Extracting ARM processor behavior information for analyzing the worst-case execution time of programs in real-time embedded applications - دانشکده فنی و مهندسی
Extracting ARM processor behavior information for analyzing the worst-case execution time of programs in real-time embedded applications
نوع: Type: Thesis
مقطع: Segment: masters
عنوان: Title: Extracting ARM processor behavior information for analyzing the worst-case execution time of programs in real-time embedded applications
ارائه دهنده: Provider: Amirhosein Asgari
اساتید راهنما: Supervisors: Dr Mahdi Sakhaei-nia
اساتید مشاور: Advisory Professors:
اساتید ممتحن یا داور: Examining professors or referees: Dr Yousef Sanati - Dr Vahid Nosrati
زمان و تاریخ ارائه: Time and date of presentation: 2026
مکان ارائه: Place of presentation: اتاق سمینار کامپیوتر
چکیده: Abstract: Worst-case execution time (WCET) analysis is one of the important components in the evaluation of real-time and embedded systems and requires precise knowledge of execution paths and the program’s control-flow structure. The control-flow graph (CFG) is one of the main structures used in this analysis, but in some cases, particularly when the source code is unavailable or when the structure of the source code differs from that of the executable file, it is necessary to reconstruct the CFG from the executable file. CFG reconstruction is challenging due to the presence of control-transfer instructions, especially indirect branches, as well as its dependence on the characteristics of the target architecture. In this paper, a hybrid approach for reconstructing the CFG of executable files on the AArch64 architecture is presented, which combines static machine-code analysis with information obtained from program execution. In this approach, the AFRA tool compiles C source-code files for the AArch64 architecture and, using information extracted from assembly code and program execution traces, identifies basic blocks and control-flow relationships. Finally, the CFG of the program is reconstructed based on static and dynamic information and is used as one of the inputs to subsequent WCET analysis stages. The performance of the proposed method is evaluated by assessing parameters related to the CFG reconstruction process. The results of this evaluation demonstrate the capability of the proposed approach to reconstruct CFGs for AArch64 executable files and provide the control-flow structure required for WCET analysis.