一句话：提出面向商用 GPU 的嵌入模型训练系统 Frugal，通过主动刷写与优先级调度提升训练吞吐和性价比。
嵌入模型在推荐系统、图学习等稀疏场景中能有效学习大规模 ID 类特征的表示。商用 GPU 性价比高，适合内存密集型的嵌入训练，但其通信带宽低且不支持 PCIe P2P，直接训练性能不佳。Frugal 专为商用 GPU 设计：利用 GPU 通信必须经主机内存中转的特点，主动将其他 GPU 会访问的参数刷写到主机内存，把一半通信开销解耦到非关键路径；同时为刷写操作分配优先级，优先处理将被访问的参数、延迟其他刷写，并用两级优先队列保证可扩展性。实验覆盖推荐模型和图嵌入训练；在商用 GPU 上显著提高吞吐，在数据中心 GPU 上达到现有系统相近吞吐，且性价比提升 4.0–4.3 倍。
Embedding models show superiority in learning representations of massive ID-type features in sparse learning scenarios such as recommendation systems (e.g., user/item IDs) and graph learning (e.g., node/edge IDs). Commodity GPUs are highly favored for their cost-efficient computing power, which is ideally suited for the low computing demand of memory-intensive embedding models. However, directly running embedding model training on commodity GPUs yields poor performance because of their deficient communication resources (including low communication bandwidth and no PCIe P2P support). This paper presents Frugal, an embedding model training system tailored for commodity GPUs. Based on the observation that the communication between commodity GPUs must be bounced on host memory (due to no PCIe P2P support), the key idea of Frugal is proactively flushing, where each GPU proactively flushes its own parameters that other GPUs will access into host memory, thereby decoupling half of the communication overhead to non-critical paths. To alleviate the communication contention of proactively flushing on foreground training processes, Frugal assigns priorities to each flush operation, and prioritizes flushing parameters that GPUs will access while deferring others. Further, Frugal tailors a two-level priority queue to ensure high scalability for operations involving priorities. Frugal has been applied to train embedding models including recommendation models and graph embedding. Experiments indicate that Frugal can significantly increase training throughput on commodity GPUs, and achieve similar throughput compared to existing systems on datacenter GPUs with 4.0-4.3× improvement in cost-effectiveness.
@inproceedings{XieZGGL25,
title = {<scp>Frugal:</scp>
Efficient and Economic Embedding Model Training with Commodity GPUs},
author = {Minhui Xie and Shaoxun Zeng and Hao Guo and Shiwei Gao and Youyou Lu},
booktitle = {ASPLOS},
year = {2025},
doi = {10.1145/3669940.3707245}
}