cuda-samples/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU
2023-11-09 16:52:00 +00:00
..
.vscode add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
cuda_consumer.cpp add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
cuda_consumer.h add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
cuda_producer.cpp add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
cuda_producer.h add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
eglstrm_common.cpp add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
eglstrm_common.h add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
findegl.mk Update samples for CUDA 11.8 with correct props 2022-10-14 17:43:37 -07:00
helper.h add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
kernel.cu add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
main.cpp add and update samples for CUDA 11.6 2022-01-13 11:35:24 +05:30
Makefile Changelog updates 2023-06-29 19:33:40 +00:00
NsightEclipse.xml Updating files for Ada architecture 2023-02-27 22:33:19 +00:00
README.md Fixing jitlto regression, including missing cuDLA source files for bug #235, and updating changelogs 2023-11-09 16:52:00 +00:00

EGLStream_CUDA_CrossGPU - EGLStream_CUDA_CrossGPU

Description

Demonstrates CUDA and EGL Streams interop, where consumer's EGL Stream is on one GPU and producer's on other and both consumer-producer are different processes.

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

EGL

Prerequisites

Download and install the CUDA Toolkit 12.3 for your corresponding platform. Make sure the dependencies mentioned in Dependencies section above are installed.

Build and Run

Linux

The Linux samples are built using makefiles. To use the makefiles, change the current directory to the sample directory you wish to build, and run make:

$ cd <sample_dir>
$ make

The samples makefiles can take advantage of certain options:

  • TARGET_ARCH= - cross-compile targeting a specific architecture. Allowed architectures are x86_64, armv7l. By default, TARGET_ARCH is set to HOST_ARCH. On a x86_64 machine, not setting TARGET_ARCH is the equivalent of setting TARGET_ARCH=x86_64.
    $ make TARGET_ARCH=x86_64
    $ make TARGET_ARCH=armv7l
    See here for more details.

  • dbg=1 - build with debug symbols

    $ make dbg=1
    
  • SMS="A B ..." - override the SM architectures for which the sample will be built, where "A B ..." is a space-delimited list of SM architectures. For example, to generate SASS for SM 50 and SM 60, use SMS="50 60".

    $ make SMS="50 60"
    
  • HOST_COMPILER=<host_compiler> - override the default g++ host compiler. See the Linux Installation Guide for a list of supported host compilers.

    $ make HOST_COMPILER=g++

References (for more details)