cuSZ-i: High-Ratio Scientific Lossy Compression on GPUs with Optimized Multi-Level Interpolation

Jinyang Liu; Jiannan Tian; Shixun Wu; Sheng Di; Boyuan Zhang; Robert Underwood; Yafan Huang; Jiajun Huang; Kai Zhao; Guanpeng Li; Dingwen Tao; Zizhong Chen; Franck Cappello

doi:10.1109/SC41406.2024.00019

Conference proceeding

cuSZ-i: High-Ratio Scientific Lossy Compression on GPUs with Optimized Multi-Level Interpolation

Jinyang Liu, Jiannan Tian, Shixun Wu, Sheng Di, Boyuan Zhang, Robert Underwood, Yafan Huang, Jiajun Huang, Kai Zhao, Guanpeng Li, …

Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, pp.1-15

ACM Conferences

SC '24: The International Conference for High Performance Computing, Networking, Storage, and Analysis

11/17/2024

DOI: 10.1109/SC41406.2024.00019

View Online

Abstract

Error-bounded lossy compression is a critical technique for significantly reducing scientific data volumes. Compared to CPU-based compressors, GPU-based compressors exhibit substantially higher throughputs, fitting better for today's HPC applications. However, the critical limitations of existing GPU-based compressors are their low compression ratios and qualities, severely restricting their applicability. To overcome these, we introduce a new GPU-based error-bounded scientific lossy compressor named cuSZ-i, with the following contributions: (1) A novel GPU-optimized interpolation-based prediction method significantly improves the compression ratio and decompression data quality. (2) The Huffman encoding module in cuSZ-i is optimized for better efficiency. (3) cuSZ-i is the first to integrate the NVIDIA Bitcomplossless as an additional compression-ratio-enhancing module. Evaluations show that cuSZ-i significantly outperforms other latest GPU-based lossy compressors in compression ratio under the same error bound (hence, the desired quality), showcasing a 476% advantage over the second-best. This leads to cuSZ-i's optimized performance in several real-world use cases.

Computer systems organization

Computer systems organization -- Architectures

Computer systems organization -- Architectures -- Parallel architectures

Computer systems organization -- Architectures -- Parallel architectures -- Single instruction, multiple data

Computing methodologies

Computing methodologies -- Computer graphics

Computing methodologies -- Computer graphics -- Graphics systems and interfaces

Computing methodologies -- Computer graphics -- Graphics systems and interfaces -- Graphics processors

Computing methodologies -- Computer graphics -- Image compression

Computing methodologies -- Parallel computing methodologies

Computing methodologies -- Parallel computing methodologies -- Parallel algorithms

Computing methodologies -- Parallel computing methodologies -- Parallel algorithms -- Massively parallel algorithms

Information systems

Information systems -- Data management systems

Information systems -- Data management systems -- Data structures

Information systems -- Data management systems -- Data structures -- Data layout

Information systems -- Data management systems -- Data structures -- Data layout -- Data compression

Theory of computation

Theory of computation -- Design and analysis of algorithms

Theory of computation -- Design and analysis of algorithms -- Data structures design and analysis

Theory of computation -- Design and analysis of algorithms -- Data structures design and analysis -- Data compression

Details

Title: Subtitle: cuSZ-i: High-Ratio Scientific Lossy Compression on GPUs with Optimized Multi-Level Interpolation
Creators: Jinyang Liu - University of Houston
Jiannan Tian - Indiana University Bloomington
Shixun Wu - University of California, Riverside
Sheng Di - Argonne National Laboratory
Boyuan Zhang - Indiana University Bloomington
Robert Underwood - Argonne National Laboratory
Yafan Huang - University of Iowa, Iowa City, IA, USA
Jiajun Huang - University of California, Riverside
Kai Zhao - Florida State University
Guanpeng Li - University of Iowa, Iowa City, IA, USA
Dingwen Tao - Indiana University Bloomington
Zizhong Chen - University of California, Riverside
Franck Cappello - Argonne National Laboratory
Resource Type: Conference proceeding
Publication Details: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, pp.1-15
Conference: SC '24: The International Conference for High Performance Computing, Networking, Storage, and Analysis
Series: ACM Conferences
DOI: 10.1109/SC41406.2024.00019
Publisher: IEEE Press
Grant note: U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research (ASCR): DE-AC02-06CH11357 National Science Foundation: 2003709, 2303064, 2104023, 2247080, 2247060, 2312673, 2311875, 2311876
This research was supported by the U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research (ASCR), under contracts DE-AC02-06CH11357. This work was also supported by the National Science Foundation (Grant Nos. 2003709, 2303064, 2104023, 2247080, 2247060, 2312673, 2311875, and 2311876). We also acknowledge the computing resources provided by Argonne Leadership Computing Facility (ALCF) and Advanced Cyberinfrastructure Coordination Ecosystem-Purdue Anvil through Services & Support (ACCESS).
Language: English
Date published: 11/17/2024
Academic Unit: Computer Science
Record Identifier: 9984748155702771

Metrics

22 Record Views

12 Times Cited - Web of Science