Connect with us

Networking

A Brief History of Ethernet, From an Office Experiment to AI Superclusters

Ethernet started as a way to connect computers in one research lab. Fifty years later, it links data centers and AI clusters. Here is how it got there.

Published

on

A yellow ethernet cable on a blue background

Few technologies have had a run like Ethernet. It began as a way to connect computers and printers in a single research building in the 1970s. Today, versions of it carry data across offices, homes, factories, cloud data centers and some of the largest AI clusters ever built.

The beginning at Xerox PARC

Ethernet was invented at Xerox’s Palo Alto Research Center in the early 1970s, where researchers were building networked workstations and laser printers. The name was a nod to the luminiferous ether, the medium nineteenth-century physicists once imagined carried light. The original design used a shared coaxial cable that every computer tapped into.

Because all machines shared one wire, Ethernet needed a way to handle collisions when two machines spoke at once. Its solution, known as carrier sense multiple access with collision detection, let each machine listen before talking, detect collisions and retry after a random wait.

Advertisement

Becoming a standard

In the early 1980s, Ethernet was formalized as an open standard through the IEEE 802.3 committee. Openness proved decisive. Many companies could build compatible equipment, which drove prices down and adoption up. Competing local network technologies of the era gradually faded.

Twisted pair, switches and speed

Several shifts made Ethernet what it is today:

  • Moving from coaxial cable to inexpensive twisted-pair copper wiring, the familiar network cable with a plastic plug.
  • Replacing shared hubs with switches, which gave each device its own dedicated link and effectively ended collisions.
  • Adding fiber optic versions for longer distances and higher speeds.

Speeds climbed through 10 megabits, 100 megabits and 1 gigabit per second, then on to 10, 40 and 100 gigabits. Data center links have since moved to 400 and 800 gigabits, with faster rates following.

From office network to data center fabric

As cloud computing grew, Ethernet became the default network inside data centers. Its huge ecosystem, broad expertise and steadily falling cost per bit made it the natural choice for connecting servers at scale.

Ethernet was never designed to be lossless, though, and that mattered when AI training arrived. Tightly synchronized workloads suffer when packets are dropped. The industry responded with technologies such as RDMA over Converged Ethernet, refined congestion control and, more recently, industry efforts like the Ultra Ethernet Consortium, formed in 2023 to adapt Ethernet more fully for AI and high-performance computing.

Advertisement

Why its history matters

Ethernet’s story is a good illustration of how open standards tend to win over time. A technology that many vendors can build and many engineers understand gets cheaper and better with each generation. That track record is a big part of why so many in the industry expect Ethernet to play a growing role in AI networking, even as specialized alternatives continue to evolve. Fifty years on, the basic idea of a common, interoperable way to connect machines still shapes how the world’s computers talk.

Milestones Along the Way

Ethernet’s history can be read as a series of steps, each solving a problem the previous generation ran into. A simplified timeline of the major shifts:

  1. The shared cable era. Early Ethernet, developed at PARC by a team that included Robert Metcalfe and David Boggs, ran over thick coaxial cable. Computers attached to the cable with clamp-on taps. A later version used thinner, easier-to-handle coax. Both shared one medium among many machines.
  2. An industry agreement. Before the IEEE standard, Digital Equipment Corporation, Intel and Xerox published a joint specification around 1980, often called DIX Ethernet. Bringing major companies together early helped the technology spread.
  3. The move to twisted pair. Standards for running Ethernet over telephone-style twisted-pair wiring, with each device cabled back to a central point, made networks easier to install and troubleshoot. A single bad connection no longer brought down a whole segment.
  4. Switching. As switches replaced hubs, each device gained a private link, and full-duplex operation let it send and receive at the same time. Collision detection, once central to the design, became largely unnecessary in practice.
  5. Speed generations. Each new speed tier kept the familiar Ethernet frame format, so software and management tools carried forward even as the physical layer changed dramatically.
  6. Data center scale. Ethernet moved from connecting desks to connecting entire server farms, with fiber and high-speed copper links and switch chips handling enormous volumes.
  7. Adapting for AI. RDMA support, congestion control and new specification work aim to give Ethernet the predictable, low-loss behavior that AI training demands.

