gptkbp:instanceOf
|
parallel computing platform
|
gptkbp:API
|
gptkb:cuBLAS
gptkb:cuFFT
gptkb:cuSPARSE
gptkb:CUDA_Toolkit
gptkb:cuDNN
gptkb:NCCL
Thrust
|
gptkbp:competitor
|
gptkb:ROCm
gptkb:DirectCompute
gptkb:OpenCL
|
gptkbp:developedBy
|
gptkb:NVIDIA
|
gptkbp:documentation
|
https://docs.nvidia.com/cuda/
|
gptkbp:enables
|
gptkb:machine_learning
gptkb:GPGPU
deep learning
high-performance computing
scientific computing
video processing
real-time graphics
parallel processing
|
gptkbp:firstSupportedGPU
|
NVIDIA G80
|
gptkbp:hasVersion
|
gptkb:Tesla
gptkb:Volta
gptkb:Ada
gptkb:Hopper
gptkb:Ampere
gptkb:Kepler
gptkb:Pascal
gptkb:Turing
gptkb:Maxwell
gptkb:Fermi
|
https://www.w3.org/2000/01/rdf-schema#label
|
CUDA architecture
|
gptkbp:includes
|
streams
grids
shared memory
CUDA cores
global memory
SIMT model
thread blocks
warp scheduling
|
gptkbp:introducedIn
|
2006
|
gptkbp:latestToolkitVersion
|
12.x (as of 2024)
|
gptkbp:platform
|
gptkb:NVIDIA_GPUs
|
gptkbp:supportsLanguage
|
gptkb:Python
gptkb:Fortran
gptkb:C++
C
|
gptkbp:usedFor
|
general-purpose computing on GPUs
|
gptkbp:bfsParent
|
gptkb:CUDA_Toolkit
|
gptkbp:bfsLayer
|
7
|