Research on the influencing factors of LLVM IR optimization effect

The intermediate representation has a natural advantage in solving the problem of cross-architecture binary code similarity detection, which can greatly reduce the amount of data required for machine learning model training and improve the versatility and scalability of the model. optimizing the intermediate representation can solve the problem of binary differences caused by different compilation architectures, compilers, optimization options, and obfuscation strategies, which is conducive to improving the accuracy of binary code similarity detection. We explored the effects of compilation architectures, compilers, optimization options and obfuscation strategies on the optimization of intermediate representations through four experiments. The experimental results show that the compilers GCC and Clang at the time of binary file compilation have a significant improvement on the optimization effect of intermediate representation. In addition, the optimization effect using opt-Ol and opt-O2 is the best, and the similarity can be improved by up to 21.7%. The compiler architectures XS6_32, XS6_64, ARM32, ARM64 and optimization options −OO, −Ol, −O2, −O3 have little effect on the optimization effect of the intermediate representation. The compiler architecture MIP32 and obfuscation strategies F1a, Sub, Bcf, All have a negative effect on the optimization effect of intermediate representation.