Optimizing for KNL Usage Modes When Data Doesn’t Fit in MCDRAM
Optimizing for KNL Usage Modes When Data Doesn’t Fit in MCDRAM
复制标题
当数据不适合 MCDRAM 时优化 KNL 使用模式
DOI：
10.1145/3225058.3225116
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Kogge, Peter M.
中科院分区：
文献类型：
--
作者：
Butcher, Neil;Olivier, Stephen L.;Berry, Jonathan;Hammond, Simon D.;Kogge, Peter M.
多通道DRAM(McDram)或高带宽存储器(HBM)等技术提供的带宽比传统存储器大得多。这一趋势引发了一些问题，即应用程序应该如何管理级别之间的数据传输。本文重点对英特尔骑士登陆(KNL)多核处理器中McDram的不同使用模式进行了评估。我们通过一个排序内核和一个基于排序的流媒体基准来评估这些使用模式。我们为基准测试开发了一个性能模型，并使用实验证据证明了该模型的正确性。该模型为内存带宽限制计算预测了接近最佳数量的复制线程。我们在Knl上演示了，与不使用McDram的OpenMP GNU排序相比，当问题不适合McDram时，排序的加速比高达1.9倍。
Technologies such as Multi-Channel DRAM (MCDRAM) or High Bandwidth Memory (HBM) provide significantly more bandwidth than conventional memory. This trend has raised questions about how applications should manage data transfers between levels. This paper focuses on evaluating different usage modes of the MCDRAM in Intel Knights Landing (KNL) manycore processors. We evaluate these usage modes with a sorting kernel and a sorting-based streaming benchmark. We develop a performance model for the benchmark and use experimental evidence to demonstrate the correctness of the model. The model projects near-optimal numbers of copy threads for memory bandwidth bound computations. We demonstrate on KNL up to a 1.9X speedup for sort when the problem does not fit in MCDRAM over an OpenMP GNU sort that does not use MCDRAM.