Data center networks usually employ the scale-out model to provide high bisection
bandwidth for applications. A large amount of data is required to be transferred frequently …

Complementary to the fancy big data applications, networking for big data is an
indispensable supporting platform for these applications in practice. This emerging research …

Congestion control (CC) is the key to achieving ultra-low latency, high bandwidth and
network stability in high-speed networks. From years of experience operating large-scale …

Large language models (LLMs) power a new generation of interactive AI applications
exemplified by ChatGPT. The interactive nature of these applications demands low latency …

Deep learning (DL) training jobs bring some unique challenges to existing cluster
managers, such as unpredictable training times, an all-or-nothing execution model, and …

Homa is a new transport protocol for datacenter networks. It provides exceptionally low
latency, especially for workloads with a high volume of very short messages, and it also …

Datacenter networks employ multi-rooted topologies (eg, Leaf-Spine, Fat-Tree) to provide
large bisection bandwidth. These topologies use a large degree of multipathing, and need a …

Many networking tasks now employ deep learning (DL) to solve complex prediction and
optimization problems. However, current design philosophy of DL-based algorithms entails …

The recently proposed dataplanes for microsecond scale applications, such as IX and
ZygOS, use non-preemptive policies to schedule requests to cores. For the many real-world …

Data center networks are inclined towards increasing line rates to 200Gbps and beyond to
satisfy the performance requirements of applications such as NVMe and distributed ML. With …