Statements (51)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Library
|
| gptkbp:available_on |
gptkb:Linux
gptkb:mac_OS gptkb:Windows |
| gptkbp:developed_by |
gptkb:NVIDIA
|
| gptkbp:has |
community support
|
| https://www.w3.org/2000/01/rdf-schema#label |
cu BLAS
|
| gptkbp:includes |
matrix multiplication routines
BLAS (Basic Linear Algebra Subprograms) functionality |
| gptkbp:integrates_with |
gptkb:Tensor_Flow
gptkb:MATLAB gptkb:Py_Torch gptkb:Num_Py |
| gptkbp:is |
cross-platform
open-source |
| gptkbp:is_optimized_for |
gptkb:NVIDIA_GPUs
|
| gptkbp:latest_version |
11.0
11.4 11.3 11.9 11.5 11.6 11.1 11.2 11.7 11.8 |
| gptkbp:part_of |
gptkb:CUDA_Toolkit
|
| gptkbp:provides |
API for developers
error handling mechanisms documentation and examples high-performance computing capabilities GPU-accelerated linear algebra routines performance optimization for matrix operations |
| gptkbp:supports |
gptkb:CUDA
multi-threading asynchronous execution double precision single precision custom kernels half precision mixed precision |
| gptkbp:used_in |
gptkb:Graphics_Processing_Unit
gptkb:machine_learning image processing data analysis deep learning financial modeling scientific computing signal processing |
| gptkbp:bfsParent |
gptkb:CUDA
|
| gptkbp:bfsLayer |
4
|