fat-tree network topology
E679889
A fat-tree network topology is a hierarchical, tree-like interconnection structure for parallel and distributed systems that increases link bandwidth toward the root to avoid bottlenecks and provide high bisection bandwidth and scalability.
All labels observed (2)
| Label | Occurrences |
|---|---|
| Clos topology | 1 |
| fat-tree network topology canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T7666043 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: fat-tree network topology Context triple: [Charles E. Leiserson, notableConcept, fat-tree network topology]
-
A.
Network-in-Network architecture
Network-in-Network architecture is a convolutional neural network design that replaces traditional linear convolution layers with micro multilayer perceptrons (MLPs) to enhance feature abstraction and model expressiveness.
-
B.
Equinix Fabric
Equinix Fabric is a software-defined interconnection service that enables private, on-demand connectivity between enterprises, cloud providers, and network services within Equinix’s global data center ecosystem.
-
C.
OSA-Express networking
OSA-Express networking is IBM’s high-speed, integrated network adapter technology for mainframe systems, providing advanced Ethernet and IP connectivity for IBM System z environments.
-
D.
Next Generation Network architectures
Next Generation Network architectures are advanced telecommunications frameworks that integrate voice, data, and multimedia services over a unified, packet-based IP infrastructure to enable flexible, scalable, and service-agnostic communication.
-
E.
AVE network
The AVE network is Spain’s high-speed rail system that connects major cities across the country with fast, long-distance train services.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: fat-tree network topology Target entity description: A fat-tree network topology is a hierarchical, tree-like interconnection structure for parallel and distributed systems that increases link bandwidth toward the root to avoid bottlenecks and provide high bisection bandwidth and scalability.
-
A.
Network-in-Network architecture
Network-in-Network architecture is a convolutional neural network design that replaces traditional linear convolution layers with micro multilayer perceptrons (MLPs) to enhance feature abstraction and model expressiveness.
-
B.
Equinix Fabric
Equinix Fabric is a software-defined interconnection service that enables private, on-demand connectivity between enterprises, cloud providers, and network services within Equinix’s global data center ecosystem.
-
C.
OSA-Express networking
OSA-Express networking is IBM’s high-speed, integrated network adapter technology for mainframe systems, providing advanced Ethernet and IP connectivity for IBM System z environments.
-
D.
Next Generation Network architectures
Next Generation Network architectures are advanced telecommunications frameworks that integrate voice, data, and multimedia services over a unified, packet-based IP infrastructure to enable flexible, scalable, and service-agnostic communication.
-
E.
AVE network
The AVE network is Spain’s high-speed rail system that connects major cities across the country with fast, long-distance train services.
- F. None of above. chosen
Statements (50)
| Predicate | Object |
|---|---|
| instanceOf |
interconnection network
ⓘ
network topology ⓘ |
| basedOn | tree topology ⓘ |
| canBeImplementedWith |
commodity Ethernet switches
ⓘ
multi-stage switch networks ⓘ |
| commonlyUsedFor |
cloud data center fabrics
ⓘ
cluster interconnects ⓘ |
| connects |
aggregation switches to core switches
ⓘ
edge switches to aggregation switches ⓘ end hosts to edge switches ⓘ |
| differsFrom |
Clos network
NERFINISHED
ⓘ
bus topology ⓘ mesh topology ⓘ ring topology ⓘ simple tree topology ⓘ |
| enables | full bisection bandwidth with sufficient switch ports ⓘ |
| hasAdvantage |
can be built from identical switch building blocks
ⓘ
good scalability with number of switches ⓘ |
| hasCharacteristic |
higher link capacity near the root
ⓘ
multiple equal-cost paths between hosts ⓘ |
| hasDesignGoal |
avoid bottlenecks near the root
ⓘ
provide high aggregate bandwidth ⓘ support large-scale system expansion ⓘ |
| hasLevel |
aggregation layer
ⓘ
core layer ⓘ edge layer ⓘ |
| hasLimitation |
increased cabling complexity
ⓘ
requires careful routing and traffic engineering ⓘ |
| hasProperty |
high bisection bandwidth
ⓘ
multi-path connectivity ⓘ non-blocking under certain traffic patterns ⓘ regular ⓘ scalable ⓘ symmetrical ⓘ |
| hasStructure |
hierarchical
ⓘ
tree-like ⓘ |
| increasesBandwidthToward | root of the tree ⓘ |
| introducedBy | Charles E. Leiserson NERFINISHED ⓘ |
| introducedIn | 1985 ⓘ |
| isInspiredBy | fat-tree data structure in computer science NERFINISHED ⓘ |
| oftenUses |
ECMP routing
ⓘ
layer-3 IP routing in data centers ⓘ |
| originallyProposedFor | VLSI networks ⓘ |
| requires | routing protocols that exploit path diversity ⓘ |
| supports |
fault tolerance via path redundancy
ⓘ
load balancing across multiple paths ⓘ |
| usedIn |
data center networks
ⓘ
distributed systems ⓘ high-performance computing clusters ⓘ parallel computing systems ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: fat-tree network topology Description of subject: A fat-tree network topology is a hierarchical, tree-like interconnection structure for parallel and distributed systems that increases link bandwidth toward the root to avoid bottlenecks and provide high bisection bandwidth and scalability.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
Clos topology