一句话：提出 Wave 框架，将用户态系统软件卸载到 SmartNIC ARM 核，并设计微秒级通信 API。
本文研究将用户态系统软件的决策任务从云服务器 CPU 卸载到 SmartNIC ARM 核，以释放主机资源。提出 Wave 框架，把用户态系统软件作为进程/代理运行在 SmartNIC 上，并设计新的主机-SmartNIC 通信 API，支持微秒级卸载。作者将内核线程调度、内存管理和 RPC 栈等卸载到 SmartNIC，与主机实现相比性能下降 1.1%-7.4%；内存管理节省 16 个主机核，RPC 节省 8 个主机核，虚拟机性能提升 11.2%。这表明系统软件放置方式可提升数据中心效率与可扩展性。
SmartNICs are increasingly deployed in datacenters to offload tasks from server CPUs, improving the efficiency and flexibility of datacenter security, networking and storage. Optimizing cloud server efficiency in this way is critically important to ensure that virtually all server resources are available to paying customers. Userspace system software, specifically, decision-making tasks performed by various operating system subsystems, is particularly well suited for execution on mid-tier SmartNIC ARM cores. To this end, we introduce Wave, a framework for offloading userspace system software to processes/agents running on the SmartNIC. Wave uses Linux userspace systems to better align system functionality with SmartNIC capabilities. It also introduces a new host-SmartNIC communication API that enables offloading of even μs-scale system software. To evaluate Wave, we offloaded preexisting userspace system software including kernel thread scheduling, memory management, and an RPC stack to SmartNIC ARM cores, which showed a performance degradation of 1.1%-7.4% in an apples-to-apples comparison with on-host implementations. Wave recovered host resources consumed by on-host system software for memory management (saving 16 host cores), RPCs (saving 8 host cores), and virtual machines (an 11.2% performance improvement). Wave highlights the potential for rethinking system software placement in modern datacenters, unlocking new opportunities for efficiency and scalability.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{HumphriesNKNTLC25,
title = {Wave: Offloading Resource Management to SmartNIC Cores},
author = {Jack Tigar Humphries and Neel Natu and Kostis Kaffes and Stanko Novaković and Paul Turner and Henry M. Levy and David Culler and Christos Kozyrakis},
booktitle = {ASPLOS},
year = {2025},
doi = {10.1145/3676642.3736113}
}