Automatic NUMA Characterization using Cbench∗

Clusters of seemingly homogeneous compute nodes are increas-ingly heterogeneous within each node due to replication and dis-tribution of node-level subsystems. This intra-node heterogene-ity can adversely affect program execution performance by inflict-ing additional data-access costs when accessing non-local data. In this work-in-progress paper, we present extensions to the Cbench Scalable Testing Framework for analyzing main memory and PCIe data-access performance in modern NUMA architectures. The in-formation provided by this tool will be of use for task scheduling, performance modeling, and evaluation of NUMA systems