Why Backward Compatibility Was a Superpower

One of Ethernet’s quiet strengths is that it changed almost everything about its physical form while keeping the core frame structure recognizable. That had practical effects:

  • Software kept working. Operating systems and applications did not need to be rewritten every time speeds increased.
  • Skills carried over. Network engineers could build on what they already knew rather than starting fresh with each generation.
  • Mixed networks were possible. Older and newer equipment could often operate on the same network, letting organizations upgrade gradually.
  • Auto-negotiation helped. Devices could detect a shared speed automatically, so a new device plugged into an older port still connected.

Common Misunderstandings

“Ethernet and the internet are the same thing”

Ethernet connects devices within a local network or data center. The internet is a network of networks, using the Internet Protocol to carry traffic between them. Ethernet frames often carry internet traffic over each local hop, but the two are separate layers.

“Wi-Fi is wireless Ethernet”

Wi-Fi was developed under a different IEEE standards family, 802.11. The two are designed to work together smoothly, and Wi-Fi networks usually connect into wired Ethernet, but they are distinct technologies.

“Ethernet won because it was technically best”

Technical merit mattered, but openness, cost, broad vendor support and a large pool of skilled people played major roles. Rival local network technologies of the 1980s and 1990s had their own strengths, yet Ethernet’s ecosystem grew faster.

Questions Readers Ask

Why did collisions stop mattering?

Collisions happen when devices share one medium. Once each device had its own dedicated link to a switch and could send and receive simultaneously, there was no shared wire for signals to collide on.

Is the original collision-handling method still in the standard?

It remains part of Ethernet’s history and early standards, but modern high-speed links operate in full-duplex mode, where it plays no practical role.

What does Ethernet’s future look like?

Specification work continues on faster speeds and on features for AI and high-performance computing. As the original article suggests, its long record of adapting makes it a strong candidate to keep evolving.

This history is general education and not investment advice. For financial decisions related to networking companies, consult a qualified financial professional.

Latest stories

View all

Networking

The Control Plane Can Be a Shared Dependency Across Separate Systems

Two independent-looking systems can still rely on one service to decide what they should do. Configuration management, identity, name resolution and orchestration can become common dependencies even when the data paths are physically separate.

Published

on

Bundles of blue network cables

Photo: Scott Rodgerson / Unsplash

Two independent-looking systems can still rely on one service to decide what they should do. Configuration management, identity, name resolution and orchestration can become common dependencies even when the data paths are physically separate.

The operating distinction

The data plane moves the work, while control functions establish or manage its behavior. Some equipment continues operating through a temporary control interruption; other actions may fail until control returns. The distinction matters because successful ongoing traffic does not necessarily prove that new sessions or changes will work.

Advertisement

Management dependencies can extend beyond the network team. Identity services and access systems may be owned by another group, while the people restoring equipment assume those services are available. That creates an organizational boundary as well as a technical one.

A practical example

Picture a hypothetical network that keeps existing connections running while its management service is unavailable. Monitoring may report that traffic is flowing, yet a new deployment cannot receive the configuration it needs. Both observations can be true at the same time.

Questions worth asking

Duplicated data links do not explain the availability of the services that configure them. Identifying control dependencies helps distinguish uninterrupted traffic from the broader ability to manage, replace and restart equipment after a fault.

  • Which functions keep working when the shared control service is unavailable?
  • Can new sessions and replacement devices be brought into service?
  • How is access to the management system restored during a broader incident?

What the evidence supports

A shared control service is not automatically an unacceptable design. Centralization can simplify management. The task is to identify what depends on it, how interruption affects different operations and how restoration is tested. A diagram should show management dependencies as well as the visible cables.

