BLAS
E440649
BLAS (Basic Linear Algebra Subprograms) is a standardized collection of low-level routines for performing common linear algebra operations such as vector and matrix multiplication, widely used as a performance-optimized foundation in scientific computing.
All labels observed (1)
| Label | Occurrences |
|---|---|
| BLAS canonical | 5 |
How this entity was disambiguated
This entity first appeared as the object of triple T4443242 — 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: BLAS Context triple: [LinearAlgebra, exportsConstant, BLAS]
-
A.
LINPACK
LINPACK is a widely used benchmark and software library for performing numerical linear algebra computations, particularly solving systems of linear equations.
-
B.
cuBLAS
cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
-
C.
cuSPARSE
cuSPARSE is NVIDIA’s GPU-accelerated library providing high-performance sparse linear algebra routines for CUDA applications.
-
D.
LinearAlgebra
LinearAlgebra is Julia’s standard library module providing core functionality for vectors, matrices, and advanced linear algebra operations.
-
E.
XLA
XLA (Accelerated Linear Algebra) is a domain-specific compiler for linear algebra that optimizes and accelerates machine learning computations on hardware such as TPUs and GPUs.
- 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: BLAS Target entity description: BLAS (Basic Linear Algebra Subprograms) is a standardized collection of low-level routines for performing common linear algebra operations such as vector and matrix multiplication, widely used as a performance-optimized foundation in scientific computing.
-
A.
LINPACK
LINPACK is a widely used benchmark and software library for performing numerical linear algebra computations, particularly solving systems of linear equations.
-
B.
cuBLAS
cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
-
C.
cuSPARSE
cuSPARSE is NVIDIA’s GPU-accelerated library providing high-performance sparse linear algebra routines for CUDA applications.
-
D.
LinearAlgebra
LinearAlgebra is Julia’s standard library module providing core functionality for vectors, matrices, and advanced linear algebra operations.
-
E.
XLA
XLA (Accelerated Linear Algebra) is a domain-specific compiler for linear algebra that optimizes and accelerates machine learning computations on hardware such as TPUs and GPUs.
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
application programming interface
ⓘ
numerical linear algebra library specification ⓘ software standard ⓘ |
| abbreviation | BLAS NERFINISHED ⓘ |
| defines | standard interfaces for linear algebra kernels ⓘ |
| designedFor |
high performance on a wide range of architectures
ⓘ
portability across hardware platforms ⓘ |
| field |
high‑performance computing
ⓘ
numerical linear algebra ⓘ scientific computing ⓘ |
| fullName | Basic Linear Algebra Subprograms NERFINISHED ⓘ |
| hasImplementation |
ATLAS
NERFINISHED
ⓘ
Apple Accelerate framework NERFINISHED ⓘ IBM ESSL NERFINISHED ⓘ Intel Math Kernel Library NERFINISHED ⓘ Netlib reference BLAS NERFINISHED ⓘ OpenBLAS NERFINISHED ⓘ cuBLAS NERFINISHED ⓘ |
| hasLevel |
Level 1 BLAS
NERFINISHED
ⓘ
Level 2 BLAS NERFINISHED ⓘ Level 3 BLAS NERFINISHED ⓘ |
| languageBinding |
C
NERFINISHED
ⓘ
C++ ⓘ Fortran NERFINISHED ⓘ Python (via wrappers such as NumPy and SciPy) ⓘ |
| layer | low‑level numerical software ⓘ |
| operationType |
matrix‑matrix operations
ⓘ
matrix‑vector operations ⓘ vector operations ⓘ vector‑vector operations ⓘ |
| optimizationTarget |
cache efficiency
ⓘ
parallel execution ⓘ vectorization ⓘ |
| property | interface is standardized while implementations may be vendor‑optimized ⓘ |
| purpose |
provide standardized low‑level routines for linear algebra operations
ⓘ
serve as a performance‑optimized foundation for higher‑level numerical libraries ⓘ |
| standardizedBy | Netlib community NERFINISHED ⓘ |
| supportsDataType |
double‑precision complex
ⓘ
double‑precision real ⓘ single‑precision complex ⓘ single‑precision real ⓘ |
| typicalUseCase |
dense linear algebra computations
ⓘ
machine learning workloads ⓘ numerical simulations ⓘ |
| usedAs |
backend for linear algebra in many programming environments
ⓘ
building block for LAPACK ⓘ building block for many scientific computing libraries ⓘ |
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: BLAS Description of subject: BLAS (Basic Linear Algebra Subprograms) is a standardized collection of low-level routines for performing common linear algebra operations such as vector and matrix multiplication, widely used as a performance-optimized foundation in scientific computing.
Referenced by (5)
Full triples — surface form annotated when it differs from this entity's canonical label.