ITR: An Optimizing Compiler for Languages with Programmable Memory Models

编程语言的内存模型规定了数据访问在程序中出现的顺序和不同程序组件在执行过程中看到的顺序之间的关系。随着POSIX线程、Java和OpenMP等并行编程环境的出现，多线程显式并行程序变得更加频繁。这增加了对易于理解和高效的内存模型的需求，以便能够开发正确的程序并仍然提供良好的性能。不幸的是，内存模型的可用性、它们的影响性能以及执行并行程序优化所需的编译器技术被理解得很差。其结果是，当前的内存模型倾向于通过限制可以用它们编写的程序或难以理解来倾向于性能而不是可用性。这个项目的目标是研究编译技术，通过使用优化和分析算法来优化显式并行程序，这些算法被构造来处理广泛的一致性模型。所研究的技术将在编译器中实现，该编译器将用作程序语言存储模型的原型和研究以及显式并行程序的优化和分析的试验台。

The memory model for a programming language specifiesthe relationship between the order in which data accessesappear in a program and the order seen during execution bythe different program components With the advent of parallelprogramming environments like Posix threads, Java, and OpenMP, multi-threaded explicitly parallel programs have become much morefrequent. This increases the need for memory models thatare easy to understand and efficient so that correct pro-grams can be developed and still give good performance.Unfortunately, the usability of memory models, their impacton performance, and the compiler technology needed to per-form optimizations of parallel programs are poorly under-stood. The result is that current memory models tend tofavor performance over usability by restricting the programsthat can be written with them, or by being difficult tounderstand. The objective of this project is to study com-piler techniques to optimize explicitly parallel programs byusing optimizations and analysis algorithms structured tohandle a broad class of consistency models. The techniquesstudied will be implemented in a compiler that will serveas a testbed for prototyping and studying programminglanguage memory models and for studying the optimizationand analysis of explicitly parallel programs.