Modeling superscalar processors via statistical simulation

Parallel Architectures and Compilation Techniques - Conference Proceedings, PACT

Volumn , Issue , 2001, Pages 15-24

  Nussbaum, Sébastien ^a   Smith, James E ^a  

^a University of Wisconsin Madison   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; ERROR ANALYSIS; INFORMATION ANALYSIS; PROBABILISTIC LOGICS; STATISTICAL METHODS;

SUPERSCALAR PROCESSORS;

PROGRAM PROCESSORS;

EID: 0035177240     PISSN: 1089795X     EISSN: None     Source Type: Journal    
DOI: 10.1109/PACT.2001.953284     Document Type: Article

References (17)

1. The simplescalar tool set, version 2.0
2. Performance analysis and its impact on design
3. Performance evaluation and validation of microprocessors
4. Adapting the SPEC 2000 benchmark suite for simulation-based computer architecture research
5. Reducing state loss for effective trace sampling of superscalar processors
6. Code cloning tracing: A "pay per trace" Approach
7. Instruction window size trade-offs and characterization of program parallelism
8. A framework for statistical modeling of superscalar processor performance
9. Modeling superscalar processors via statistical simulation
10. Performance analysis through synthetic trace generation
11. HLS: Combining statistical and symbolic simulation to guide microprocessor design
12. Microprocessor power estimation using profile-driven program synthesis
13. Analysis of benchmark characteristics and benchmark performance prediction
14. Techniques for cache and memory simulation using address reference traces
15. An automated and flexible framework for integrated processor and system-level design space exploration