2.1 Introduction

This chapter describes recent advances in genetic programming of machine code. Evolutionary program induction using binary machine code is the fastest known Genetic Programming method. It is, in addition, the most well studied Genetic Programming system that uses a linear genome. Evolutionary program induction using binary machine code was originally referred to as Compiling Genetic Programming System (CGPS). For clarity, the name was changed in early 1998 to Automatic Induction of Machine Code—Genetic Programming (AIM-GP). AIM-GP stores evolved programs as linear strings of native binary machine code, which are directly executed by the processor. The absence of an interpreter and complex memory handling increases the speed of AIM-GP by about two orders of magnitude. AIM-GP has so far been applied to processors with a fixed instruction length (RISC) using integer and floating-point arithmetic. We also describe several recent advances in the AIM-GP technology. Such advances include enabling the induction of code for CISC processors such as the INTEL x86 as well as JAVA and many embedded processors. The new techniques also make AIM-GP more portable in general and simplify the adaptation to any processor architecture. Other additions include the use of floating point instructions, control flow instructions, ADFs and new genetic operators e.g. aligned homologous crossover. This chapter also discusses the benefits and drawbacks of register machine GP versus tree-based GP. This chapter is directed towards the practitioner, who wants to extend AIM-GP to new architectures and application domains.