A comprehensive analytical model for embedded parallel microprocessors performance prediction
Mauro Olivieri, Mirko Scarana · 2005
This paper presents an analytical model for the early performance prediction of VLSI microprocessor cores. The model involves a wide set of architecture parameters (including data on memory hierarchy data, branch prediction and pipeline organization) and instruction level parameters as well as statistical information obtained from an ad-hoc version of the SimpleScalar toolset. The model validation against cycle accurate simulation shows a very good fitting.