Exceeding the dataflow limit via value prediction
Proceedings of the 29th annual ACM/IEEE international symposium on Microarchitecture
The predictability of data values
MICRO 30 Proceedings of the 30th annual ACM/IEEE international symposium on Microarchitecture
Highly accurate data value prediction using hybrid predictors
MICRO 30 Proceedings of the 30th annual ACM/IEEE international symposium on Microarchitecture
The effect of instruction fetch bandwidth on value prediction
Proceedings of the 25th annual international symposium on Computer architecture
Exploiting value locality to exceed the dataflow limit
International Journal of Parallel Programming - Special issue: MICRO-29, 29th annual IEEE/ACM international symposium on microarchitecture
ISCA '99 Proceedings of the 26th annual international symposium on Computer architecture
Table size reduction for data value predictors by exploiting narrow width values
Proceedings of the 14th international conference on Supercomputing
Automatically characterizing large scale program behavior
Proceedings of the 10th international conference on Architectural support for programming languages and operating systems
Partial Resolution in Data Value Predictors
ICPP '00 Proceedings of the Proceedings of the 2000 International Conference on Parallel Processing
Detecting global stride locality in value streams
Proceedings of the 30th annual international symposium on Computer architecture
HPCA '02 Proceedings of the 8th International Symposium on High-Performance Computer Architecture
Picking Statistically Valid and Early Simulation Points
Proceedings of the 12th International Conference on Parallel Architectures and Compilation Techniques
Characterizing and Comparing Prevailing Simulation Techniques
HPCA '05 Proceedings of the 11th International Symposium on High-Performance Computer Architecture
Hi-index | 0.01 |
Stride data value predictor is widely used by researchers in data value prediction study. Compared with context-based hybrid data value predictors, stride data value predictors are simple. But when encountering non-stride repeated sequences, a stride value predictor does not perform as well as a contextbased hybrid data value predictor. In this paper, a revised stride data value predictor is introduced. With a little augment to a traditional stride data value predictor, the new predictor can make correct predictions on some patterns that can only be done by the context-based data value predictors. Simulation results show that the new predictor works well with most value predictable instructions. Design decisions such as predictor size, confidence mechanism and storing partial tag are analyzed.