search-icon
Workshop
:
On Advanced Monte Carlo Methods for Linear Algebra on Advanced Accelerator Architectures
Event Type
Workshop
Registration Categories
W
Tags
Algorithms
Heterogeneous Systems
Resiliency
TimeMonday, November 12th5:10pm - 5:30pm
LocationD161
DescriptionIn this paper we present computational experiments performed using the Markov Chain Monte Carlo Matrix Inversion (MCMCMI) on several architectures of NVIDIA accelerators and two iterations of the Intel x86 architecture and investigate their impact on performance and scalability of the method.
The method is used as a preconditioner and iterative methods, such as generalized minimal residuals (GMRES) or bi-conjugate gradient stabilized (BICGstab), are used for solving the corresponding system of linear equations.
Numerical experiments are carried out to highlight the benefits and deficiencies of both architecture types and to assess their overall usefulness in light of the scalability of the method.
Archive
Back To Top Button