skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Resilient Computing with Dynamical Systems.

Abstract

We reformulate fundamental numerical problems to run on novel hardware inspired by the brain. Such "neuromorphie hardware consumes less energy per computation, promising a means to augment next-generation exascale computers. However, their programming model is radically different from floating-point machines, with fewer guarantees about precision and communication. The approach is to pass each given problem through a sequence of transformations (algorithmic "reductions") which change it from conventional form into a dynamical system, then ultimately into a spiking neural network. Results for the eigenvalue problem are presented, showing that the dynamical system formulation is feasible. This page left blank

Authors:
;
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1569151
Report Number(s):
SAND2019-10963
679662
DOE Contract Number:  
AC04-94AL85000
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English

Citation Formats

Rothganger, Fredrick, and Cardwell, Suma George. Resilient Computing with Dynamical Systems.. United States: N. p., 2019. Web. doi:10.2172/1569151.
Rothganger, Fredrick, & Cardwell, Suma George. Resilient Computing with Dynamical Systems.. United States. doi:10.2172/1569151.
Rothganger, Fredrick, and Cardwell, Suma George. Sun . "Resilient Computing with Dynamical Systems.". United States. doi:10.2172/1569151. https://www.osti.gov/servlets/purl/1569151.
@article{osti_1569151,
title = {Resilient Computing with Dynamical Systems.},
author = {Rothganger, Fredrick and Cardwell, Suma George},
abstractNote = {We reformulate fundamental numerical problems to run on novel hardware inspired by the brain. Such "neuromorphie hardware consumes less energy per computation, promising a means to augment next-generation exascale computers. However, their programming model is radically different from floating-point machines, with fewer guarantees about precision and communication. The approach is to pass each given problem through a sequence of transformations (algorithmic "reductions") which change it from conventional form into a dynamical system, then ultimately into a spiking neural network. Results for the eigenvalue problem are presented, showing that the dynamical system formulation is feasible. This page left blank},
doi = {10.2172/1569151},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {9}
}