Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Takeru_T_Intel
Employee
213 Views

classification_sample_async.exe is not working with GPU (Gen6 Core)

Jump to solution

I cannot run classification_sample_async.exe due to error.

Does this error come from OpenCL or Inference Engine ?

[command]

C:\Intel\computer_vision_sdk_2018.3.343\inference_engine\bin\intel64\Release>classification_sample_async.exe -i C:\Users\ttsuchiy\Projects\imagenet\ILSVRC2012_img_val_100 -m C:\Intel\computer_vision_sdk_2018.3.343\deployment_tools\model_downloader\classification\googlenet\v1\caffe\FP16\googlenet-v1.xml -d GPU

[Error Messages]

[ INFO ] Loading plugin
 
        API version ............ 1.2
        Build .................. cldnn/GEN_GPU_clDNN_ci-main_cldnn-main-03988_artifacts.zip
        Description ....... clDNNPlugin
 
...........................
 
[ INFO ] Batch size is 100
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the plugin
[ ERROR ] failed to create engine: No OpenCL device found which would match provided configuration:
    Intel(R) Core(TM) i5-6300U CPU @ 2.40GHz: invalid device type
0 Kudos
1 Solution
nikos1
Valued Contributor I
213 Views

Seems that somehow the GPU OpenCL device ( the HD Graphics 520 in your Core(TM) i5-6300U CPU )  does not get properly detected and only the CPU OpenCL device is detected hence the invalid device type.

What is the output of clinfo or gpu caps viewer?  Can you see the GPU OpenCL device?  Can you see the Intel GPU in Device manager / Display Adapters?

If not try re-installing graphics drivers or in some cases a simple reboot can fix the issues.

If you also have a discrete GPU in the system try to reboot with monitor connected to the system DVI/HDMI/DP connector. In some cases you may enable igfx from BIOS too. 

 

 

 

View solution in original post

5 Replies
nikos1
Valued Contributor I
214 Views

Seems that somehow the GPU OpenCL device ( the HD Graphics 520 in your Core(TM) i5-6300U CPU )  does not get properly detected and only the CPU OpenCL device is detected hence the invalid device type.

What is the output of clinfo or gpu caps viewer?  Can you see the GPU OpenCL device?  Can you see the Intel GPU in Device manager / Display Adapters?

If not try re-installing graphics drivers or in some cases a simple reboot can fix the issues.

If you also have a discrete GPU in the system try to reboot with monitor connected to the system DVI/HDMI/DP connector. In some cases you may enable igfx from BIOS too. 

 

 

 

View solution in original post

Takeru_T_Intel
Employee
213 Views

Thank you, Nikos

It looks OpenCL installation issue on my system (Windows10) by your advice. 

I'm use the latest igfx driver and it can be detected on Device manager/Display Adapters. 

I captured gpu cap viewer and clinfo result.   I'll try to fix issue but your advice is 

 

gpucapsviewer.jpg

 

Number of platforms:                             3
  Platform Profile:                              FULL_PROFILE
  Platform Version:                              OpenCL 2.0
  Platform Name:                                 Intel(R) OpenCL
  Platform Vendor:                               Intel(R) Corporation
  Platform Extensions:                           cl_khr_icd cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_intel_exec_by_local_thread cl_khr_spir cl_khr_dx9_media_sharing cl_intel_dx9_media_sharing cl_khr_d3d11_sharing cl_khr_gl_sharing cl_khr_fp64 cl_khr_image2d_from_buffer
  Platform Profile:                              FULL_PROFILE
  Platform Version:                              OpenCL 2.0
  Platform Name:                                 Intel(R) OpenCL
  Platform Vendor:                               Intel(R) Corporation
  Platform Extensions:                           cl_khr_icd cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_intel_exec_by_local_thread cl_khr_spir cl_khr_dx9_media_sharing cl_intel_dx9_media_sharing cl_khr_d3d11_sharing cl_khr_gl_sharing cl_khr_fp64 cl_khr_image2d_from_buffer
  Platform Profile:                              FULL_PROFILE
  Platform Version:                              OpenCL 2.1
  Platform Name:                                 Experimental OpenCL 2.1 CPU Only Platform
  Platform Vendor:                               Intel(R) Corporation
  Platform Extensions:                           cl_khr_icd cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_intel_exec_by_local_thread cl_khr_spir cl_khr_dx9_media_sharing cl_intel_dx9_media_sharing cl_khr_d3d11_sharing cl_khr_gl_sharing cl_khr_fp64 cl_khr_image2d_from_buffer
 
