Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction With Massive Parallelization" by SCC Team From ETH Zurich

Abstract

This report analyzes the reproducibility of the paper "MemXCT: Memory-Centric X-ray CT Reconstruction with Massive Parallelization" by Hidayetoglu et al. in the cloud as part of the SC20 Virtual Student Cluster Competition (VSCC). To reproduce the results from the original work, the ETH Zurich SC20 VSCC team performed a series of CT reconstructions and performed a scaling study using three provided sinograms. All experimental runs were performed during the SC20 VSCC on an HPC cluster hosted in the Microsoft Azure CycleCloud. In this paper, we describe discrepancies in results as a factor of the differences in experiment environments and insufficient parameter tuning. We successfully reproduce the single device performance and partially reproduce the strong scaling behavior. Digital artifacts from these experiments are available at: 10.5281/zenodo.5598108.