Continuous performance optimization on odern Architectures

如今，多核可伸缩性给所有平台的开发人员带来了越来越大的挑战 移动到数据中心。主要处理器供应商之间的激烈竞争包括 英特尔、AMD、IBM和ARM正在引领计算机体系结构的新创新 软件和应用程序开发商才刚刚开始利用这一优势。有一个增加的 在这些平台上开发软件的复杂性，在这些平台上开发人员现在面临的风险更大 对处理器体系结构的性能特性产生了前所未有的影响。影响性能， 性能隔离，甚至应用程序的安全性。 这项研究的目标是提供工具和见解，帮助开发人员充分利用 硬件的使用。我们主要做了三个方面的工作：第一，设计并实现了一个连续的剖析器 帮助开发人员理解一、二、三阶性能指标的系统 在现代处理器中可用。第二，构建可移植的运行时，帮助开发人员优化 使用允许应用程序控制缓存行为的新指令，可以说是 对开发者来说收益最大的最复杂的问题。第三，探索该运行时的用法 以及几个新的处理器功能，用于对应用程序进行分区以确保性能、正确性和 保安。

Today, multicore scalability poses increasing challenges to developers across all platforms from mobile to the data center. The intensive competition between the major processor vendors including Intel, AMD, IBM, and ARM is leading new innovation in computer architecture that systems software and application developers have only begun to take advantage of. There is an increased complexity of developing software on these platforms where developers are now exposed more than ever to the performance idiosyncrasies of the processor architecture. Impacting performance, performance isolation, and even security of their applications. The goal of this research is to provide the tools and insights to help developers make the best use of the hardware. We focus on three pieces: First, design and implement a continuous profiling system that will help developers make sense of the first, second and third order performance metrics available in modern processors. Second, build a portable runtime to help developers make optimal use of the new instructions that allow applications to control cache behavior, arguably one of the most complex issues with the largest gain for developers. Third, explore the use of this runtime and several new processor features for partitioning applications for performance, correctness, and security.