A useful tabletop discussion asks what can be observed, changed and recovered if the common management service is absent. The answer should distinguish a service that can continue automatically from one that needs human intervention or new configuration. It can then identify the approved route for that intervention. This provides a better picture of recovery capability than a diagram that shows duplicated data links but omits who or what controls them.

Advertisement

Separate the ability to keep current work moving from the ability to manage or restart it.

Quick check

How much did you catch? Tap a question to see the answer.

1. How can separate systems share a dependency?

Answer: Through control functions like identity, configuration management, name resolution or orchestration.

2. Does flowing traffic prove new changes will work?

Answer: No. Existing connections can run while new sessions or deployments fail.

3. Why is this an organizational issue too?

Answer: Identity and access services may belong to another team.

A Map of Common Control Dependencies

Control dependencies are often invisible on a physical diagram because they do not occupy their own cables. Listing them explicitly is a useful first step. In many environments, the shared services include:

  • Identity and authentication. The systems that confirm who an engineer or automated process is and what they are allowed to change.
  • Name resolution. The services that translate names into addresses for both applications and management tools.
  • Configuration management. The repositories and tools that hold intended device settings and push them out.
  • Orchestration and scheduling. The systems that decide where workloads run and start or stop them.
  • Certificates and secrets. The services that issue and renew the credentials systems use to trust each other.
  • Time synchronization. Accurate time underpins logging, certificate validity and coordination.
  • Out-of-band management. The separate access path engineers use when the main network is unavailable.

Running a Control-Plane Tabletop Exercise

A tabletop exercise lets a team walk through a scenario without touching live systems. A simple structure works well.

  1. Pick one shared service. Assume it is unavailable for a defined period.
  2. List what keeps running. Identify functions expected to continue automatically, such as existing traffic flows.
  3. List what stops. Identify actions that would fail, such as new deployments, logins, configuration pushes or device replacements.
  4. Trace the recovery route. Determine how engineers would reach the affected systems, and whether that route itself depends on the missing service.
  5. Check emergency access. Confirm that break-glass credentials or local access methods exist, are controlled and have been tested.
  6. Record corrections. Capture missing documentation, unclear ownership or circular dependencies discovered during the walk-through.

Common mistakes

A frequent discovery is a circular dependency, where the tool needed to restore a service relies on that same service. Another is an out-of-band network that quietly shares authentication or name resolution with the main environment. A third is assuming that the identity team will be available and informed during an infrastructure incident, when no joint procedure exists. Finally, emergency credentials are sometimes created and never tested, so nobody knows whether they still work.

What This Means for Businesses and Readers

For organizations using cloud and hosted services, control-plane dependencies help explain why an outage can affect services that appear unrelated. A disruption in a shared management or identity function can prevent changes and new connections across many systems while existing work continues. For readers trying to understand an incident report, distinguishing between data-plane and control-plane effects often clarifies what customers actually experienced.

Separate cables can carry the work. Something still has to tell them what to do.

This is general education about system design. It does not assess any particular provider’s architecture.

Questions Readers Ask

Is centralizing control a mistake?

Not necessarily. Centralized management can improve consistency and security. The important part is understanding and testing what depends on it.

What is the difference between the data plane and the control plane?

The data plane carries the actual traffic or work. The control plane decides how that traffic is routed, configured and managed.

Why might existing connections survive while new ones fail?

Established sessions may already have the information they need, while new sessions require lookups, authentication or configuration from the unavailable service.

What is break-glass access?

A tightly controlled emergency method of reaching systems when normal access paths are unavailable, used under defined conditions and recorded.

How often should control dependencies be reviewed?

Whenever a shared service is introduced, replaced or reorganized, and periodically in between, because new dependencies tend to accumulate quietly as tools and teams change over time.

BOSSTOX is coming to iPhone

AI infrastructure explainers and news on iPhone, iPad and Apple Watch.

