Branch transition rate: A new metric for improved branch classification analysis

IEEE High-Performance Computer Architecture Symposium Proceedings

Volumn , Issue , 2000, Pages 241-250

  Haungs, Michael ^a   Sallee, Phil ^a   Farrens, Matthew ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATION THEORY; COMPUTER ARCHITECTURE; CORRELATION METHODS; SET THEORY;

BRANCH CLASSIFICATION; BRANCH TRANSITION RATE; CONDITIONAL BRANCHES; INSTRUCTION LEVEL PARALLELISM;

PARALLEL PROCESSING SYSTEMS;

EID: 0034581531     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (23)

1. Improving branch prediction accuracy by reducing pattern history table interference
2. Branch classification: A new mechanism for improving branch predictor performance
3. Analysis of branch prediction via data compression
4. The yags branch prediction scheme
5. An analysis of correlation and predictability: What makes two-level branch predictors work
6. Confidence estimation for speculation control
7. Static methods in hybrid branch prediction
8. Selective dual path execution
9. Assigning confidence to conditional branch predictions
10. Dynamic history-length fitting: A third level of adaptivity for branch prediction
11. Analyzing the working set characteristics of branch execution
12. Selective eager evaluation on the polypath architecture
13. The bi-mode branch predictor
14. Hybrid branch prediction using limited dual path execution
15. Characterizing the impact of predicated execution on branch prediction
16. Combining branch predictors
17. Trading conflict and capacity aliasing in conditional branch predictors
18. The agree predictor: A mechanism for reducing negative branch history interference
19. Variable length path branch prediction
20. Two-level adaptive branch prediction
21. Alternative implementations of two-level adaptive branch prediction
22. A comparative analysis of schemes for correlated branch prediction