Practical Multidimensional Branch Prediction

André Seznec 1 Joshua San Miguel 2 Jorge Albericio 2
1 ALF - Amdahl's Law is Forever
Inria Rennes – Bretagne Atlantique , IRISA-D3 - ARCHITECTURE
Abstract : The most efficient branch predictors proposed in academic literature exploit both global branch history and local history. However, local history predictors introduce major design challenges, particularly for the management of speculative histories. The wormhole (WH) branch predictor was recently introduced to exploit branch outcome correlation via multidimensional histories. For some branches encapsulated in a multidimensional loop, their outcomes are correlated with those of the same branch in neighbor iterations, but in the previous outer loop iteration. Unfortunately, the practical implementation of the WH predictor is even more challenging than the implementation of local history predictors. In this paper, we introduce a practical, cost-effective mechanism for capturing multidimensional branch correlations: the Inner Most Loop Iteration (IMLI) counter.
Document type :
Journal articles
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01330510
Contributor : André Seznec <>
Submitted on : Friday, June 10, 2016 - 6:51:41 PM
Last modification on : Thursday, February 7, 2019 - 2:24:52 PM

File

MI_MicroSI-2016-01-0007_Alberi...
Files produced by the author(s)

Identifiers

Citation

André Seznec, Joshua San Miguel, Jorge Albericio. Practical Multidimensional Branch Prediction. IEEE Micro, Institute of Electrical and Electronics Engineers, 2016, ⟨10.1109/MM.2016.33⟩. ⟨hal-01330510⟩

Share

Metrics

Record views

678

Files downloads

682