A Practical Low-Power Memristor-based Analog Neural Branch Predictor

  • Jianxing Wang
  • Yenni Tim
  • Weng-fai Wong
  • Hai (helen Li
ORKG logo Add to ORKG
Publication date
August 2015

Abstract

Recently, the discovery of memristor brought the promise of high density, low energy, and combined memory/arithmetic capability into computing. This paper demonstrates a practical neural branch predictor based on memristor. By using analog computation techniques, as well as exploiting the accuracy tolerance of branch prediction, our design is able to efficiently realize a neural prediction algorithm. Compared to the digital counterpart, our method achieves significant energy reduction while maintaining a better prediction accuracy and a higher IPC. Our approach also reduces the resource and energy required by an alternative design

Extracted data

Loading...

Related items

A practical low-power memristor-based analog neural branch predictor
  • Wang, J.
  • Tim, Y.
  • Wong, W.-F.
  • Li, H.H.
January 2013

10.1109/ISLPED.2013.6629290Proceedings of the International Symposium on Low Power Electronics and D...

Mixed-signal neural network branch prediction,” unpublished manuscript
  • Owen Kirby
  • Shahriar Mirabbasi
  • Tor M. Aamodt
December 2014

Accurate branch prediction is essential for modern microprocessors in order to maintain high in-stru...

Implementation of a block based neural branch predictor
  • Cadenas, O.
  • Megson, G.M.
  • Jones, D.J.
  • Cadenas, O.
  • Megson, G.M.
  • Jones, D.J.
January 2005

This paper contributes to a dynamic branch predictor algorithm based on a perceptron in two directio...

We use cookies to provide a better user experience.