One Quadrillion Triangles Queried on One Million Processors
One Quadrillion Triangles Queried on One Million Processors
复制标题
在 100 万个处理器上查询 1000 万个三角形
DOI：
10.1109/hpec.2019.8916243
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
G. Sanders
中科院分区：
文献类型：
--
作者：
R. Pearce;Trevor Steil;Benjamin W. Priest;G. Sanders
我们更新了我们之前的2017年图形挑战提交[7]，通过展示万亿边无标度图的缩放和验证，在分布式内存中进行大规模三角形计数。我们结合了最近为不规则通信工作负载开发的分布式通信优化[1]，并在LLNL演示了扩展到150万个IBM BG/Q Sequoia核心。我们使用非随机Kronecker图生成来验证我们的实现，其中地面真实局部和全局三角形计数是已知的，并在Graph 500 [5] R-MAT输入之后对我们的Kronecker图输入进行建模。据我们所知，我们的结果是迄今为止最大的三角形计数实验合成无标度图。
We update our prior 2017 Graph Challenge submission [7] on large scale triangle counting in distributed memory by demonstrating scaling and validation on trillion-edge scale-free graphs. We incorporate recent distributed communication optimizations developed for irregular communication workloads [1], and demonstrate scaling up to 1.5 million cores of IBM BG/Q Sequoia at LLNL. We validate our implementation using nonstochastic Kronecker graph generation where ground-truth local and global triangle counts are known, and model our Kronecker graph inputs after the Graph500 [5] R-MAT inputs. To our knowledge, our results are the largest triangle count experiments on synthetic scale-free graphs to date.