Jump prediction

Details Jump prediction Jump prediction

1996-02-07

1998-02-24

Treat, William M.

39542103, 3954211, G06F 938

Patent

active

057218943

ABSTRACT:
A pipelined data processing system has a jump prediction mechanism for predicting the outcomes of jump instructions. The prediction mechanism includes a jump prediction memory which provides the predictions. The jump prediction memory is addressed by a jump signature, formed by adjustably selecting bits from an address value and from a jump path value. The address value is based on the address of the jump instruction and the jump path value is based on a history of recently executed jump instructions prior to said jump instruction. A mode register is used to indicate, for each bit of the jump signature, whether that bit is to be selected from the address value or from the jump path value. Adjustment of the contents of the mode register allows fine tuning of the jump prediction mechanism to optimize performance.

REFERENCES:
patent: 5553253 (1996-09-01), Pan et al.
"Polymorphic Branch Predictor", IBM Technical Disclosure Bulletin, vol. 37, No. 07, Jul. 1994, pp. 109-113.
Pan, "Improving the Accuracy of Dynamic Branch Prediction Using Branch Correlation", ACM SIGPLAN Notices, vol. 27, No. 9, Sep. 1992, pp. 76-84.
"Branch History Indexing with Execution Path Information", IBM Technical Disclosure Bulletin, vol. 36, No. 08, Aug. 1993, pp. 557-558.
Chang, "Alternative Implementations of Hybrid Branch Predictors", IEEE Symposium on Microarchitecture, Nov. 29-Dec. 1, 1995, pp. 252-257.
Pan et al., "Improving the Accuracy of Dynamic Branch Prediction Using Branch Correlation", ASPLOS V, ACM, Oct. 1992, pp. 76-84.

Affiliated with

Also associated with

Rating

Jump prediction does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Jump prediction, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Jump prediction will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1881430