Code Optimization in Compilers using ANN

Today’s compilers have a plethora of optimizations to choose from, and the correct choice of optimizations can have a significant impact. Furthermore, choosing the correct order in which to apply those optimizations has been a long standing problem in compilation research. Traditional compilers typically apply the same set of optimization in a fixed order to all functions in a program, without regard the code being optimized. Understanding the interactions of optimizations is very important in determining a good solution to the phase ordering problem. We will develop a system that automatically selects good optimization orderings on a per method basis within a dynamic compiler by including profiles of programs. Keywords— Compilers; Code Optimization; Artificial Neural Networks; Feature set; Profiles