Multi-Criteria Function Inlining for Hard Real-Time Systems
Multi-Criteria Function Inlining for Hard Real-Time Systems
复制标题
DOI：
10.1145/3394810.3394819
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Kateryna Muts;H. Falk
中科院分区：
文献类型：
--
作者：
Kateryna Muts;H. Falk
现代硬实时系统需要满足一些特殊的要求。除了时序限制，额外的设计标准，如代码大小和能量消耗也是不可忽略的。同时优化一个系统以达到上述规范是不可能的，因为其中一个规范的改进可能导致其他规范的退化。已经提出了许多基于编译器的优化技术来优化嵌入式应用程序，只考虑一个需求。尽管如此，一些数学家认为其他的要求作为约束，但没有多少作品试图解决一个多目标的问题，在这种情况下。我们的目标是扩展一个著名的基于编译器的优化，函数内联，多目标问题。我们表明，在这种设置的情况下，所考虑的优化导致一组时间约束，代码大小和能耗之间的权衡。根据需求，系统设计人员可以利用输出集来做出关于系统配置的最终决定，而无需构建昂贵的硬件。
Modern hard real-time systems shall satisfy some special requirements. Besides timing constraints, the additional design criteria such as code size and energy consumption are also not negligible. To optimize a system towards the mentioned specifications simultaneously is impossible, since the improvement in one of them may lead to the degradation of others. Many compiler-based optimizations techniques have been proposed to optimize an embedded application taking into account only one requirement. Nevertheless, some heuristics consider other requirements as constraints, but not many works have tried to solve a multi-objective problem in this context. We aim to extend a well-known compiler-based optimization, function inlining, to a multi-objective problem. We show that in case of such setup, the considered optimization leads to a set of trade-offs between timing constraints, code size, and energy consumption. Depending on the requirements, a system designer can utilize the output set to make a final decision about the system configuration without building an expensive hardware.