I'm running the benchmark app file as
python3 benchmark_app.py -m ~/model.xml -d gpu
This is the stack trace I get -
[Step 1/11] Parsing and validating input arguments [ WARNING ] -nstreams default value is determined automatically for a device. Although the automatic selection usually provides a reasonable performance, but it still may be non-optimal for some cases, for more information look at README. [Step 2/11] Loading Inference Engine [ INFO ] InferenceEngine: API version............. 2.1.37988 [ ERROR ] Failed to create plugin /opt/intel/openvino_2020.1.023/deployment_tools/inference_engine/lib/intel64/libclDNNPlugin.so for device GPU Please, check your environment [CLDNN ERROR]. clGetPlatformIDs error -1001 Traceback (most recent call last): File "benchmark_app.py", line 40, in main version = benchmark.get_version_info() File "/opt/intel/openvino_2020.1.023/python/python3.6/openvino/tools/benchmark/benchmark.py", line 52, in get_version_info for device, version in self.ie.get_versions(self.device).items(): File "ie_api.pyx", line 105, in openvino.inference_engine.ie_api.IECore.get_versions RuntimeError: Failed to create plugin /opt/intel/openvino_2020.1.023/deployment_tools/inference_engine/lib/intel64/libclDNNPlugin.so for device GPU Please, check your environment [CLDNN ERROR]. clGetPlatformIDs error -1001
My system doesn't have a dedicated GPU, I'm trying to use the Integrated GPU - Intel® HD Graphics 520 (Skylake GT2).
Before this, I already ran sudo apt-get install ocl-icd-opencl-dev to install opencl
Thanks for reaching out, did you follow the additional Steps for Intel® Processor Graphics (GPU) and source the environment variables?
If you continue to see the error, could you try to run the benchmark_app demo script as follows?
cd /opt/intel/openvino/deployment_tools/demo ./demo_benchmark_app.sh -d GPU