Falcon: A Reliable, Low Latency Hardware Transport

[ paper ] [ doi ]

ACM SIGCOMM 2025

Arjun Singhvi, Nandita Dukkipati, Prashant Chandra, Hassan M. G. Wassel, Naveen Kr. Sharma, Anthony Rebello, Henry Schuh, Praveen Kumar, Behnam Montazeri, Neelesh Bansod, Sarin Thomas, Inho Cho, Hyojeong Lee Seibert, Baijun Wu, Rui Yang, Yuliang Li, Kai Huang, Qianwen Yin, Abhishek Agarwal, Srinivas Vaduvatha, Weihuang Wang, Masoud Moshref, Tao Ji, David Wetherall, and Amin Vahdat.

Abstract

Hardware transports such as RoCE deliver high performance with minimal host CPU, but are best suited to special-purpose deployments that limit their use, e.g., backend networks or Ethernet with Priority Flow Control (PFC). We introduce Falcon, the first hardware transport that supports multiple Upper Layer Protocols (ULPs) and heterogeneous application workloads in general-purpose Ethernet datacenter environments (with losses and without special switch support). Key design elements include: delay-based congestion control with multipath load balancing; a layered design with a simple request-response transaction interface for multi-ULP support; hardware-based retransmissions and error-handling for scalability; and a programmable engine for flexibility. The first Falcon hardware implementation delivers a peak performance of 200 Gbps, 120 Mops/sec, with near-optimal operation completion times that are up to 8× lower than CX-7 RoCE under network congestion, and up to 65% higher goodput under lossy conditions.

Bibtex

@inproceedings{google2025falcon,
  author = {Singhvi, Arjun and Dukkipati, Nandita and Chandra, Prashant and Wassel, Hassan M. G. and Sharma, Naveen Kr. and Rebello, Anthony and Schuh, Henry and Kumar, Praveen and Montazeri, Behnam and Bansod, Neelesh and Thomas, Sarin and Cho, Inho and Seibert, Hyojeong Lee and Wu, Baijun and Yang, Rui and Li, Yuliang and Huang, Kai and Yin, Qianwen and Agarwal, Abhishek and Vaduvatha, Srinivas and Wang, Weihuang and Moshref, Masoud and Ji, Tao and Wetherall, David and Vahdat, Amin},
  title = {Falcon: A Reliable, Low Latency Hardware Transport},
  year = {2025},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3718958.3754353},
  doi = {10.1145/3718958.3754353},
  booktitle = {Proceedings of the ACM SIGCOMM 2025 Conference},
  pages = {248–263},
  numpages = {16},
  location = {S\~{a}o Francisco Convent, Coimbra, Portugal},
  series = {SIGCOMM '25}
  publisher = {Association for Computing Machinery (ACM)},
}

[ paper ] [ doi ]