gptkbp:instanceOf
|
gptkb:software
|
gptkbp:category
|
GPU programming
parallel computing platform
|
gptkbp:compatibleWith
|
gptkb:NVIDIA_GPUs
|
gptkbp:developedBy
|
gptkb:NVIDIA
|
gptkbp:documentation
|
https://docs.nvidia.com/cuda/
|
gptkbp:enables
|
gptkb:machine_learning
deep learning
high-performance computing
scientific computing
GPU acceleration
|
gptkbp:firstReleased
|
2007
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVIDIA CUDA Toolkit
|
gptkbp:includes
|
gptkb:CUDA_Graphs
gptkb:cuBLAS
gptkb:cuFFT
gptkb:cuRAND
gptkb:cuSPARSE
gptkb:CUDA_libraries
gptkb:cuDNN
gptkb:CUDA_debugger
gptkb:CUDA_profiler
gptkb:CUDA_runtime
gptkb:CUDA_Driver_API
gptkb:CUDA_Math_Library
gptkb:CUDA_Runtime_API
gptkb:CUDA_compiler_(nvcc)
gptkb:NCCL
gptkb:CUDA_Events
gptkb:CUDA_Streams
Thrust
|
gptkbp:latestReleaseVersion
|
12.x
|
gptkbp:license
|
proprietary
|
gptkbp:operatingSystem
|
gptkb:Windows
gptkb:macOS
gptkb:Linux
|
gptkbp:supports
|
gptkb:Unified_Memory
gptkb:Tensor_Cores
CUDA events
CUDA streams
dynamic parallelism
peer-to-peer memory access
multi-GPU programming
|
gptkbp:supportsLanguage
|
gptkb:Python_(via_libraries)
gptkb:Fortran
gptkb:C++
C
|
gptkbp:usedFor
|
parallel computing
GPU computing
general-purpose computing on GPUs
|
gptkbp:website
|
https://developer.nvidia.com/cuda-toolkit
|
gptkbp:bfsParent
|
gptkb:NVIDIA_cuBLAS
|
gptkbp:bfsLayer
|
6
|