SIP: Boosting Up Graph Computing by Separating the Irregular Property Data
SIP: Boosting Up Graph Computing by Separating the Irregular Property Data
复制标题
DOI：
10.1145/3386263.3406905
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Jiacheng Ni;Xiaochen Guo;Yuanqing Cheng
中科院分区：
文献类型：
--
作者：
Jiacheng Ni;Xiaochen Guo;Yuanqing Cheng
图分析是一类重要的应用程序，也是大数据工作负载的基石之一。不幸的是，由于大多数图形应用程序中的数据局部性较差，传统的通用计算机架构无法发挥其最佳处理能力。局部性差的主要原因是访问顶点属性。上层缓存由于其有限的容量和顶点属性的长重用距离而不能保持足够长的数据块。此外，对属性的访问可能会驱逐其他具有良好局部性的有用数据，这会导致更多的冲突未命中。在这项工作中，专门为属性添加了一个小缓存来解决这个问题。在此基础上，我们进一步利用预取器对该结构进行了改进，以提高属性的命中率，提高系统性能。实验结果表明，与两种最先进的预取器和加速器相比，本文提出的架构实现了1.13倍-2.54倍和1.04倍-1.27倍的性能提升。与此同时，可分别节约能耗6.41%~ 13.43%和34.67%~ 43.92%。
Graph analytics is an important class of applications and is one of the cornerstone of big-data workloads. Unfortunately, due to poor data locality in most graph applications, conventional general-purpose computer architectures are unable to perform the best of their processing abilities. The main source of poor locality comes from accessing vertex properties. Upper-level caches cannot hold data blocks long enough due to their limited capacity and the long reuse distance of vertex properties. Moreover, accesses to properties can evict other useful data with good locality, which causes more conflicting misses. In this work, a small cache is added exclusively for the properties to solve this problem. We further enhance this structure with prefetchers to increase the hit rate of properties and improve performance of system. Experimental results show that compared to two state-of-the-art prefetcher and accelerator for graph computing, our proposed architecture achieves 1.13x-2.54x and 1.04x-1.27x performance improvements. In the meanwhile, the energy consumptions can be saved by 6.41%-13.43% and 34.67%-43.92% respectively.