Performance modeling of the sparse matrix–vector product via convolutional neural networks
Impacto
Scholar |
Otros documentos de la autoría: Barreda Vayá, Maria; Dolz, Manuel F.; Castaño Álvarez, María Asunción; Alonso-Jordá, Pedro; Quintana-Orti, Enrique S.
Metadatos
Mostrar el registro completo del ítemcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONEste recurso está restringido
https://doi.org/10.1007/s11227-020-03186-1 |
Metadatos
Título
Performance modeling of the sparse matrix–vector product via convolutional neural networksAutoría
Fecha de publicación
2020-02-04Editor
SpringerCita bibliográfica
Barreda, M., Dolz, M.F., Castaño, M.A. et al. Performance modeling of the sparse matrix–vector product via convolutional neural networks. J Supercomput (2020). https://doi.org/10.1007/s11227-020-03186-1Tipo de documento
info:eu-repo/semantics/articleVersión de la editorial
https://link.springer.com/article/10.1007/s11227-020-03186-1Versión
info:eu-repo/semantics/publishedVersionPalabras clave / Materias
Resumen
Modeling the execution time of the sparse matrix–vector multiplication (SpMV) on a current CPU architecture is especially complex due to (i) irregular memory accesses; (ii) indirect memory referencing; and (iii) low ... [+]
Modeling the execution time of the sparse matrix–vector multiplication (SpMV) on a current CPU architecture is especially complex due to (i) irregular memory accesses; (ii) indirect memory referencing; and (iii) low arithmetic intensity. While analytical models may yield accurate estimates for the total number of cache hits/misses, they often fail to predict accurately the total execution time. In this paper, we depart from the analytic approach to instead leverage convolutional neural networks (CNNs) in order to provide an effective estimation of the performance of the SpMV operation. For this purpose, we present a high-level abstraction of the sparsity pattern of the problem matrix and propose a blockwise strategy to feed the CNN models by blocks of nonzero elements. The experimental evaluation on a representative subset of the matrices from the SuiteSparse Matrix collection demonstrates the robustness of the CNN models for predicting the SpMV performance on an Intel Haswell core. Furthermore, we show how to generalize the network models to other target architectures to estimate the performance of SpMV on an ARM A57 core. [-]
Proyecto de investigación
MINECO, Spain (project TIN2017-82972-R) ; Generalitat Valenciana, Spain, (Plan GenT project CDEIGENT/2018/014) ; Universitat Jaume I (POSDOC-A/2017/11 project)Derechos de acceso
© 2020 Springer Nature Switzerland AG. Part of Springer Nature.
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/restrictedAccess
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/restrictedAccess
Aparece en las colecciones
- ICC_Articles [419]