Dr. Kai Zhao has a paper accepted at The 2025 ACM SIGMOD International Conference on Management of Data. SIGMOD is a flagship conference in data management. The paper, titled “LCP: Enhancing Scientific Data Management with Lossy Compression for Particles,” is authored by Dr. Kai Zhao, his PhD student Longtao Zhang, Ruoyu Li, and collaborators from several universities and national laboratories in the US.
This paper proposes LCP, an innovative lossy compressor designed for particle datasets, offering superior compression quality and higher throughput compared to existing compression solutions. Many scientific applications opt for particles instead of mesh as their basic primitives to model complex systems composed of billions of discrete entities. The scale of the particles in those scientific applications increases substantially thanks to the ever-increasing computational power in high-performance computing platforms. However, the actual gains from such increases are often undercut by obstacles in data management systems related to data storage, transfer, and processing. LCP aims to reduce the size of particle datasets with error-bounded compression design in both the spatial and temporal domains. The evaluation alongside six state-of-the-art alternatives on nine real-world particle datasets from seven distinct domains demonstrate that LCP achieves up to 112% improvement in compression ratios and up to 592% increase in speed compared to the second-best option, under the same error criteria.
The paper will be presented at 2025 ACM SIGMOD International Conference on Management of Data in Berlin, Germany on June 22-27, 2025.