Data centers heavily rely on scale-out architectures like fat-tree, BCube and VL2 to
accommodate a large number of commodity servers. Since the traditional electrical network …

All-optical circuit-switching (OCS) technology is the key to design energy-efficient and high-
performance datacenter network (DCN) architectures for the future. However, existing round …

Edge computing has emerged in recent years to reduce latency, conserve bandwidth, and
enhance privacy for applications. As more edge computing applications are being deployed …

The metaverse, envisioned as a vast, distributed virtual world, relies on edge computing for
low-latency data processing. However, ensuring fault tolerance–the system's ability to …

Data centers extensively employ topologies such as CLOS, BCube, and Xpander to manage
their large networks of devices. Data center networks (DCN), which rely on traditional …

Distributed training includes two important operations: gradient transmission and gradient
aggregation, which will consume massive bandwidth and computing resources. To achieve …

Model inference in edge is often regarded as an effective method to alleviate high latency
and enhance data privacy in edge-cloud collaborative computing environment. In this paper …

We propose a novel architecture to explore the mutual benefits of optical rackless data
center (ORDC) and in-network computing for accelerating collective communications. It …