Please use this identifier to cite or link to this item:
Title: A comprehensive analysis of indirect branch prediction
Authors: Santana, Oliverio J. 
Falcón, Ayose
Fernández, Enrique 
Medina, Pedro 
Raḿrez, A.
Valero, Mateo
UNESCO Clasification: 330406 Arquitectura de ordenadores
Keywords: Microarchitecture
Branch prediction
Branch target buffer
Indirect branch
Multi-stage cascaded predictor
Issue Date: 2002
Journal: Lecture Notes in Computer Science 
Conference: 4th International Symposium on High Performance Computing, ISHPC 2002 
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.
ISBN: 978-3-540-43674-4
ISSN: 0302-9743
DOI: 10.1007/3-540-47847-7_13
Source: Zima H.P., Joe K., Sato M., Seo Y., Shimasaki M. (eds) High Performance Computing. ISHPC 2002. Lecture Notes in Computer Science, vol 2327. Springer, Berlin, Heidelberg
Appears in Collections:Actas de congresos
Show full item record


checked on Feb 28, 2021

Page view(s)

checked on Feb 28, 2021

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.