# Expanding across time to deliver bandwidth efficiency and low latency

arXiv: https://arxiv.org/abs/1903.12307 · HTML: https://mlsanity.com/paper/1903.12307/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [Rail-only: A Low-Cost High-Performance Network for Training LLMs with Trillion Parameters](https://mlsanity.com/paper/2307.12169/) (2023)
- [MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training](https://mlsanity.com/paper/2501.03905/) (2025)
- [InfiniteHBD: Building Datacenter-Scale High-Bandwidth Domain for LLM with Optical Circuit Switching Transceivers](https://mlsanity.com/paper/2502.03885/) (2025)
- [Efficient Direct-Connect Topologies for Collective Communications](https://mlsanity.com/paper/2202.03356/) (2022)
- [LUMION: Fast Fault Recovery for ML Jobs Using Programmable Optical Fabrics](https://mlsanity.com/paper/2505.23105/) (2025)
- [Morphlux: Transforming Torus Fabrics for Efficient Multi-tenant ML](https://mlsanity.com/paper/2508.03674/) (2025)
- [Assistants, Not Architects: The Role of LLMs in Networked Systems Design](https://mlsanity.com/paper/2604.25506/) (2026)

## Abstract (arXiv)

Datacenters need networks that support both low-latency and high-bandwidth packet delivery to meet the stringent requirements of modern applications. We present Opera, a dynamic network that delivers latency-sensitive traffic quickly by relying on multi-hop forwarding in the same way as expander-graph-based approaches, but provides near-optimal bandwidth for bulk flows through direct forwarding over time-varying source-to-destination circuits. The key to Opera's design is the rapid and deterministic reconfiguration of the network, piece-by-piece, such that at any moment in time the network implements an expander graph, yet, integrated across time, the network provides bandwidth-efficient single-hop paths between all racks. We show that Opera supports low-latency traffic with flow completion times comparable to cost-equivalent static topologies, while delivering up to 4x the bandwidth for all-to-all traffic and supporting 60% higher load for published datacenter workloads.