BNNS
E732975
BNNS (Basic Neural Network Subroutines) is Apple’s low-level, hardware-accelerated framework for performing neural network and machine learning computations efficiently on Apple devices.
All labels observed (2)
| Label | Occurrences |
|---|---|
| BNNS canonical | 2 |
| MPSNNGraph | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T8415092 — 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: BNNS Context triple: [Core ML, integratesWith, BNNS]
-
A.
.bn
.bn is the country code top-level domain (ccTLD) assigned to Brunei Darussalam for use in its internet addresses.
-
B.
SNN
SNN is the National Rail station code assigned to Swinton railway station in South Yorkshire, England.
-
C.
SNN
SNN is the three-letter IATA airport code for Shannon Airport in County Clare, Ireland, a major international gateway on the country’s west coast.
-
D.
NNS
NNS is the commonly used abbreviation for Newport News Shipbuilding, a major American shipyard known for constructing U.S. Navy aircraft carriers and submarines.
-
E.
BN2
BN2 is a UK postal district covering parts of eastern Brighton and nearby areas within the BN (Brighton) postcode region.
- 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: BNNS Target entity description: BNNS (Basic Neural Network Subroutines) is Apple’s low-level, hardware-accelerated framework for performing neural network and machine learning computations efficiently on Apple devices.
-
A.
.bn
.bn is the country code top-level domain (ccTLD) assigned to Brunei Darussalam for use in its internet addresses.
-
B.
SNN
SNN is the National Rail station code assigned to Swinton railway station in South Yorkshire, England.
-
C.
SNN
SNN is the three-letter IATA airport code for Shannon Airport in County Clare, Ireland, a major international gateway on the country’s west coast.
-
D.
NNS
NNS is the commonly used abbreviation for Newport News Shipbuilding, a major American shipyard known for constructing U.S. Navy aircraft carriers and submarines.
-
E.
BN2
BN2 is a UK postal district covering parts of eastern Brighton and nearby areas within the BN (Brighton) postcode region.
- F. None of above. chosen
Statements (46)
| Predicate | Object |
|---|---|
| instanceOf |
Apple framework
ⓘ
machine learning framework ⓘ software framework ⓘ |
| abbreviationFor | Basic Neural Network Subroutines ⓘ |
| category |
low-level API
ⓘ
neural network library ⓘ |
| designGoal |
efficient memory usage
ⓘ
high performance on Apple devices ⓘ low-overhead neural network primitives ⓘ |
| developer | Apple Inc. ⓘ |
| documentationSite | https://developer.apple.com/documentation/accelerate/bnns ⓘ |
| fullName | Basic Neural Network Subroutines ⓘ |
| introducedBy | Apple developer tools ⓘ |
| languageBinding | C ⓘ |
| optimizedFor |
Apple hardware accelerators
ⓘ
vector processing units ⓘ |
| partOf |
Accelerate framework
ⓘ
linked to:
Apple Accelerate framework
|
| platform |
Apple devices
ⓘ
linked to:
Apple hardware
iOS ⓘ macOS ⓘ tvOS ⓘ watchOS ⓘ |
| purpose |
efficient tensor operations
ⓘ
hardware-accelerated inference ⓘ machine learning computation ⓘ neural network computation ⓘ |
| relatedTo |
Core ML
ⓘ
Metal Performance Shaders ⓘ |
| runsOn |
Apple CPUs
ⓘ
linked to:
Apple silicon
Apple GPUs ⓘ
linked to:
Apple GPU
Apple silicon ⓘ |
| supports |
activation functions
ⓘ
convolutional neural networks ⓘ fully connected layers ⓘ inference ⓘ loss functions ⓘ normalization layers ⓘ optimizers ⓘ pooling layers ⓘ training (limited) ⓘ |
| supportsDataType |
16-bit floating point
ⓘ
32-bit floating point ⓘ 8-bit quantized formats ⓘ |
| useCase |
energy-efficient ML workloads
ⓘ
on-device machine learning ⓘ real-time inference ⓘ |
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: BNNS Description of subject: BNNS (Basic Neural Network Subroutines) is Apple’s low-level, hardware-accelerated framework for performing neural network and machine learning computations efficiently on Apple devices.
Referenced by (3)
Full triples — surface form annotated when it differs from this entity's canonical label.
linked to: BNNS