrontal QR Factorization
NUMA Multicore Architecture
Parallel processing
Performance gain
Task Mapping Optimization
Task Stream Processing
ISSN:2167-4337
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multifrontal QR algorithm, which consists of symbolic analysis and numerical factorization, is a high-performance algorithm for orthogonal factorizing sparse matrix. In this work, a graph convolutional network (GCN) for adaptively selecting the optimal reordering algorithm is proposed in symbolic analysis. Using our GCN adaptive classifier, the average numerical factorization time is reduced by 20.78% compared with the default approach, and the additional memory overhead is approximately 4% higher than that of prior work. Moreover, for numerical factorization, an optimized tasks stream parallel processing strategy is proposed and a more efficient computing task mapping framework for NUMA architecture is adopted in this paper, which called STM-Multifrontal QR factorization. Numerical experiments on the TaiShan Server show average 1.22x performance gains over the original SuiteSparseQR. Nearly 80% of datasets have achieved better performance compared with the MKL sparse QR on Intel Xeon 6248.
ISSN:2167-4337
DOI:10.1145/3458817.3476199