See BOSSTOX

Continue Reading

Networking

Two Fiber Contracts Can Still Share One Excavation Risk

Buying connections from different suppliers does not establish that the physical routes are independent. Somewhere beyond the facility fence, those services may pass through the same duct, bridge or building entrance, creating a common exposure.

Published

on

Road work on a county road

Photo: Tom Shamberger / Unsplash

Buying connections from different suppliers does not establish that the physical routes are independent. Somewhere beyond the facility fence, those services may pass through the same duct, bridge or building entrance, creating a common exposure.

The operating distinction

Network service is a chain of physical assets and operational arrangements. Separate billing relationships can sit on shared infrastructure. Route diversity therefore asks where the cables actually travel and which crossings, access points and equipment rooms they share. Logical paths alone cannot answer every physical question.

Advertisement

The same reasoning applies to restoration plans. An alternate service that survives one local cable fault may still be affected by a wider event. Naming the scenario avoids an all-or-nothing conversation about whether a network is diverse.

A practical example

Imagine two connections that enter a campus from opposite sides but meet at the same nearby road crossing. A fault at that crossing could affect both services. The separate entrances remain useful, but they do not remove that shared section of the route.

Questions worth asking

Different contracts can provide useful commercial options without proving physical independence. Reading the route evidence separately helps identify the actual benefit of the arrangement and the remaining shared exposure that needs another response.

  • Which physical segments are shared outside the property boundary?
  • When was the route information last confirmed with the providers?
  • What restoration options remain if that common segment is unavailable?

What the evidence supports

Route documentation can be incomplete or subject to confidentiality limits. It can also become stale after changes. The practical goal is to establish the important shared risks and the evidence available, rather than assume that a second contract eliminates every possible network interruption.

A route sketch should distinguish confirmed information from an assumption or a supplier statement awaiting clarification. It can then show the important uncertainty without revealing sensitive route details publicly. The point is to make procurement and operating discussions more precise: which kind of damage is covered, which common dependencies remain and what evidence would justify a stronger claim. That is more useful than assuming that different service names imply different physical journeys.

Advertisement

Diversity is a property of the complete path, not simply the number of names on the invoices.

Quick check

How much did you catch? Tap a question to see the answer.

1. Do two suppliers guarantee independent routes?

Answer: No. They may share a duct, bridge or building entrance.

2. What does route diversity ask?

Answer: Where the cables physically travel and which crossings they share.

3. What could two entrances on opposite sides still share?

Answer: The same nearby road crossing.

How Shared Segments Usually Hide

Common exposure rarely announces itself on a contract. It tends to sit in places that are easy to overlook because they are outside the property and outside the day-to-day attention of the facility team.

  • Shared conduit or duct banks. Different providers may lease space in the same underground structure along a road.
  • Bridge and rail crossings. Physical geography often funnels routes toward a small number of practical crossing points over rivers, highways or rail lines.
  • Common meet points. Carriers can hand traffic off in the same nearby building or cabinet before it reaches the facility.
  • Resold or leased capacity. One supplier may carry traffic over another supplier’s fiber, so two names on two invoices can describe one physical cable.
  • The same building entrance. Even when routes are separate for miles, they may converge on a single entrance room or cable vault.

A Practical Route Review, Step by Step

Facility teams and buyers can approach route diversity as a structured review rather than a yes-or-no question.

  1. Request route information from each provider. Ask for the level of detail they are able to share, recognizing that some route data is confidential.
  2. Mark known convergence points. Identify crossings, meet points, entrances and any segments where the routes appear to run near each other.
  3. Label the quality of each claim. Separate confirmed information from provider statements awaiting verification and from assumptions.
  4. Name the scenarios. Consider a single cable cut near the site, construction damage along a shared road, a bridge closure and a problem in a shared equipment room.
  5. Map restoration options to each scenario. Decide which services would remain available and which would require a separate response.
  6. Set a refresh date. Routes change when providers reroute, rebuild or sell assets. Agree on how often the information will be confirmed again.

