A Performance Evaluation of QR-eigensolver on IBM Roadrunner cluster for Large Sparse Matrices

The paper presents a performance analysis of theQR eigensolver from ScaLAPACK library on the IBMRoadrunner machine. A ScaLAPACK-based testing platformwas developed in order to evaluate the performance of a parallelsolver to compute the eigenvalues and eigenvectors for largescalesparse matrices. Our...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of applied computer science & mathematics 2013-01, Vol.7 (14), p.38-41
Hauptverfasser:	Ionela RUSU, Stefan Gh. PENTIUC, Elena Gina CRACIUN, Stefania SOIMAN
Format:	Artikel
Sprache:	eng
Schlagworte:	eigenvalues high performance computing QR factorization ScaLAPACK systems of linear equations
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The paper presents a performance analysis of theQR eigensolver from ScaLAPACK library on the IBMRoadrunner machine. A ScaLAPACK-based testing platformwas developed in order to evaluate the performance of a parallelsolver to compute the eigenvalues and eigenvectors for largescalesparse matrices. Our experiments showed encouragingresults on the IBM Roadrunner cluster, the acceleration factorgained was up to 40 for large matrices. This result is bright tosolve problems that involve scientific and large-scale computing.
ISSN:	2066-4273 2066-3129