Work can be found on https://docs.google.com/document/d/1VIH3Y10lPmNawKz7RS_vak2KJJaEGGTNwjf_Pz_M-EA/edit
Branch prediction is a technique used in CPU design that attempts to guess the outcome of a conditional operation and prepare for the most likely result. A digital circuit that performs this operation is known as a branch predictor. It is an important component of modern CPU architectures, such as the x86.
In this work, the problem of branch prediction is treated as a binary classification problem. I use an off-line training methods such as Decision Trees, Random Forest and MLP to compare them with current SOTA - TAGE predictor.
Branch prediction, binary classification, Decision Tree, Random Forest, MLP
