GPU inference

[Gayathri_Sankaran]

Hi ,

I was trying to run the yolox build for openvino.

https://github.com/Megvii-BaseDetection/YOLOX/blob/main/demo/OpenVINO/cpp/yolox_openvino.cpp

The build was completed and tried to infer the model in GPU of the device. Getting error in this stage.

Was compiled in openvino - 2022.3.1-9227-cf2c7da5689-releases/2022/3

both CPU and GPU inferencing was fine.

Build system info:

Processor 13th Gen Intel(R) Core(TM) i7-13800H, 2500 Mhz, 14 Core(s), 20 Logical Processor(s)

Intel UHD graphics

when I try to run the windows application in the system with processor Intel(R) Core(TM) i3-6100U CPU @ 2.30GHz, 2304 Mhz, 2 Core(s), 4 Logical Processor(s) with Intel HD graphics, GPU inferencing is not possible stating the following error:

1 error generated.

8:3274:2: error: implicit declaration of function 'intel_sub_group_block_write_us' is invalid in OpenCL

8:3205:46: note: expanded from macro 'OUTPUT_BLOCK_WRITE'

8:290:2: note: expanded from macro 'BLOCK_WRITEN'

8:284:2: note: expanded from macro 'BLOCK_WRITEN_RAW'

The openvino version in the run system - 2022.3.0-9052-9752fafe8eb-releases/2022/3

[Aznie_Intel]

Hi Gayathri_Sankar an,

Thanks for reaching out.

The error is related to OpenCL kernel. The Intel® Core™ i3-6100U Processor GPU does not support OpenCL. Meanwhile, Intel® Core™ i7-13800H Processor GPU supporting OpenCL.

Regards,

Aznie

[Aznie_Intel]

Hi Gayathri_Sankaran,

This thread will no longer be monitored since we have provided information. If you need any additional information from Intel, please submit a new question.

Regards,

Aznie