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

TL;DR

ZCCL introduces error-bounded lossy compression to MPI collective communication, significantly reducing message sizes and communication costs while maintaining data accuracy, thus improving large-scale scientific application performance.

Contribution

The paper presents a novel framework and compressor for error-bounded lossy compression in MPI collectives, enhancing efficiency and generalizability over prior fixed-rate methods.

Findings

Achieves 1.9--8.9X performance improvement over baseline MPI collectives.

Reduces communication costs significantly while preserving data accuracy.

Effectively integrates into multiple MPI collective operations.

Abstract

With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communication turns out to be a critical bottleneck in large-scale distributed and parallel processing. The large message size in MPI collectives is particularly concerning because it can significantly degrade overall parallel performance. To address this issue, prior research simply applies off-the-shelf fixed-rate lossy compressors in the MPI collectives, leading to suboptimal performance, limited generalizability, and unbounded errors. In this paper, we propose a novel solution, called ZCCL, which leverages error-bounded lossy compression to significantly reduce the message size, resulting in a substantial reduction in communication costs. The key contributions are three-fold. (1) We develop two general, optimized lossy-compression-based frameworks for both types of MPI collectives (collective data movement as well as collective computation), based on their particular characteristics. Our framework not only reduces communication costs but also preserves data accuracy. (2) We customize fZ-light, an ultra-fast error-bounded lossy compressor, to meet the specific needs of collective communication. (3) We integrate ZCCL into multiple collectives, such as Allgather, Allreduce, Scatter, and Broadcast, and perform a comprehensive evaluation based on real-world scientific application datasets. Experiments show that our solution outperforms the original MPI collectives as well as multiple baselines by 1.9--8.9X.