Emerging applications -- cloud computing, the internet of things, and augmented/virtual reality -- need responsive, available, secure, ubiquitous, and scalable datacenter networks. Network management currently uses simple, per-packet, data-plane heuristics (e.g., ECMP and sketches) under an intelligent, millisecond-latency control plane that runs data-driven performance and security policies. However, to meet users' quality-of-service expectations in a modern data center, networks must operate intelligently at line rate. In this paper, we present Taurus, an intelligent data plane capable of machine-learning inference at line rate. Taurus adds custom hardware based on a map-reduce abstraction to programmable network devices, such as switches and NICs; this new hardware uses pipelined and SIMD parallelism for fast inference. Our evaluation of a Taurus-enabled switch ASIC -- supporting several real-world benchmarks -- shows that Taurus operates three orders of magnitude faster than a server-based control plane, while increasing area by 24% and latency, on average, by 178 ns. On the long road to self-driving networks, Taurus is the equivalent of adaptive cruise control: deterministic rules steer flows, while machine learning tunes performance and heightens security.

中文翻译：

---

金牛座：智能数据平面

新兴应用程序——云计算、物联网和增强/虚拟现实——需要响应迅速、可用、安全、无处不在和可扩展的数据中心网络。网络管理目前在运行数据驱动的性能和安全策略的智能、毫秒级延迟控制平面下使用简单的、每包数据平面启发式算法（例如 ECMP 和草图）。然而，为了在现代数据中心满足用户对服务质量的期望，网络必须以线速智能运行。在本文中，我们介绍了 Taurus，一种能够以线速进行机器学习推理的智能数据平面。Taurus 将基于 map-reduce 抽象的自定义硬件添加到可编程网络设备，例如交换机和 NIC；这个新硬件使用流水线和 SIMD 并行来进行快速推理。我们对支持 Taurus 的交换机 ASIC 的评估（支持多个真实世界的基准测试）表明，Taurus 的运行速度比基于服务器的控制平面快三个数量级，同时将面积增加 24%，延迟平均增加 178 ns。在通往自动驾驶网络的漫长道路上，Taurus 相当于自适应巡航控制：确定性规则引导流量，而机器学习则调整性能并提高安全性。