A Comprehensive Analysis of Indirect Branch Prediction

  • Authors:
  • Oliverio J. Santana;Ayose Falcón;Enrique Fernández;Pedro Medina;Alex Ramírez;Mateo Valero

  • Affiliations:
  • Dpto. de Arquitectura de Computadores, Universidad Politécnica de Cataluccña, Spain;Dpto. de Arquitectura de Computadores, Universidad Politécnica de Cataluccña, Spain;Dpto. de Informática y Sistemas, Universidad de Las Palmas de Gran Canaria, Spain;Dpto. de Informática y Sistemas, Universidad de Las Palmas de Gran Canaria, Spain;Dpto. de Arquitectura de Computadores, Universidad Politécnica de Cataluccña, Spain;Dpto. de Arquitectura de Computadores, Universidad Politécnica de Cataluccña, Spain

  • Venue:
  • ISHPC '02 Proceedings of the 4th International Symposium on High Performance Computing
  • Year:
  • 2009
  • Multiple stream prediction

    ISHPC'05/ALPS'06 Proceedings of the 6th international symposium on high-performance computing and 1st international conference on Advanced low power systems

Quantified Score

Hi-index 0.00

Visualization

Abstract

Indirect branch prediction is a performance limiting factor for current computer systems, preventing superscalar processors from exploiting the available ILP. Indirect branches are responsible for 55.7% of mispredictions in our benchmark set, although they only stand for 15.5% of dynamic branches. Moreover, a 10.8% average IPC speedup is achievable by perfectly predicting all indirect branches.The Multi-Stage Cascaded Predictor (MSCP) is a mechanism proposed for improving indirect branch prediction. In this paper, we show that a MSCP can replace a BTB and accurately predict the target address of both indirect and non-indirect branches. We do a detailed analysis of MSCP behavior and evaluate it in a realistic setup, showing that a 5.7% average IPC speedup is achievable.