On Table Bandwidth and Its Update Delay for Value Prediction on Wide-Issue ILP Processors

We study two issues which could affect the performance of value prediction on wide-issue ILP processors. One is the large number of accesses to the value prediction tables needed in each machine cycle, and the other is the delay required to update stale values in the value prediction tables. We introduce a prediction value cache (PVC) which augments the instruction cache to hold the prediction values to handle these issues.

[1]  Todd M. Austin,et al.  The SimpleScalar tool set, version 2.0 , 1997, CARN.

[2]  Sang Jeong Lee,et al.  Decoupled value prediction on trace processors , 2000, Proceedings Sixth International Symposium on High-Performance Computer Architecture. HPCA-6 (Cat. No.PR00550).

[3]  John Paul Shen,et al.  Efficacy and performance impact of value prediction , 1998, Proceedings. 1998 International Conference on Parallel Architectures and Compilation Techniques (Cat. No.98EX192).

[4]  Kai Wang,et al.  Highly accurate data value prediction using hybrid predictors , 1997, Proceedings of 30th Annual International Symposium on Microarchitecture.

[5]  Avi Mendelson,et al.  The effect of instruction fetch bandwidth on value prediction , 1998, ISCA.

[6]  John Paul Shen,et al.  Efficient and Accurate Value Prediction Using Dynamic Classification , 1998 .

[7]  MendelsonAvi,et al.  The effect of instruction fetch bandwidth on value prediction , 1998 .

[8]  Pen-Chung Yew,et al.  On some implementation issues for value prediction on wide-issue ILP processors , 2000, Proceedings 2000 International Conference on Parallel Architectures and Compilation Techniques (Cat. No.PR00622).

[9]  James E. Smith,et al.  The predictability of data values , 1997, Proceedings of 30th Annual International Symposium on Microarchitecture.