stOMP: A Specializing Threads Library for OpenMP Runtime Compilation and Optimizations for OpenMP
stOMP: A Specializing Threads Library for OpenMP Runtime Compilation and Optimizations for OpenMP(2009)
摘要
While runtime compilation has in practice been largely restricted to programming languages that execute on virtual machines, such as Java and C#, parallel OpenMP programs show many promising traits for efficient and effective runtime optimization. This work introduces stOMP: a specializing thread-library for OpenMP. Using a combined compile-time and run-time system, stOMP specializes OpenMP parallel regions for frequently-seen values and the configuration of the runtime system. We present a detailed description of the system, focusing on the optimizations implemented and techniques to minimize the runtime overhead: a context-based hot-spot detector; a pruning mechanism that eliminates poorly behaved variables as specialization targets; several runtime optimization policies; and several code optimizations and transformations that further allow performance improvement. We evaluate our work on the SPEC OMP benchmark suite, showing a performance increase of up to 7.8%.
更多查看译文
关键词
performance improvement,runtime compilation,effective runtime optimization,Specializing Threads Library,parallel OpenMP program,OpenMP parallel region,runtime system,runtime overhead,OpenMP Runtime Compilation,code optimizations,run-time system,runtime optimization policy
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要