Conference proceeding
SZOps: Scalar Operations for Error-bounded Lossy Compressor for Scientific Data
SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp.260-269
11/17/2024
DOI: 10.1109/SCW63240.2024.00042
Abstract
Error-bounded lossy compression has been a critical technique to significantly reduce the sheer amounts of simulation datasets for high-performance computing (HPC) scientific applications while effectively controlling the data distortion based on user-specified error bound. In many real-world use cases, users must perform computational operations on the compressed data. However, none of the existing error-bounded lossy compressors support operations, inevitably resulting in undesired decompression costs. In this paper, we propose a novel error-bounded lossy compressor (called SZOps), which supports not only error-bounding features but efficient computations (including negation, scalar addition, scalar multiplication, mean, variance, etc.) on the compressed data without the complete decompression step, which is the first attempt to the best of our knowledge. We develop several optimization strategies to maximize the overall compression ratio and execution performance. We evaluate SZOps compared to other state-of-the-art lossy compressors based on multiple real-world scientific application datasets.
Details
- Title: Subtitle
- SZOps: Scalar Operations for Error-bounded Lossy Compressor for Scientific Data
- Creators
- Tripti Agarwal - University of UtahSheng Di - Argonne National LaboratoryJiajun Huang - University of California, RiversideYafan Huang - University of IowaGanesh Gopalakrishnan - University of UtahRobert Underwood - Argonne National LaboratoryKai Zhao - Florida State UniversityXin Liang - University of KentuckyGuanpeng Li - Argonne National LaboratoryFranck Cappello - Argonne National Laboratory
- Resource Type
- Conference proceeding
- Publication Details
- SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp.260-269
- Publisher
- IEEE
- DOI
- 10.1109/SCW63240.2024.00042
- Grant note
- Office of Science (10.13039/100006132) Advanced Scientific Computing Research (10.13039/100006192) U.S. Department of Energy (10.13039/100000015) National Science Foundation (10.13039/100000001)
- Language
- English
- Date published
- 11/17/2024
- Academic Unit
- Computer Science
- Record Identifier
- 9984774235802771
Metrics
1 Record Views