Applying Automated Memory Analysis to Improve Iterative Algorithms

Historically, iterative solvers have been designed so as to minimize the number of floating-point operations. The authors propose instead that iterative solvers should be designed to minimize the amount of data that must be loaded from the memory hierarchy to the CPU. In this paper, they describe automated memory analysis, a technique to improve the memory efficiency of a sparse linear iterative solver. The automated memory analysis uses a language processor to predict the data movement required for an iterative algorithm based upon a Matlab implementation. They demonstrate how automated memory analysis is used to reduce the execution time of a component of a global parallel ocean model.