TY - GEN
T1 - Predicting the solvability space of the preconditioned krylov subspace methods
AU - Xu, Shuting
AU - Kim, Sang Bae
AU - Zhang, Jun
PY - 2016
Y1 - 2016
N2 - In this paper we predict the parameter solvability space of the preconditioned Krylov subspace methods with two or more parameters. The parameter solvability space is usually irregular, however, in many situations it shows spatial locality, i.e. the parameter locations that are closer in parameter space are more likely to have similar solvability. We propose three methods to predict the solvability of ILUT which make usage of spatial locality in different ways. The three methods are multi-points SVM classifier (MSC), overall SVM classifier (OSC), and Overall Spatial Autoregressive Classifier (OSAC). The experimental results show that both MSC and OSAC can obtain 90% accuracy in prediction, but OSAC is much simpler to implement. We focus our work on ILUT preconditioner [6], but the proposed strategies should be applicable to other preconditioners with two or more parameters. Copyright ISCA.
AB - In this paper we predict the parameter solvability space of the preconditioned Krylov subspace methods with two or more parameters. The parameter solvability space is usually irregular, however, in many situations it shows spatial locality, i.e. the parameter locations that are closer in parameter space are more likely to have similar solvability. We propose three methods to predict the solvability of ILUT which make usage of spatial locality in different ways. The three methods are multi-points SVM classifier (MSC), overall SVM classifier (OSC), and Overall Spatial Autoregressive Classifier (OSAC). The experimental results show that both MSC and OSAC can obtain 90% accuracy in prediction, but OSAC is much simpler to implement. We focus our work on ILUT preconditioner [6], but the proposed strategies should be applicable to other preconditioners with two or more parameters. Copyright ISCA.
UR - http://www.scopus.com/inward/record.url?scp=84973395012&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84973395012&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84973395012
T3 - Proceedings of the 31st International Conference on Computers and Their Applications, CATA 2016
SP - 293
EP - 297
BT - Proceedings of the 31st International Conference on Computers and Their Applications, CATA 2016
A2 - Bossard, Antoine
T2 - 31st International Conference on Computers and Their Applications, CATA 2016
Y2 - 4 April 2016 through 6 April 2016
ER -