处理器硅前性能评估仿真点全局贪心分配方法OA

SimPoint,as a representative sampling technique,is widely employed in pre-silicon performance evaluation of processors.SimPoint determines the number of simulation points for each program based on the Bayesian informa-tion criterion,yet it fails to recognize the complexity variations among different programs.However,within a stand-ard test suite,different programs exhibit varying levels of behavioral complexity,necessitating different numbers of simulation points to accurately characterize their behaviors.Given a fixed total number of simulation points,Sim-Point is incapable of allocating more simulation points to more complex programs to reduce their performance evaluation errors while assigning fewer simulation points to simpler programs without compromising their perform-ance evaluation accuracy.Due to the lack of a global view of the test suite,although SimPoint can provide relatively accurate average performance evaluation errors,certain behaviorally complex programs still exhibit significant per-formance evaluation errors.To address this issue,this paper optimizes the local allocation of simulation points with-in the SimPoint method and proposes a global greedy allocation method,GreedyPoint.This method abstracts the simulation point allocation problem as a constrained optimization problem,utilizes microarchitecture-independent characteristics to quantify represent errors,and employs a global greedy algorithm to solve the optimization prob-lem.Experimental data indicate that,under the same simulation overhead,compared to SimPoint,GreedyPoint reduces the average performance evaluation error of the SPEC CPU 2017 test suite from 3.23％to 2.08％,and sig-nificantly decreases the maximum performance evaluation error from 21.22％to 7.01％.