Common mistakes

One mistake is accepting a provider’s diversity label without asking what it covers. Another is checking diversity once at contract signing and never again. A third is focusing entirely on the long-haul portion of a route while ignoring the last stretch near the facility, where excavation work is often most likely to occur. A fourth is assuming that a wireless or alternate technology backup has no shared dependency, when it may rely on the same power, building or tower infrastructure.

What This Means for Businesses Relying on Connectivity

For organizations that depend on a data center or cloud region, network diversity is part of the resilience they are buying, whether or not they negotiate it directly. A provider that can explain its known shared exposures clearly is usually giving a more honest picture than one that simply states its routes are diverse. For readers following infrastructure companies, route quality is one of the less visible factors behind service reliability, and it rarely appears in a headline.

The most useful diversity statement describes which failures the arrangement is expected to survive and which it is not.

Questions Readers Ask

Why do providers keep route details confidential?

Detailed route maps can create security concerns and may be commercially sensitive. Buyers can often obtain enough information to assess shared risk under appropriate agreements.

Is physical diversity always worth the cost?

It depends on how much an interruption would cost the business and which scenarios matter most. The decision benefits from naming the risk rather than buying diversity as a general label.

Can two routes ever be fully independent?

Complete independence is difficult to prove. The practical aim is to reduce the most likely and most damaging shared exposures and to know which ones remain.

How does excavation risk relate to fiber?

Buried cable can be damaged during digging for roads, utilities or construction. Shared corridors mean one digging accident can affect more than one service.

BOSSTOX is coming to iPhone

AI infrastructure explainers and news on iPhone, iPad and Apple Watch.

See BOSSTOX

Continue Reading

Networking

InfiniBand vs. Ethernet for AI Clusters

InfiniBand offers a tightly integrated path for synchronized AI traffic, while Ethernet offers broader compatibility and choice; the right fabric depends on workload, scale, software, and operating priorities.

Published

on

A hand plugging in an ethernet cable

The networking choice inside an AI cluster is not a simple bandwidth comparison. Training jobs repeatedly move parameters, gradients, and activations between accelerators. If the network stalls, expensive GPUs wait. The result can be lower utilization even when every link’s headline speed looks impressive.

InfiniBand and Ethernet can both build large clusters. They differ in how much of the transport, congestion control, topology, and software stack is standardized or integrated for the target workload.

Why AI traffic is unusual

AI training produces synchronized bursts. Many accelerators finish a step and communicate at nearly the same time. That creates a traffic pattern that is sensitive to tail latency, congestion, packet loss, and collective-operation performance.

Advertisement

A general enterprise network can tolerate variable paths and occasional retransmission. A large training cluster may lose efficiency if a small number of links become hot and delay an all-reduce operation. The network is part of the compute system, not just plumbing.

InfiniBand’s case

InfiniBand was designed for high-performance computing. It supports low-latency communication, remote direct memory access, and features intended to keep data moving between nodes with limited CPU intervention.

NVIDIA’s April 2025 description of a DGX SuperPOD deployment cited Quantum-2 InfiniBand networking and a digital-twin validation process. The company said a SoftBank deployment of 510 DGX B200 systems was completed in three weeks, compared with a typical six-plus months, and that NVIDIA estimated the avoided downtime at roughly $1 million per day for a 1,000-server, 8,000-GPU data center. That estimate is NVIDIA’s analysis, not an independent industry average, but it illustrates why network deployment speed can have financial value.

InfiniBand’s strength is a validated stack. Hardware, drivers, collective libraries, and topology can be designed together. That can reduce the integration burden for a customer that wants a high-performing training appliance.

Its weaknesses are ecosystem and flexibility. It can require specialized adapters, switches, expertise, and operational tools. A company with a large Ethernet organization may prefer a fabric it already knows.

