CHOCOLATE: Congestion Handling on Controllable Oblivious Lightweight Algorithm Through Explicit-Notification

Authors

  • Haotian Wu Shanghai AI Power Technology Co., Ltd, Shanghai, China
  • Jiasheng Wang School of Computer Science and Technology, Tongji University, Shanghai, China
  • Yuehao Xu School of Computer Science and Technology, Tongji University, Shanghai, China
  • Song He School of Computer Science and Technology, Tongji University, Shanghai, China
  • Jian Yu School of Computer Science and Technology, Tongji University, Shanghai, China
  • Zhijun Ding School of Computer Science and Technology, Tongji University, Shanghai, China

Keywords:

RDMA, RoCE, congestion control, data center network, switch

Abstract

RoCE is widely deployed in data centers for AI training, but network congestion causes GPU underutilization and slows training. Existing congestion control algorithms suffer from slow feedback loops and isolated handling of slowdown and recovery, leading to oscillations and poor bandwidth utilization. We propose CHOCOLATE, which integrates reverse explicit notification (REN) with lightweight flow prediction for congestion sensing, and unifies slowdown and recovery into a coordinated control system. Experimental results demonstrate improved RoCE performance in lossy networks.

Downloads

Download data is not yet available.

Published

2026-08-31

How to Cite

Wu, H., Wang, J., Xu, Y., He, S., Yu, J., & Ding, Z. (2026). CHOCOLATE: Congestion Handling on Controllable Oblivious Lightweight Algorithm Through Explicit-Notification. Computing and Informatics, 45(4). Retrieved from http://147.213.75.17/ojs/index.php/cai/article/view/9380

Issue

Vol. 45 No. 4 (2026): Computing and Informatics

Section

Articles

Most read articles by the same author(s)

1 2 > >>