This paper investigates the performance of graph-structured analytics on large-scale shared memory systems. Graph analytics are highly demanding for efficient graph traversal due to large data set size and irregular data access patterns. In order to achieve efficient graph analytics, we consider and discuss the performance of three common types of graph data structures. Also, we demonstrate that load balance is to a large extent determined by the number of edges and number of unique vertices processed by each thread. Finally, we propose an automatic graph data structure selection algorithm and an efficient reordering as a pre-processing step to balance the number of vertices and edges together. Reordering algorithm also optimally balances edges and vertices for graphs with a power-law degree distribution and ensures an equal degree distribution across threads. The developed techniques are implemented in GraphGrind, a new shared memory graph analytics framework. Evaluation in GraphGrind, shows that this outperforms state-of-the-art graph analytics frameworks for shared memory including Ligra (Shun and Blelloch, 2013) up to 10.4$\times$, and Polymer (Zhang et al., 2015) up to 8.3$\times$ across 8 algorithms and 6 graphs.

本文研究了图结构分析在大规模共享存储系统上的性能。由于数据集规模大和数据访问模式不规则，因此图形分析对有效遍历图形的要求很高。为了实现有效的图形分析，我们考虑并讨论了三种常见类型的图形数据结构的性能。同样，我们证明了负载平衡在很大程度上取决于每个线程处理的边数和唯一顶点的数量。最后，我们提出了一种自动图形数据结构选择算法和一种有效的重新排序作为预处理步骤，以平衡顶点和边的数量。重新排序算法还可以最佳地平衡具有幂律度分布的图形的边缘和顶点，并确保线程之间的度分布相等。所开发的技术在新共享内存图分析框架GraphGrind中实现。GraphGrind中的评估表明，该性能优于包括Ligra（Shun和Blelloch，2013年）在内的共享内存的最新图形分析框架（最高可达10.4）$\times$，以及Polymer（Zhang等人，2015）达到8.3$\times$ 涵盖8种算法和6种图表。