cuda-samples
cuda-samples copied to clipboard
simpleGL could not be run from docker container in DGX2
Hi,
I am trying to run simpleGL sample inside docker container running on DGX2 machine with CUDA version 10.2. However, I get this error.
May I know what is the possible cause of this error?
I managed to compile the code by removing line 322 (about --threads) and removing '80 85' in line 301 and 302 in the Makefile. I am using this docker image nvcr.io/nvidia/pytorch:20.02-py3
# ./simpleGL
simpleGL (VBO) starting...
GPU Device 0: "Volta" with compute capability 7.0
CUDA error at simpleGL.cu:421 code=304(cudaErrorOperatingSystem) "cudaGraphicsGLRegisterBuffer(vbo_res, *vbo, vbo_res_flags)"
CUDA error at simpleGL.cu:433 code=400(cudaErrorInvalidResourceHandle) "cudaGraphicsUnregisterResource(vbo_res)"
Thanks!