Neuromorphic computing systems such as DYNAPs and Loihi have recently been introduced to the computing community to improve performance and energyefficiency of machine learning programs . The role of a system software forneuromorphic systems is to cluster a large machine learning model (e.g., withmany neurons and synapses) and map these clusters to computing resources of the hardware . We formulate a simpleheuristic-based mapping approach to place the neurons andsynapses onto thecomputing resources to reduce energy consumption . We evaluate our approach with10 machine learning applications and demonstrate that the proposed mapping approach leads to a significant reduction of energy consumption of neuromorphiccomputing systems. We demonstrate that proposed mapping approaches leads to the . proposed mappingapproach leads to . a significant .

Author(s) : Twisha Titirsha, Shihao Song, Adarsha Balaji, Anup Das

Links : PDF - Abstract

Code :
Coursera

Keywords : computing - approach - mapping - systems - energy -

Leave a Reply

Your email address will not be published. Required fields are marked *