Presidential Young Investigator: Code Generation for Uniprocessors

这项研究的长期重点是提高并行程序的性能。一种方法是使用编译器技术来获得更好的多处理器缓存性能，即减少与共享相关的总线流量。这项工作的初始阶段是检测错误共享并测量其对缓存缺失率和总线利用率的影响。另一个研究领域是测量非科学并行程序中程序级并行性的数量和类型，并确定最适合执行这些程序的硬件并行性级别。目前的研究重点在以下几个方面：1。共享数据的编译器重组；2. 运行时代码生成；和3。单个地址空间体系结构的保护模型。

Eggers The long range focus of this research is on improving the performance of parallel programs. One thrust uses compiler technology to obtain better multiprocessor cache performance, i.e., reduce the amount of sharing-related bus traffic. The initial phase of that work is the detection of false sharing and measuring its impact on cache miss ratios and bus utilization. Another area of investigation is measuring the amount and type of program level parallelism in nonscientific parallel programs and determining the levels of hardware parallelism that best execute them. The current focus of the research is in the following areas: 1. Compiler reorganization of shared data; 2. Runtime code generation; and 3. A protection model for a single address space architecture.