It is very natural when people compile their programs, they would require a compiler that gives the best program performance. Even though today’s compiler have reached the point in which they provide the users a large number of options, however, because of the unavailability of program input data and insufficient knowledge of the target architecture; it can still seriously limit the accuracy of compile-time performance models. Thus, the problem is how to choose the best combination of optimization options provided by compiler for a given program or program section. This gives rise the requirement of an orchestration algorithm that fast and effective to search for the best optimization combination for a program.There have been several algorithms developed, such as Exhaustive Search (ES); Batch Elimination (BE); Iterative Elimination (IE); Combined Elimination (CE); Optimization Space Exploration (OSE); and Statistical Selection (SS). Based on those of algorithms, in this paper we proposed Heuristics Elimination (HE) algorithm, a simple algorithm that was mostly inspired by OSE with some differences. The HE algorithm uses a heuristic approach by applying genetic algorithm to find the best combination of compiler’s optimization options. It is unlike OSE, however, this proposed algorithm starts from a set of some possible combinations randomly selected, then they are iteratively refined by some genetic operators to find one optimal combination (as the solution).