Back to Search Start Over

A Stochastic Performance Model for Pipelined Krylov Methods

Authors :
Morgan, Hannah
Knepley, Matthew G.
Sanan, Patrick
Scott, L. Ridgway
Publication Year :
2016

Abstract

Pipelined Krylov methods seek to ameliorate the latency due to inner products necessary for projection by overlapping it with the computation associated with sparse matrix-vector multiplication. We clarify a folk theorem that this can only result in a speedup of $2\times$ over the naive implementation. Examining many repeated runs, we show that stochastic noise also contributes to the latency, and we model this using an analytical probability distribution. Our analysis shows that speedups greater than $2\times$ are possible with these algorithms.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1602.04873
Document Type :
Working Paper