Skip to main content

Optimized Assembly Tests from Machine Learning Correlation Algorithms

We explore ways of developing more efficient x86 assembly tests which check for functional coverage. The current testing suite used by our sponsor contains redundancies caused by the pseudo randomly generated test files. These redundancies lead to wasted computational time and resources. In our solution, we analyze pseudo randomly generated tests with known functional coverage checks, or "bin hits," using machine learning. For the training phase, our algorithm looks for common sequences of assembly instructions within tests that hit a given bin. Once our algorithm is trained, it is passed a new x86 assembly test and outputs the percentage likelihood of that test hitting a given bin. Future work will involve using these results to generate a sequence of assembly instructions that always cause a given bin to be hit. These sequences can then be used to create a suite of x86 assembly tests that efficiently check for functional coverage.

Team Members: 

Ismael Marquez

Mehrad Yousefi

Jacob Knight