Publications

FSZ: Breaking the Prediction-Throughput Trade-off in GPU Lossy Compression

Jiajun Huang

in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2026 (Best Paper Nomination)

This work advances GPU lossy compression by pairing high prediction capability with extreme throughput.

hZCCL2: Co-Designing Collective Communication with Vectorized Homomorphic Compression

Jiefeng Zhou, Sheng Di, Yanfei Guo, Yuhao Guo, Linqi Zhang, Kai Zhao, Rajeev Thakur, Franck Cappello, and Jiajun Huang

in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2026

This paper co-designs vectorized homomorphic compression with collective communication.

ghZCCL: Advancing GPU-aware Collective Communications with Homomorphic Compression

Jiajun Huang, Sheng Di, Yafan Huang, Zizhong Chen, Franck Cappello, Yanfei Guo, and Rajeev Thakur

in Proceedings of the 39th ACM International Conference on Supercomputing, 2025

This paper is the first co-design of GPU-centric homomorphic compression with collective communications.

hZCCL: Accelerating Collective Communication with Co-designed Homomorphic Compression

Jiajun Huang, Sheng Di, Xiaodong Yu, Yujia Zhai, Jinyang Liu, Zizhe Jian, Xin Liang, Kai Zhao, Xiaoyi Lu, Zizhong Chen, Franck Cappello, Yanfei Guo, and Rajeev Thakur

in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2024

This paper is the first co-design of homomorphic compression and communications.

ZCCL: Significantly Improving Collective Communication With Error-Bounded Lossy Compression

Jiajun Huang, Sheng Di, Xiaodong Yu, Yujia Zhai, Zhaorui Zhang, Jinyang Liu, Xiaoyi Lu, Ken Raffenetti, Hui Zhou, Kai Zhao, Khalid Alharthi, Zizhong Chen, Franck Cappello, Yanfei Guo, and Rajeev Thakur

arXiv, 2024

This paper is the journal extension of the IPDPS 2024 paper.

gZCCL: Compression-Accelerated Collective Communication Framework for GPU Clusters

Jiajun Huang, Sheng Di, Xiaodong Yu, Yujia Zhai, Jinyang Liu, Yafan Huang, Ken Raffenetti, Hui Zhou, Kai Zhao, Xiaoyi Lu, Zizhong Chen, Franck Cappello, Yanfei Guo, and Rajeev Thakur

in Proceedings of the 38th ACM International Conference on Supercomputing, 2024

This paper details the first GPU-aware compression-accelerated collective communications library.

An Optimized Error-controlled MPI Collective Framework Integrated with Lossy Compression

Jiajun Huang, Sheng Di, Xiaodong Yu, Yujia Zhai, Zhaorui Zhang, Jinyang Liu, Xiaoyi Lu, Ken Raffenetti, Hui Zhou, Kai Zhao, Zizhong Chen, Franck Cappello, Yanfei Guo, and Rajeev Thakur

38th IEEE International Parallel and Distributed Processing Symposium, 2024

This conference paper is the starting point of the ZCCL family.