编译指导下的静态分析与代码转换策略研究-计算机技术专业论文.docxVIP

华 华 中 科 技 大 学 硕 士 学 位 论 文 II II Abstract With the rapid development of CPU production process, the core number of CPU develops from the original single-core, dual-core to the quad-core, eight-core or even more. In order to improve processing speed, multi-core runtime system emerges to effectively organize existing physical core effectively. Multi-core runtime system can effectively organize the multi-core computing resources, allocation and scheduling the computing tasks at run time and provide users with high-performance computing services. Static analysis technology is a key component of the compiler background, analysis and process the program behavior without the execution process, generate the analysis result related to the code. Lacking of effective analysis of the target code, most of existing scheduling policy of the runtime system increases the system overhead, thereby reducing the performance of the system. By taking the result of the analysis system and users compiler-directed information into consideration, this paper presents an analysis based task management strategy, through making full use of the static program analysis and the code transformation, analysis based strategy want to reduce the overhead of task management. Consider the task creation overhead and the computing power of core, most of the cores can maintain a relatively low idle rate within the specified time during task execution. In static program analysis phase, the analysis system does the optimization work according to the degree of parallelism and the execution plan. Through the code safety test to ensure the correctness of the code transformation process. In run time phase, the choice of the task execution plan considering the depth information of the task node and the computational overhead of the compute cores, select the appropriate enforcement response calculation request. The system dynamically manages tasks running status, reduce the overhead and ensure the correctness of th