Related papers: FatPaths: Routing in Supercomputers and Data Cente…
Next-generation datacenters require highly efficient network load balancing to manage the growing scale of artificial intelligence (AI) training and general datacenter traffic. However, existing Ethernet-based solutions, such as Equal Cost…
We introduce a blackbox framework that simplifies all known parallel algorithms with near-linear work for single-source reachability and shortest paths in directed graphs. Specifically, existing reachability algorithms rely on constructing…
Cloud interactive data-driven applications generate swarms of small TCP flows that compete for the small buffer space in data-center switches. Such applications require a short flow completion time (FCT) to perform their jobs effectively.…
Packet classification is a vital and complicated task as the processing of packets should be done at a specified line speed. In order to classify a packet as belonging to a particular flow or set of flows, network nodes must perform a…
This paper presents an optimal network topology control framework using cutting-plane methods for efficient network partitioning with controllable edges. The objective is to enable real-time reconfiguration of interconnected sub-networks…
A recent advance in networking is the deployment of path-aware multipath network architectures, where network endpoints are given multiple network paths to send their data on. In this work, we tackle the challenge of selecting paths for…
In this letter, we propose a new routing strategy with a single free parameter $\alpha$ only based on local information of network topology. In order to maximize the packets handling capacity of underlying structure that can be measured by…
DPillar has recently been proposed as a server-centric datacenter network and is combinatorially related to (but distinct from) the well-known wrapped butterfly network. We explain the relationship between DPillar and the wrapped butterfly…
Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However, at fixed FLOPs a looped model has strictly less capacity than a baseline transformer. We…
This paper aims to apply two major scaling transformations from the computing packaging industry to internet routers: the heterogeneous integration of high-bandwidth memories (HBMs) and chiplets, as well as in-package optics. We propose a…
Designing an efficient routing strategy is of great importance to alleviate traffic congestion in multilayer networks. In this work, we design an effective routing strategy for multilayer networks by comprehensively considering the roles of…
Emerging chips with hundreds and thousands of cores require networks with unprecedented energy/area efficiency and scalability. To address this, we propose Slim NoC (SN): a new on-chip network design that delivers significant improvements…
Urban rail transit is a fundamental component of public transportation, however, commonly station-based path search algorithms often overlook the impact of transfer times on search results, leading to decreased accuracy. To solve this…
Both IP lookup and packet classification in IP routers can be implemented by some form of tree traversal. SRAM-based Pipelining can improve the throughput dramatically. However, previous pipelining schemes result in unbalanced memory…
To interconnect their growing number of servers, current supercomputers and data centers are starting to adopt low-diameter networks, such as HyperX, Dragonfly and Dragonfly+. These emergent topologies require balancing the load over their…
Inter-datacenter networks connect dozens of geographically dispersed datacenters and carry traffic flows with highly variable sizes and different classes. Adaptive flow routing can improve efficiency and performance by assigning paths to…
As high-performance computing systems scale in size and complexity, efficient resource management is essential to minimize communication overhead. The HyperX is a richly connected, low-diameter network that offers a scalable and…
This paper introduces a new architectural framework, known as input fast-forwarding, that can enhance the performance of deep networks. The main idea is to incorporate a parallel path that sends representations of input values forward to…
High throughput satellites (HTSs) outpace traditional satellites due to their multi-beam transmission. The rise of low Earth orbit mega constellations amplifies HTS data rate demands to terabits/second with acceptable latency. This surge in…
Internet is known to display a highly heterogeneous structure and complex fluctuations in its traffic dynamics. Congestion seems to be an inevitable result of user's behavior coupled to the network dynamics and it effects should be…