Barriers reconsidered, friendlier still!

Barriers reconsidered, friendlier still!
复制标题

重新考虑障碍,更加友好!

DOI:
10.1145/2258996.2259004
复制
发表时间:
2012
期刊:
Proceedings of the 19th annual ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications
影响因子:
--
通讯作者:
Antony Hosking
Antony Hosking
中科院分区:
--
文献类型:
--
作者:
Xi Yang;S. Blackburn;Daniel Frampton;Antony Hosking

文献摘要

参考文献

被引文献

相似文献

读写障碍可以调解对堆的访问,从而使收集器能够控制和监视突变器的作用。因此,障碍是设计任何堆管理算法的强大工具,但是普遍的智慧是它们施加了巨大的成本。但是,硬件和工作负载的变化使这些成本成为移动的目标。在这里,我们在一系列现代硬件和工作负载上衡量一系列有用障碍的成本。我们确认一些旧结果并推翻其他结果。我们评估了屏障性能的微体系敏感性以及基准套件之间的差异。我们还考虑了上下文中的障碍,重点介绍其在组合组合时的行为,并研究已知的病理并评估解决方案。我们的结果表明,读写障碍的平均开销分别低至5.4%和0.9%。我们发现,与旧SpecJVM98基准相比,现代DACAPO基准测试提供的工作量更容易受到障碍。此外,在排序机和订购机外及其各自的内存子系统之间的障碍行为存在差异,这表明不同平台的障碍选择不同。这些不断变化的成本意味着算法设计人员需要重新考虑其设计选择以及其由此产生的算法的性质,以利用现代硬件带来的机会。
Read and write barriers mediate access to the heap allowing the collector to control and monitor mutator actions. For this reason, barriers are a powerful tool in the design of any heap management algorithm, but the prevailing wisdom is that they impose significant costs. However, changes in hardware and workloads make these costs a moving target. Here, we measure the cost of a range of useful barriers on a range of modern hardware and workloads. We confirm some old results and overturn others. We evaluate the microarchitectural sensitivity of barrier performance and the differences among benchmark suites. We also consider barriers in context, focusing on their behavior when used in combination, and investigate a known pathology and evaluate solutions. Our results show that read and write barriers have average overheads as low as 5.4% and 0.9% respectively. We find that barrier overheads are more exposed on the workload provided by the modern DaCapo benchmarks than on old SPECjvm98 benchmarks. Moreover, there are differences in barrier behavior between in-order and out-of- order machines, and their respective memory subsystems, which indicate different barrier choices for different platforms. These changing costs mean that algorithm designers need to reconsider their design choices and the nature of their resulting algorithms in order to exploit the opportunities presented by modern hardware.
DOI: 10.1145/1806651.1806666
发表时间: 2010-06
期刊: --
影响因子: --
作者:
L. Hellyer;Richard E. Jones;Antony Hosking
通讯作者: L. Hellyer;Richard E. Jones;Antony Hosking