2.1 KiB
cudaNvSciBufMultiplanar - CUDA NvSciBufMultiplanar Image Samples
Description
This sample demonstrates CUDA-NvSciBuf Interop for Multiplanar images. A YUV 420 multiplanar image is flipped and allocated using NvSciBuf APIs and imported into CUDA with CUDA External Resource Interoperability. A CUDA surface is created from the corresponding mapped CUDA array and again bit flipping is performed on the surface. The result is copied back to a YUV image which is compared against the input.
Key Concepts
CUDA NvSci Interop, Data Parallel Algorithms, Image Processing
Supported SM Architectures
SM 6.0 SM 6.1 SM 7.0 SM 7.2 SM 7.5 SM 8.0 SM 8.6 SM 8.7 SM 8.9 SM 9.0 SM 10.0 SM 10.1 SM 12.0
Supported OSes
Linux
Supported CPU Architecture
aarch64
CUDA APIs involved
CUDA Runtime API
cudaDeviceGetAttribute, cudaNvSciBufMultiplanar, cudaDestroyExternalMemory, cuDriverGetVersion, cuDeviceGetUuid, cudaSetDevice, cudaGetMipmappedArrayLevel, cudaFreeMipmappedArray, cudaImportExternalMemory, cudaCreateChannelDesc, cudaExternalMemoryGetMappedMipmappedArray, cuCtxSynchronize, cudaMemcpy2DToArray, cudaMemcpy2DFromArray
Dependencies needed to build/run
Prerequisites
Download and install the CUDA Toolkit 12.8 for your corresponding platform. Make sure the dependencies mentioned in Dependencies section above are installed.