2.5 KiB
EGLStream_CUDA_CrossGPU - EGLStream_CUDA_CrossGPU
Description
Demonstrates CUDA and EGL Streams interop between separate consumer and producer processes. By default, both processes use the same GPU. Use -crossdev to place the consumer on a discrete GPU and the producer on an integrated GPU.
The consumer adds its process ID to the Unix socket name and passes the path to the producer. Each process pair uses a separate socket, so multiple sample instances can run at the same time.
Key Concepts
EGLStreams Interop
Supported SM Architectures
SM 5.0 SM 5.2 SM 5.3 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
Supported OSes
Linux
Supported CPU Architecture
x86_64, armv7l
CUDA APIs involved
CUDA Driver API
cuDeviceGetName, cuEGLStreamConsumerReleaseFrame, cuEGLStreamConsumerConnect, cuEGLStreamConsumerDisconnect, cuCtxPushCurrent, cuEGLStreamProducerReturnFrame, cuStreamCreate, cuEGLStreamProducerPresentFrame, cuMemFree, cuGraphicsResourceGetMappedEglFrame, cuInit, cuMemcpyHtoD, cuDeviceGet, cuEGLStreamConsumerAcquireFrame, cuEGLStreamProducerDisconnect, cuEGLStreamProducerConnect, cuDeviceGetAttribute, cuCtxSynchronize, cuMemAlloc, cuCtxPopCurrent, cuCtxCreate
CUDA Runtime API
cudaMemcpy, cudaMalloc, cudaProducerPresentFrame, cudaFree, cudaGetErrorString, cudaConsumerReleaseFrame, cudaProducerReturnFrame, cudaDeviceSynchronize, cudaDeviceCreateProducer, cudaProducerDeinit, cudaProducerPrepareFrame, cudaGetValueMismatch, cudaConsumerAcquireFrame, cudaProducerInit, cudaDeviceCreateConsumer
Dependencies needed to build/run
Prerequisites
Download and install the CUDA Toolkit for your corresponding platform. Make sure the dependencies mentioned in Dependencies section above are installed.