Abstract
Architecture simulations may take days during design when silicon is not available. Long simulation time is impractical; yet the cost of early design mistake is high. Hence, fast architectural parameter exploration without rigorous simulation is an important problem. Analytical models can execute fast. However, few analytical models can produce benchmark performance of a design. The presented method, termed Fast Benchmarking, based on analytical models, can produce benchmark performance of a processor in a few hundred milliseconds. With accurate model, performance data produced by the tool is accurate. For example, instruction fetch results differ by 7±% on average with simulations. This article further extends the concept by presenting a new method for analytically guided adaptive architecture simulation. To our knowledge, no other work has presented a full methodology to use analytical models for the study of processor performance during design. The method gives birth to a valuable tool that can be used in the industry for designing high-performance multi-core, multi-threaded processors.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
