SOFTWARE PERFORMANCE INDICATORS DETERMINATION FOR COMPUTING SYSTEMS WITH HIERARCHICAL MEMORY STRUCTURE
Vitaly A. Egunov · Vestnik komp iuternykh i informatsionnykh tekhnologii · 2025
Model-Driven Engineering is one of the software development methodologies. Modeling at the software design stage is mainly used to reduce the development complexity by increasing the abstraction level. Similar approaches are often used to improve the efficiency of the designed software. Efficiency in this case is understood as minimizing the costs associated with software at various life cycle stages, including the costs of software development, modification, and operation. The software efficiency is closely related to the concept of computing resource efficiency, which is determined by the degree of computing resources utilization involved in the computing process. The paper considers an approach based on "white box" modeling, which makes it possible to evaluate the designed software effectiveness based on a mathematical model of a computing system with a hierarchical memory structure. The study is based on the author's previous research, which suggests an iterative method for improving the data caching strategy. This method is based on a set of quality metrics used to evaluate the software effectiveness. Within the framework of this method, an analytical approach has been developed to evaluate the software effectiveness in terms of using a memory subsystem with a hierarchical structure. This approach is implemented using static analysis of the program source code. The process of determining the C-program source code characteristics is described in detail. The conclusions obtained as a result of static analysis are compared with the computational experiments results. The computational experiments results confirm the effectiveness and reliability of the proposed method.