cuBLAS
E209957
cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
All labels observed (2)
How this entity was disambiguated
This entity first appeared as the object of triple T1893377 — 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: cuBLAS Context triple: [NVIDIA CUDA, includes, cuBLAS]
-
A.
CuPy
CuPy is an open-source array library for Python that accelerates numerical computing by providing a NumPy-compatible interface backed by GPU execution.
-
B.
NVIDIA CUDA
NVIDIA CUDA is a parallel computing platform and programming model that enables developers to use NVIDIA GPUs for general-purpose high-performance computing.
-
C.
OpenCL
OpenCL is an open, cross-platform framework for writing programs that execute across heterogeneous systems including CPUs, GPUs, and other processors.
-
D.
PlaidML
PlaidML is an open-source, hardware-agnostic deep learning engine designed to accelerate neural network computation on a wide range of GPUs and other devices.
-
E.
OpenACC
OpenACC is a directive-based parallel programming standard designed to simplify the development of portable, high-performance code on heterogeneous systems such as GPUs and multicore CPUs.
- 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: cuBLAS Target entity description: cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
-
A.
CuPy
CuPy is an open-source array library for Python that accelerates numerical computing by providing a NumPy-compatible interface backed by GPU execution.
-
B.
NVIDIA CUDA
NVIDIA CUDA is a parallel computing platform and programming model that enables developers to use NVIDIA GPUs for general-purpose high-performance computing.
-
C.
OpenCL
OpenCL is an open, cross-platform framework for writing programs that execute across heterogeneous systems including CPUs, GPUs, and other processors.
-
D.
PlaidML
PlaidML is an open-source, hardware-agnostic deep learning engine designed to accelerate neural network computation on a wide range of GPUs and other devices.
-
E.
OpenACC
OpenACC is a directive-based parallel programming standard designed to simplify the development of portable, high-performance code on heterogeneous systems such as GPUs and multicore CPUs.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
GPU-accelerated BLAS library
ⓘ
software library ⓘ |
| developer |
NVIDIA
ⓘ
linked to:
NVIDIA Corporation
|
| distribution | included in CUDA Toolkit installers ⓘ |
| documentationURL | https://docs.nvidia.com/cuda/cublas/index.html ⓘ |
| implements | BLAS ⓘ |
| license | proprietary (distributed with CUDA Toolkit) ⓘ |
| optimizedFor |
NVIDIA GPUs
ⓘ
linked to:
GPU
|
| partOf |
NVIDIA CUDA Toolkit
ⓘ
linked to:
NVIDIA CUDA
|
| programmingModel |
CUDA
ⓘ
linked to:
NVIDIA CUDA
|
| providesAPI |
C API
ⓘ
device-side API (cuBLASLt / newer interfaces) ⓘ host-side API ⓘ |
| relatedLibrary |
cuBLASLt
ⓘ
linked to:
cuBLAS
cuFFT ⓘ cuSOLVER ⓘ cuSPARSE ⓘ |
| requires |
CUDA driver
ⓘ
CUDA runtime ⓘ
linked to:
CUDA Driver API
|
| runsOn | CUDA-enabled GPUs ⓘ |
| supportsDataType |
Tensor Core-accelerated mixed precision
ⓘ
double-precision floating point ⓘ half-precision floating point ⓘ single-precision floating point ⓘ |
| supportsFeature |
asynchronous execution with CUDA streams
ⓘ
handle-based context management ⓘ strided batched GEMM ⓘ tensor core acceleration (on supported GPUs) ⓘ workspace configuration for performance tuning ⓘ |
| supportsLanguage |
C
ⓘ
C++ ⓘ Fortran (via wrappers) ⓘ |
| supportsOperation |
GEMM (general matrix-matrix multiply)
ⓘ
Hermitian matrix operations ⓘ batched linear algebra operations ⓘ matrix-matrix operations (Level 3 BLAS) ⓘ matrix-vector operations (Level 2 BLAS) ⓘ rank-k updates ⓘ symmetric matrix operations ⓘ triangular matrix operations ⓘ vector operations (Level 1 BLAS) ⓘ |
| supportsPlatform |
Linux
ⓘ
Windows ⓘ macOS (on older CUDA-supported systems) ⓘ
linked to:
macOS
|
| supportsStandard | BLAS API semantics ⓘ |
| useCase |
HPC applications
ⓘ
deep learning primitives (e.g., GEMM-based layers) ⓘ high-performance linear algebra on GPUs ⓘ scientific computing ⓘ |
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: cuBLAS Description of subject: cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
Referenced by (5)
Full triples — surface form annotated when it differs from this entity's canonical label.