Lean and Efficient Software: Whole-Program Optimization of Executables

Abstract : The objective of this project is to investigate the feasibility of improving the performance, size, and robustness of binary executables by using static and dynamic binary program analysis techniques to perform whole-program optimization directly on compiled programs. The scope includes analyzing the effectiveness of techniques for specializing library subroutines, removing redundant argument checking and interface layers, eliminating dead code, and improving computational efficiency. The contractor expects the optimizations to be applied at or immediately prior to deployment of software, allowing them to tailor the optimized software to its target platform. Today, machine-code analysis and binary-rewriting techniques have reached a sufficient maturity level to make whole-program, machine-code optimization feasible. These techniques open avenues for aggressive optimization that benefit from detailed knowledge of an application's composition and its environment.