Dual decode architecture for dynamic branch prediction

Vishnu P. Bharadwaj, Manjunath Kohalli

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

One of the old techniques for performance improvements is branch prediction. As the branch misprediction rate has reached less than 0.01 for certain techniques, it is safe to say that current branch prediction techniques are very efficient. But for certain critical applications a small misprediction also poses a problem. In this paper, a new prediction technique is discussed which always predicts the branch correctly. This technique works well for else if loop at the cost of increased hardware resources.

Original languageEnglish
Title of host publication2017 2nd International Conference for Convergence in Technology, I2CT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1140-1143
Number of pages4
Volume2017-January
ISBN (Electronic)9781509043071
DOIs
Publication statusPublished - 18-12-2017
Externally publishedYes
Event2nd International Conference for Convergence in Technology, I2CT 2017 - Pune, India
Duration: 07-04-201709-04-2017

Conference

Conference2nd International Conference for Convergence in Technology, I2CT 2017
CountryIndia
CityPune
Period07-04-1709-04-17

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Networks and Communications
  • Information Systems and Management
  • Health Informatics
  • Communication

Fingerprint Dive into the research topics of 'Dual decode architecture for dynamic branch prediction'. Together they form a unique fingerprint.

  • Cite this

    Bharadwaj, V. P., & Kohalli, M. (2017). Dual decode architecture for dynamic branch prediction. In 2017 2nd International Conference for Convergence in Technology, I2CT 2017 (Vol. 2017-January, pp. 1140-1143). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/I2CT.2017.8226306