Minimizing code size via page selection optimization on partitioned memory architectures

For 8-bit microcontrollers, bank-switching is commonly used to increase memory capacity. The disadvantage of this technique is that bank (page) selection instructions are introduced when switching active data (program) bank. The page selection problem is to minimize the number of page selection instructions inserted. While previous efforts work on optimizing bank selection instructions for the data segment, our work focuses on minimizing page selection instructions for the program segment. Minimizing page selection instructions is a more challenging problem as the size of each procedure being allocated is affected by the number of inserted page selection instructions. In this paper, we first give a formal definition of the page selection problem, and then we formulate the problem as an Integer Linear Programming (ILP) to find the optimal solution. We introduce a tabu search heuristic algorithm, TMSEARCH, to solve the problem efficiently. The experimental results show that ILP can find optimal solutions for small-scale problems, and TMSEARCH is able to find good solutions for all benchmarks within reasonable time. Com-pared to a commercial compiler, TMSEARCH reduces total code size between 0.04% and 19.3%, and reduces page selection instructions between 24.3% and 78.7%.