NSFRII Track-4: NSF: Scalable MPI with Adaptive Compression for GPU-based Computing Systems

Project description

RII Track-4: NSF: Scalable MPI with Adaptive Compression for GPU-based Computing Systems

This Research Infrastructure Improvement Track-4 EPSCoR Research Fellows project will provide a fellowship to an Assistant professor and training for a graduate student at the University of Kentucky Research Foundation. This work will be conducted in collaboration with researchers at the Argonne National Laboratory (ANL). Message Passing Interface (MPI) is the de facto standard to perform communication and scale applications on high-performance computing systems. The performance of MPI is crucial to various downstream applications, including scientific simulations, big data analytics, and artificial intelligence. However, as the recent development of GPUs continues to outpace that of commodity networks, large-size data transfer is becoming the major performance bottleneck in state-of-the-art MPI libraries. This work aims to tackle this problem by developing a performant and scalable MPI library through integrated data compression, which is critical to fully exploit the power of current and next-generation computing systems. The success of this project will allow for accelerated executions of scientific code and data analytics, reducing the time to scientific insights for applications running on large-scale GPU-based computing systems. This will help advance scientific discoveries across a wide range of computer and computational disciplines. The deliverables of this project will be made publicly accessible to the community to enhance the research and engineering cyberinfrastructure in broader domains. In addition, this project will contribute to the education and workforce development for advanced cyberinfrastructure through the training of graduate students.

Publications

ICDE'26

Mingze Xia, Yuxiao Li, Pu Jiao, Bei Wang, Xin Liang*, and Hanqi Guo.
Time-varying Vector Field Compression with Preserved Critical Point Trajectories.
Proceedings of the 42nd IEEE International Conference on Data Engineering, Montreal, Canada, May 4 - 8, 2026. (*: Corresponding author) [DOI]

ICDE'26

Xuan Wu, Sheng Di, Tripti Agarwal, Kai Zhao, Xin Liang*, and Franck Cappello.
Enabling Homomorphic Analytical Operations on Compressed Scientific Data with Multi-stage Decompression.
Proceedings of the 42nd IEEE International Conference on Data Engineering, Montreal, Canada, May 4 - 8, 2026. (*: Corresponding author) [DOI]

IPDPS'26

Yuxiao Li, Mingze Xia, Xin Liang, Bei Wang, Robert Underwood, Sheng Di, Hemant Sharma, Dishant Beniwal, Franck Cappello, and Hanqi Guo.
pMSz: A Distributed Parallel Algorithm for Correcting Extrema and Morse-Smale Segmentations in Lossy Compression.
Proceedings of the 40th IEEE International Parallel & Distributed Processing Symposium, New Orleans, LA, May 25 - May 29, 2026. Acceptance Rate: 23.3% (101/434). [DOI]

SC'25

Franck Cappello et. al.
What to Support When You’re Compressing: The State of Practice, Gaps, and Opportunities for Scientific Data Compression.
Proceedings of the 2025 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, St. Louis, MO, USA, Nov 16 - 21, 2025. Acceptance Rate: 22.0% (137/623). [DOI]

IPDPS'25

Jieyang Chen, Qian Gong, Xin Liang, Qing Liu, Lipeng Wan, Yanliang Li, Norbert Podhorszki, and Scott Klasky.
HPDR: High-Performance Portable Scientific Data Reduction Framework.
Proceedings of the 39th IEEE International Parallel & Distributed Processing Symposium, Milan, Italy, June 3 - June 7, 2025. Acceptance Rate: 24.7% (105/425). [DOI]

IPDPS'25

Pu Jiao, Sheng Di, Mingze Xia, Xuan Wu, Jinyang Liu, Xin Liang*, and Franck Cappello.
Improving the Efficiency of Interpolation-Based Scientific Data Compressors with Adaptive Quantization Index Prediction.
Proceedings of the 39th IEEE International Parallel & Distributed Processing Symposium, Milan, Italy, June 3 - June 7, 2025. Acceptance Rate: 24.7% (105/425). (*: Corresponding author) [DOI]

IPDPS'25

Xuan Wu, Sheng Di, Congrong Ren, Pu Jiao, Mingze Xia, Cheng Wang, Hanqi Guo, Xin Liang*, and Franck Cappello.
Enabling Efficient Error-controlled Lossy Compression for Unstructured Scientific Data (Best Paper Award).
Proceedings of the 39th IEEE International Parallel & Distributed Processing Symposium, Milan, Italy, June 3 - June 7, 2025. Acceptance Rate: 24.7% (105/425). (*: Corresponding author) [DOI]

VIS'24

Yuxiao Li, Xin Liang, Bei Wang, Yongfeng Qiu, Lin Yan, and Hanqi Guo.
MSz: An Efficient Parallel Algorithm for Correcting Morse-Smale Segmentations in Error-Bounded Lossy Compressors.
Proceedings of the 2024 IEEE VIS Conference, Melbourne, Australia, Oct 22 - 27, 2024. Acceptance Rate: 22.3% (124/557). [DOI]

SC'24

Jiajun Huang, Sheng Di, Xiaodong Yu, Yujia Zhai, Jinyang Liu, Zizhe Jian, Xin Liang, Kai Zhao, Xiaoyi Lu, Zizhong Chen, and Franck Cappello.
hZCCL: Accelerating Collective Communication with Co-Designed Homomorphic Compression.
Proceedings of the 2024 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, Atlanta, GA, USA, Nov 17 - 22, 2024. Acceptance Rate: 21.1% (99/470). [DOI]

SC'24

Xuan Wu, Qian Gong, Jieyang Chen, Qing Liu, Norbert Podhorszki, Xin Liang*, and Scott Klasky.
Error-controlled Progressive Retrieval of Scientific Data under Derivable Quantities of Interest.
Proceedings of the 2024 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, Atlanta, GA, USA, Nov 17 - 22, 2024. Acceptance Rate: 21.1% (99/470). (*: Corresponding author) [DOI]