David R. Kaeli
Philip G. Emma
- 1 Kaeli I).R., Kirkpatrick S., Ong S., "PC Workload Characterization', Proceedings of the ACM Sigmetrics and I~erlbrmance "89", May 89, pp.220.Google Scholar
- 2 Adams T., Zimmerman R., "An Analysis of 8086 instruction usage in MS DOS programs', Proc. Third Symposium on Architectural Support For Programming l~anguages arid Operating Systems, Boston, 1989, pps.152-161. Google ScholarDigital Library
- 3 Clark I).W., i.evy II., "Measurement and Analysis of Instruction Use in the VAX 11/78{1", Proc. Ninth Symposium o~ Computer Architecture, Austin, Tx., April 1982, pps.9-17. Google ScholarDigital Library
- 4 Grohoski G.F., "Machine Organization of the IBM RIS(~ System/6{)00 processor", IBM Journal of Research and Development, Vol.34, No.l, Jan. 1990, pps.37-58. Google ScholarDigital Library
- 5 Patterson I).A, "Reduced Instruction Set Computers', Communications of the ACM, Vol.28-1, Jan, 1085, pps.8-21. Google ScholarDigital Library
- 6 Ditzel I).R., McLellan I I.R., "Branch Folding in the Crisp Microprocessor: Reducing Branch Delay to Zero," Proc. 14th Ann. Syrup. Computer Arch., 1987, pps.2-9. Google ScholarDigital Library
- 7 Anderson D.W. etal., "'File IBM System/360 Model 91" Machine pllilosophy and instruction handling', IBM Journal of Research and l)evclopment, Jan. 1967, pps.8-24.Google ScholarDigital Library
- 8 Campbell R., "Compiling C for the Reduced Instruction Set Computer", Master's report, EECS, U.fL Berkeley 94721), l)ec. 198(I.Google Scholar
- 9 Sll~ittl J.l~., "A Study of Branch Prediction Strategies', l~roc, i';ightll Sylnposiutn on (.'olnputer Architecture, May 1981, Minneapolis, pps.135-148. Google ScholarDigital Library
- 10 l~ee J., Smith A.J., "Branch Prediction Strategies and Branch "l'arget Buffer l)esign~, Computer 17:1, Jan. 1984, pps.6-22.Google ScholarDigital Library
- 11 Ilolgate R.W., ibbett R.N., "An Analysis of lnslruclion-l:etcl~ing Strategies in Pipelined (2omputers". IEI';E 'l'rans. on Computers. Voi.C-29. No.4, April 198{}, pps. 325-329.Google Scholar
- 12 I luglles J.I:., I.iplay J.S., Rymarczyk J.W., Stone S.E., ~Mtllti-lnslruclion Stream Branch Processing Mect~anism", U.S. Patent 4,200,927, Apr. 29, 1980.Google Scholar
- 13 Lilja D.J., "Reducing the Branch Penalty in Pipelined Processors', IEEE Computer Magazine, July 1988, pps.47-55. Google ScholarDigital Library
- 14 Pomerene J.H., Puzak T.R., Rechtschaffen R.N., Rosenfeld P.L., Sparacio F.J., "Pageable Branch History Table', U.S. Patent 4,679,141, Jul. 7, 1987.Google Scholar
- 15 Smith A.J., "Cache Memories', Computing Surveys, Vol.14 No.3, Sept. 1982. pps.473-530. Google ScholarDigital Library
- 16 SPEC Quarterly Newsletter, System Performance Evaluation Cooperative, 1st Quarter 1990.Google Scholar
- 17 Webb C.F., "Subroutine Call/Return Stack', IBM Tech. Disc. Bullen., Vol.30, No.1 I, April 1988.Google Scholar
Index Terms
- Branch history table prediction of moving target branches due to subroutine returns
Recommendations
The Impact of Branch Direction History Combined with Global Branch History in Branch Prediction
Most branch predictors use the PC information of the branch instruction and its dynamic Global Branch History (GBH). In this letter, we suggest a Branch Direction History (BDH) as the third component of the branch prediction and analyze its impact upon ...
Dynamic per-branch history length adjustment to improve branch prediction accuracy
Branch misprediction limits processor performance significantly, as the pipeline deepens and the instruction issued per cycle increases. Since the introduction of the two-level adaptive branch predictor, branch history has been a major input vector in ...
Branch history table prediction of moving target branches due to subroutine returns
ISCA '91: Proceedings of the 18th annual international symposium on Computer architecture
Comments