6.5. Program flow prediction

The Cortex-A57 MPCore multiprocessor contains program flow prediction hardware, also known as branch prediction. With program flow prediction disabled, all taken branches incur a penalty associated with flushing the pipeline. To avoid this penalty, the branch prediction hardware operates at the front of the instruction pipeline. The branch prediction hardware consists of:

The combination of global history-based direction predictor and BTB are called dynamic predictor.

This section describes program flow prediction in:

Copyright © 2013, 2014 ARM. All rights reserved.ARM DDI 0488D
Non-ConfidentialID012914