TY - GEN
T1 - A Code Selection Mechanism Using Deep Learning
AU - Cui, Hang
AU - Hirasawa, Shoichi
AU - Takizawa, Hiroyuki
AU - Kobayashi, Hiroaki
N1 - Publisher Copyright:
© 2016 IEEE.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2016/12/5
Y1 - 2016/12/5
N2 - Sparse Matrix-Vector multiplication (SpMV) is a computational kernel widely used in many applications. There are many different implementations using different processors and algorithms for SpMV. The performances of different SpMV implementations are quite different, and it is basically difficult to choose the implementation that has the best performance for a given sparse matrix and a given platform without performance profiling. This work presents a prototype implementation of an effective machine learning system for SpMV code selection best suited for a given matrix. Instead of using predefined features of a matrix for performance prediction, a feature image and a deep learning network are used to map each sparse matrix to the implementation that has the best performance in advance of the execution. The performance gain by the mechanism is evaluated by using a machine learning method for predicting the best SpMV implementation. According to our evaluation, the proposed mechanism can select an optimal or suboptimal implementation in most cases, though the prediction is not perfect. These results demonstrate the feasibility that the proposed machine learning approach can capture underlying features of an input sparse matrix useful for SpMV code selection.
AB - Sparse Matrix-Vector multiplication (SpMV) is a computational kernel widely used in many applications. There are many different implementations using different processors and algorithms for SpMV. The performances of different SpMV implementations are quite different, and it is basically difficult to choose the implementation that has the best performance for a given sparse matrix and a given platform without performance profiling. This work presents a prototype implementation of an effective machine learning system for SpMV code selection best suited for a given matrix. Instead of using predefined features of a matrix for performance prediction, a feature image and a deep learning network are used to map each sparse matrix to the implementation that has the best performance in advance of the execution. The performance gain by the mechanism is evaluated by using a machine learning method for predicting the best SpMV implementation. According to our evaluation, the proposed mechanism can select an optimal or suboptimal implementation in most cases, though the prediction is not perfect. These results demonstrate the feasibility that the proposed machine learning approach can capture underlying features of an input sparse matrix useful for SpMV code selection.
KW - SpMV
KW - autotuning
KW - code selection
KW - deep learning
UR - http://www.scopus.com/inward/record.url?scp=85010303461&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85010303461&partnerID=8YFLogxK
U2 - 10.1109/MCSoC.2016.46
DO - 10.1109/MCSoC.2016.46
M3 - Conference contribution
AN - SCOPUS:85010303461
T3 - Proceedings - IEEE 10th International Symposium on Embedded Multicore/Many-Core Systems-on-Chip, MCSoC 2016
SP - 385
EP - 392
BT - Proceedings - IEEE 10th International Symposium on Embedded Multicore/Many-Core Systems-on-Chip, MCSoC 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th IEEE International Symposium on Embedded Multicore/Many-Core Systems-on-Chip, MCSoC 2016
Y2 - 21 September 2016 through 23 September 2016
ER -