Departamento de Informática e Ingeniería de Sistemas - Aragón Institute for Engineering Research (I3A), Universidad de Zaragoza, Zaragoza, Spain.
PLoS One. 2019 Aug 1;14(8):e0220135. doi: 10.1371/journal.pone.0220135. eCollection 2019.
SPEC CPU is one of the most common benchmark suites used in computer architecture research. CPU2017 has recently been released to replace CPU2006. In this paper we present a detailed evaluation of the memory hierarchy performance for both the CPU2006 and single-threaded CPU2017 benchmarks. The experiments were executed on an Intel Xeon Skylake-SP, which is the first Intel processor to implement a mostly non-inclusive last-level cache (LLC). We present a classification of the benchmarks according to their memory pressure and analyze the performance impact of different LLC sizes. We also test all the hardware prefetchers showing they improve performance in most of the benchmarks. After comprehensive experimentation, we can highlight the following conclusions: i) almost half of SPEC CPU benchmarks have very low miss ratios in the second and third level caches, even with small LLC sizes and without hardware prefetching, ii) overall, the SPEC CPU2017 benchmarks demand even less memory hierarchy resources than the SPEC CPU2006 ones, iii) hardware prefetching is very effective in reducing LLC misses for most benchmarks, even with the smallest LLC size, and iv) from the memory hierarchy standpoint the methodologies commonly used to select benchmarks or simulation points do not guarantee representative workloads.
SPEC CPU 是计算机体系结构研究中最常用的基准套件之一。CPU2017 最近发布，以取代 CPU2006。在本文中，我们对 CPU2006 和单线程 CPU2017 基准测试的内存层次性能进行了详细评估。实验在英特尔至强 Skylake-SP 上执行，这是第一款实现大部分非包含性最后一级缓存（LLC）的英特尔处理器。我们根据内存压力对基准测试进行分类，并分析不同 LLC 大小对性能的影响。我们还测试了所有硬件预取器，发现它们在大多数基准测试中都能提高性能。经过全面的实验，我们可以得出以下结论：i）几乎一半的 SPEC CPU 基准测试在二级和三级缓存中的缺失率非常低，即使 LLC 尺寸较小且没有硬件预取，ii）总体而言，SPEC CPU2017 基准测试比 SPEC CPU2006 基准测试对内存层次资源的需求更少，iii）硬件预取对于大多数基准测试非常有效，可以减少 LLC 缺失，即使 LLC 尺寸最小，iv）从内存层次的角度来看，常用的选择基准测试或模拟点的方法并不能保证代表性的工作负载。