Advertisement

Ethernet’s case

Ethernet is widely deployed across data centers and connects servers, storage, offices, and the public network. It offers a large supplier base, familiar management tools, and multiple implementation choices.

AI Ethernet systems commonly use lossless or low-loss designs, remote direct memory access over Converged Ethernet, explicit congestion notification, and careful buffer and topology planning. The performance depends heavily on configuration. “Ethernet” by itself does not say whether a cluster will perform well.

Intel’s Gaudi 3 materials emphasize standard Ethernet and a 32-node all-Ethernet reference design. The pitch is not merely lower equipment cost. It is the ability to use existing operational skills and to avoid a completely closed networking path.

Speed changes the economics

Arista announced new 800G platforms in October 2025 and said 800GbE port shipments more than tripled sequentially in the second quarter of 2025, according to cited market research. The company described 3.2-terabit-per-second HyperPorts and AI uses including lossless training and inference.

800G matters because an AI rack can have many high-bandwidth links. If each accelerator needs 800 gigabits per second of east-west bandwidth, a 72-accelerator rack creates enormous switching demand. Moving to 1.6T transceivers can reduce port counts or support larger bisection bandwidth, but it also raises optical, thermal, and signal-integrity requirements.

The comparison should be made at job completion time

A network that delivers higher link speed but poor congestion behavior may lose to a slower network with better collective performance. The useful test is end-to-end: time to train, tokens per second, scaling efficiency from one node to 32 or 128 nodes, tail latency, and behavior during failures.

The test should include the actual model, precision, batch size, topology, and software release. A vendor’s ideal benchmark can be informative, but it is not a deployment guarantee.

Operations may decide the outcome

A cluster can fail financially through poor utilization. If the team cannot troubleshoot the fabric, the expensive accelerators sit idle. A familiar Ethernet operation may be worth more than a theoretical performance advantage. Conversely, a dedicated AI service with a specialized team may benefit from the tighter InfiniBand stack.

A hybrid architecture is common. InfiniBand or specialized Ethernet can carry accelerator-to-accelerator traffic, while ordinary Ethernet handles management, storage, and user access. The boundary must be clear so a failure in one network does not quietly degrade the other.

The decision rule

Choose InfiniBand when predictable scale-out training, validated deployment, and low-latency collectives dominate. Choose Ethernet when supplier choice, operational familiarity, interoperability, and mixed workloads matter more. Measure both on the workload that pays the bills.

The procurement decision should include the people who will operate the fabric. Ask how many engineers are trained on the selected switches, how firmware is qualified, how telemetry is exported, and how a bad optic is isolated. Also ask whether the vendor can support a mixed-generation cluster during a refresh. A network that is technically fast but difficult to diagnose can reduce accelerator utilization for weeks. In that sense, operational simplicity is a performance feature, not an administrative preference.

At very large scale, fabric choice also affects the power budget. More ports, higher-speed optics, and additional switch tiers consume electricity and occupy rack space. That overhead should be included in the same total-cost model as accelerator power. A lower-cost accelerator that needs a larger network may not be cheaper at the cluster level. The fair comparison is the amount of useful work delivered by the complete system after networking, cooling, software, and operations are included.

Sources

  1. NVIDIA, “NVIDIA Helps Build AI Factories Faster Than Ever with DGX SuperPOD,” April 11, 2025: developer.nvidia.com
  2. NVIDIA, “Blackwell: Born for Extreme-Scale AI Inference,” 2025: blogs.nvidia.com
  3. Intel, “Intel Gaudi AI Accelerator Products,” accessed October 2026: intel.com
  4. Arista, “Arista Networks Unveils Next Generation Data and AI Centers,” October 29, 2025: arista.com
  5. NVIDIA, “Reference Architectures: Deep Dive,” accessed October 2026: docs.nvidia.com

BOSSTOX Research articles are drafted with AI assistance and reviewed by our editors before publication. See our editorial standards.

Continue Reading

Trending