 
  Platform Name:                                 Intel(R) OpenCL
Number of devices:                               1
  Device Type:                                   CL_DEVICE_TYPE_CPU
  Device ID:                                     32902
  Max compute units:                             4
  Max work items dimensions:                     3
    Max work items[0]:                           8192
    Max work items[1]:                           8192
    Max work items[2]:                           8192
  Max work group size:                           8192
  Preferred vector width char:                   1
  Preferred vector width short:                  1
  Preferred vector width int:                    1
  Preferred vector width long:                   1
  Preferred vector width float:                  1
  Preferred vector width double:                 1
  Max clock frequency:                           2400Mhz
  Address bits:                                  14757395255531667488
  Max memory allocation:                         536838144
  Image support:                                 Yes
  Max number of images read arguments:           480
  Max number of images write arguments:          480
  Max image 2D width:                            16384
  Max image 2D height:                           16384
  Max image 3D width:                            2048
  Max image 3D height:                           2048
  Max image 3D depth:                            2048
  Max samplers within kernel:                    480
  Max size of kernel argument:                   3840
  Alignment (bits) of base address:              1024
  Minimum alignment (bytes) for any datatype:    128
  Single precision floating point capability
    Denorms:                                     Yes
    Quiet NaNs:                                  Yes
    Round to nearest even:                       Yes
    Round to zero:                               No
    Round to +ve and infinity:                   No
    IEEE754-2008 fused multiply-add:             No
  Cache type:                                    Read/Write
  Cache line size:                               64
  Cache size:                                    262144
  Global memory size:                            536838144
  Constant buffer size:                          131072
  Max number of constant args:                   480
  Local memory type:                             Global
  Local memory size:                             32768
  Error correction support:                      0
  Profiling timer resolution:                    410
  Device endianess:                              Little
  Available:                                     Yes
  Compiler available:                            Yes
  Execution capabilities:
    Execute OpenCL kernels:                      Yes
    Execute native function:                     Yes
  Queue properties:
    Out-of-Order:                                Yes
    Profiling :                                  Yes
  Platform ID:                                   02F174A0
  Name:                                          Intel(R) Core(TM) i5-6300U CPU @ 2.40GHz
  Vendor:                                        Intel(R) Corporation
  Driver version:                                7.2.0.10
  Profile:                                       FULL_PROFILE
  Version:                                       OpenCL 2.0 (Build 10)
  Extensions:                                    cl_khr_icd cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_intel_exec_by_local_thread cl_khr_spir cl_khr_dx9_media_sharing cl_intel_dx9_media_sharing cl_khr_d3d11_sharing cl_khr_gl_sharing cl_khr_fp64 cl_khr_image2d_from_buffer
 
