A Gaussian Set Sampling Model for Efficient Shared Cache Profiling on Multi-Cores
A Gaussian Set Sampling Model for Efficient Shared Cache Profiling on Multi-Cores
复制标题
用于多核上高效共享缓存分析的高斯集采样模型
DOI：
10.1109/access.2019.2936439
复制
发表时间：
2019
期刊：
影响因子：
3.9
通讯作者：
Guan Nan
中科院分区：
文献类型：
--
作者：
Zhang Yi;Ling Zhanwei;Lv Mingsong;Guan Nan
在现代多核处理器中，末级缓存（LLC）对系统性能有着重要的影响。但是，随着缓存大小达到几兆字节甚至更多，在LLC上探索性能的开销也会大大增加。为了提高性能分析的效率，提出了一种基于集合采样的多核LLC性能分析模型。我们首先探索LLC上的内存访问分布开发一个低开销的压力应用程序为基础的方法。结果表明，存储器访问分布可以近似为高斯分布函数。基于此，提出了一种基于高斯分布的集合抽样模型，该模型可以在有限的代表性样本下预测程序性能。我们评估我们的模型在当代多核机器上，并表明：1）所提出的方法可以精确地预测程序的性能在LLC在不同的竞争强度和2）我们的方法可以达到类似的精度与更少的样本相比，广泛采用的集合采样方法，如随机采样和连续地址采样。
The last level cache (LLC) has significant impact to system performance on modern multi-core processors. But as cache sizes reach several megabytes and more, the overhead of exploring performance on LLC greatly increases as well. To improve the efficiency of performance analysis, we propose a set-sampling-based cache profiling model for the performance analysis on multi-core LLC. We first explore the memory access distributions on LLC by developing a low-overhead stress-application-based method. The results show that memory access distributions can be approximated by Gaussian distribution function. Based on this observation, a Gaussian-distribution-based set sampling model is proposed which can predict program performance with limited representative samples. We evaluate our model on a contemporary multi-core machine and show that 1) the proposed method can precisely predict program performance on LLC under different contention intensities and 2) our method can achieve similar precision with less samples compared to widely adopted set sampling methods such as the random sampling and the continuous address sampling.