CUDA Driver API
E213159
The CUDA Driver API is a low-level programming interface from NVIDIA that gives developers fine-grained control over GPU resources and execution for CUDA applications.
All labels observed (4)
| Label | Occurrences |
|---|---|
| CUDA Driver API canonical | 2 |
| CUDA runtime | 2 |
| CUDA driver | 1 |
| NVIDIA CUDA Driver API Reference Manual | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T1893375 — 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: CUDA Driver API Context triple: [NVIDIA CUDA, includes, CUDA Driver API]
-
A.
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.
-
B.
GPUDirect
GPUDirect is an NVIDIA technology that enables high-speed, low-latency data transfers directly between GPUs and other devices or memory, bypassing the CPU to improve performance in data-intensive applications.
-
C.
cuDNN
cuDNN is NVIDIA’s GPU-accelerated library of optimized primitives for deep neural networks, widely used to speed up training and inference in frameworks like TensorFlow and PyTorch.
-
D.
cuBLAS
cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
-
E.
NCCL
NCCL (NVIDIA Collective Communications Library) is a high-performance library that optimizes multi-GPU and multi-node communication for deep learning and HPC applications.
- 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: CUDA Driver API Target entity description: The CUDA Driver API is a low-level programming interface from NVIDIA that gives developers fine-grained control over GPU resources and execution for CUDA applications.
-
A.
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.
-
B.
GPUDirect
GPUDirect is an NVIDIA technology that enables high-speed, low-latency data transfers directly between GPUs and other devices or memory, bypassing the CPU to improve performance in data-intensive applications.
-
C.
cuDNN
cuDNN is NVIDIA’s GPU-accelerated library of optimized primitives for deep neural networks, widely used to speed up training and inference in frameworks like TensorFlow and PyTorch.
-
D.
cuBLAS
cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
-
E.
NCCL
NCCL (NVIDIA Collective Communications Library) is a high-performance library that optimizes multi-GPU and multi-node communication for deep learning and HPC applications.
- F. None of above. chosen
Statements (53)
| Predicate | Object |
|---|---|
| instanceOf |
CUDA API component
ⓘ
GPU programming interface ⓘ low-level API ⓘ |
| accessedVia | C language interface ⓘ |
| allows |
control over kernel launch configuration
ⓘ
dynamic linking of device code ⓘ fine-grained control over memory allocation and deallocation ⓘ interoperability with graphics APIs ⓘ loading of CUDA modules at runtime ⓘ runtime selection of GPUs ⓘ |
| contrastedWith | CUDA Runtime API ⓘ |
| developer |
NVIDIA Corporation
ⓘ
surface form:
NVIDIA
|
| documentedIn |
CUDA Driver API
self-linksurface differs
ⓘ
surface form:
NVIDIA CUDA Driver API Reference Manual
NVIDIA CUDA Programming Guide ⓘ |
| exposes |
CUDA contexts
ⓘ
CUDA events ⓘ CUDA functions (kernels) ⓘ CUDA memory objects ⓘ CUDA modules ⓘ CUDA streams ⓘ GPU as an explicit device handle ⓘ |
| hasComponent |
context management functions
ⓘ
device management functions ⓘ driver initialization functions ⓘ error handling functions ⓘ event management functions ⓘ execution control functions ⓘ memory management functions ⓘ module management functions ⓘ peer-to-peer and unified addressing functions ⓘ stream management functions ⓘ |
| lowerLevelThan | CUDA Runtime API ⓘ |
| partOf |
NVIDIA CUDA
ⓘ
surface form:
CUDA
CUDA platform ⓘ |
| provides |
JIT compilation of PTX
ⓘ
context management ⓘ control over device attributes and limits ⓘ explicit device memory management ⓘ fine-grained control over kernel execution ⓘ low-level control over GPU resources ⓘ module and function management ⓘ multi-GPU management ⓘ peer-to-peer memory access control ⓘ stream and event management ⓘ |
| requires |
explicit context management by the application
ⓘ
explicit error checking ⓘ |
| supports |
Linux ecosystem
ⓘ
surface form:
Linux operating systems
Windows ⓘ
surface form:
Windows operating systems
macOS on supported legacy CUDA versions ⓘ |
| usedFor |
custom CUDA runtime implementations
ⓘ
high-performance GPU computing applications ⓘ language runtimes targeting CUDA ⓘ systems software that manages GPUs ⓘ |
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: CUDA Driver API Description of subject: The CUDA Driver API is a low-level programming interface from NVIDIA that gives developers fine-grained control over GPU resources and execution for CUDA applications.
Referenced by (6)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
CUDA driver
subject surface form:
CUDA
this entity surface form:
NVIDIA CUDA Driver API Reference Manual