arXiv subjects

Peiqing Chen

Publications and source records attributed to Peiqing Chen.

3 recordsLinked to original sources

arXiv2026

Don't Let a Few Network Failures Slow the Entire AllReduce

Network failures are among the most frequent hardware faults in large-scale GPU clusters and a leading cause of training-job interruptions. Modern collective communication libraries such as NCCL mitigate network failures by rerouting traffic through surviving NICs on the same server, trading reduced inter-node bandwidth for uninterrupted training. However, the degraded server remains on the critical path of the standard ring algorithm, slowing the entire collective. We present the first information-theoretic lower bound on AllReduce completion time under asymmetric network bandwidth and show that when the straggler retains at least half of its original bandwidth, the unavoidable overhead relative to the fault-free optimum is only O(1/p) for p GPUs. We then design OptCC, a four-stage pipelined AllReduce algorithm that approaches this lower bound. Experiments on SimAI confirm that OptCC closes the gap left by existing fault-tolerant schemes: under practical network failures with up to 50% bandwidth loss, OptCC completes AllReduce within 2-6% of NCCL's fault-free ring performance, whereas the state-of-the-art incurs up to 57% overhead.

cs.DC↗

arXiv2025

Sketch Disaggregation Across Time and Space

Streaming analytics are essential in a large range of applications, including databases, networking, and machine learning. To optimize performance, practitioners are increasingly offloading such analytics to network nodes such as switches. However, resources such as fast SRAM memory available at switches are limited, not uniform, and may serve other functionalities as well (e.g., firewall). Moreover, resource availability can also change over time due to the dynamic demands of in-network applications. In this paper, we propose a new approach to disaggregating data structures over time and space, leveraging any residual resource available at network nodes. We focus on sketches, which are fundamental for summarizing data for streaming analytics while providing beneficial space-accuracy tradeoffs. Our idea is to break sketches into multiple `fragments' that are placed at different network nodes. The fragments cover different time periods and are of varying sizes, and are combined to form a network-wide view of the underlying traffic. We apply our solution to three popular sketches (namely, Count Sketch, Count-Min Sketch, and UnivMon) and demonstrate we can achieve approximately a 75% memory size reduction for the same error for many queries, or a near order-of-magnitude error reduction if memory is kept unchanged.

cs.NI↗

arXiv2024

SimiSketch: Efficiently Estimating Similarity of streaming Multisets

The challenge of estimating similarity between sets has been a significant concern in data science, finding diverse applications across various domains. However, previous approaches, such as MinHash, have predominantly centered around hashing techniques, which are well-suited for sets but less naturally adaptable to multisets, a common occurrence in scenarios like network streams and text data. Moreover, with the increasing prevalence of data arriving in streaming patterns, many existing methods struggle to handle cases where set items are presented in a continuous stream. Consequently, our focus in this paper is on the challenging scenario of multisets with item streams. To address this, we propose SimiSketch, a sketching algorithm designed to tackle this specific problem. The paper begins by presenting two simpler versions that employ intuitive sketches for similarity estimation. Subsequently, we formally introduce SimiSketch and leverage SALSA to enhance accuracy. To validate our algorithms, we conduct extensive testing on synthetic datasets, real-world network traffic, and text articles. Our experiment shows that compared with the state-of-the-art, SimiSketch can improve the accuracy by up to 42 times, and increase the throughput by up to 360 times. The complete source code is open-sourced and available on GitHub for reference.

cs.DS↗