Optimal prefetching via data compression (extended abstract)
SFCS '91 Proceedings of the 32nd annual symposium on Foundations of computer science
Alternative implementations of two-level adaptive branch prediction
ISCA '92 Proceedings of the 19th annual international symposium on Computer architecture
Improving the accuracy of dynamic branch prediction using branch correlation
ASPLOS V Proceedings of the fifth international conference on Architectural support for programming languages and operating systems
Practical prefetching via data compression
SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
A comparative analysis of schemes for correlated branch prediction
ISCA '95 Proceedings of the 22nd annual international symposium on Computer architecture
Analysis of branch prediction via data compression
Proceedings of the seventh international conference on Architectural support for programming languages and operating systems
The context-tree weighting method: basic properties
IEEE Transactions on Information Theory
LeZi-update: an information-theoretic framework for personal mobility tracking in PCS networks
Wireless Networks - Selected Papers from Mobicom'99
The VPC Trace-Compression Algorithms
IEEE Transactions on Computers
Dynamic feature selection for hardware prediction
Journal of Systems Architecture: the EUROMICRO Journal
Hi-index | 0.00 |
Data compression and prediction are closely related. Thus prediction methods based on data compression algorithms have been suggested for the branch prediction problem. In this work we consider two universal compression algorithms: prediction by partial matching (PPM), and a recently developed method, context tree weighting (CTW). We describe the prediction algorithms induced by these methods. We also suggest adaptive algorithms --- variations of the basic methods that attempt to fit limited memory constraints and to match the non-stationary nature of the branch sequence. Furthermore, we show how to incorporate address information and to combine other relevant data. Finally, we present simulation results for selected programs from the SPECint95, SYSmark/32, SYSmark/NT, and transactional processing benchmarks. Our results are most promising in programs with difficult to predict branch behavior.