 
  Platform Name:                                 Intel(R) OpenCL
Number of devices:                               1
  Device Type:                                   CL_DEVICE_TYPE_CPU
  Device ID:                                     32902
  Max compute units:                             4
  Max work items dimensions:                     3
    Max work items[0]:                           8192
    Max work items[1]:                           8192
    Max work items[2]:                           8192
  Max work group size:                           8192
  Preferred vector width char:                   1
  Preferred vector width short:                  1
  Preferred vector width int:                    1
  Preferred vector width long:                   1
  Preferred vector width float:                  1
  Preferred vector width double:                 1
  Max clock frequency:                           2400Mhz
  Address bits:                                  14757395255531667488
  Max memory allocation:                         536838144
  Image support:                                 Yes
  Max number of images read arguments:           480
  Max number of images write arguments:          480
  Max image 2D width:                            16384
  Max image 2D height:                           16384
  Max image 3D width:                            2048
  Max image 3D height:                           2048
  Max image 3D depth:                            2048
  Max samplers within kernel:                    480
  Max size of kernel argument:                   3840
  Alignment (bits) of base address:              1024
  Minimum alignment (bytes) for any datatype:    128
  Single precision floating point capability
    Denorms:                                     Yes
    Quiet NaNs:                                  Yes
    Round to nearest even:                       Yes
    Round to zero:                               No
    Round to +ve and infinity:                   No
    IEEE754-2008 fused multiply-add:             No
  Cache type:                                    Read/Write
  Cache line size:                               64
  Cache size:                                    262144
  Global memory size:                            536838144
  Constant buffer size:                          131072
  Max number of constant args:                   480
  Local memory type:                             Global
  Local memory size:                             32768
  Error correction support:                      0
  Profiling timer resolution:                    410
  Device endianess:                              Little
  Available:                                     Yes
  Compiler available:                            Yes
  Execution capabilities:
    Execute OpenCL kernels:                      Yes
    Execute native function:                     Yes
  Queue properties:
    Out-of-Order:                                Yes
    Profiling :                                  Yes
  Platform ID:                                   02F174A0
  Name:                                          Intel(R) Core(TM) i5-6300U CPU @ 2.40GHz
  Vendor:                                        Intel(R) Corporation
  Driver version:                                7.2.0.10
  Profile:                                       FULL_PROFILE
  Version:                                       OpenCL 2.0 (Build 10)
  Extensions:                                    cl_khr_icd cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_intel_exec_by_local_thread cl_khr_spir cl_khr_dx9_media_sharing cl_intel_dx9_media_sharing cl_khr_d3d11_sharing cl_khr_gl_sharing cl_khr_fp64 cl_khr_image2d_from_buffer
 
 
  Platform Name:                                 Experimental OpenCL 2.1 CPU Only Platform
Number of devices:                               1
  Device Type:                                   CL_DEVICE_TYPE_CPU
  Device ID:                                     32902
  Max compute units:                             4
  Max work items dimensions:                     3
    Max work items[0]:                           8192
    Max work items[1]:                           8192
    Max work items[2]:                           8192
  Max work group size:                           8192
  Preferred vector width char:                   1
  Preferred vector width short:                  1
  Preferred vector width int:                    1
  Preferred vector width long:                   1
  Preferred vector width float:                  1
  Preferred vector width double:                 1
  Max clock frequency:                           2400Mhz
  Address bits:                                  14757395255531667488
  Max memory allocation:                         536838144
  Image support:                                 Yes
  Max number of images read arguments:           480
  Max number of images write arguments:          480
  Max image 2D width:                            16384
  Max image 2D height:                           16384
  Max image 3D width:                            2048
  Max image 3D height:                           2048
  Max image 3D depth:                            2048
  Max samplers within kernel:                    480
  Max size of kernel argument:                   3840
  Alignment (bits) of base address:              1024
  Minimum alignment (bytes) for any datatype:    128
  Single precision floating point capability
    Denorms:                                     Yes
    Quiet NaNs:                                  Yes
    Round to nearest even:                       Yes
    Round to zero:                               No
    Round to +ve and infinity:                   No
    IEEE754-2008 fused multiply-add:             No
  Cache type:                                    Read/Write
  Cache line size:                               64
  Cache size:                                    262144
  Global memory size:                            536838144
  Constant buffer size:                          131072
  Max number of constant args:                   480
  Local memory type:                             Global
  Local memory size:                             32768
  Error correction support:                      0
  Profiling timer resolution:                    410
  Device endianess:                              Little
  Available:                                     Yes
  Compiler available:                            Yes
  Execution capabilities:
    Execute OpenCL kernels:                      Yes
    Execute native function:                     Yes
  Queue properties:
    Out-of-Order:                                Yes
    Profiling :                                  Yes
  Platform ID:                                   02F57D80
  Name:                                          Intel(R) Core(TM) i5-6300U CPU @ 2.40GHz
  Vendor:                                        Intel(R) Corporation
  Driver version:                                7.0.0.2567
  Profile:                                       FULL_PROFILE
  Version:                                       OpenCL 2.1 (Build 10)
  Extensions:                                    cl_khr_icd cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_intel_exec_by_local_thread cl_khr_spir cl_khr_dx9_media_sharing cl_intel_dx9_media_sharing cl_khr_d3d11_sharing cl_khr_gl_sharing cl_khr_fp64 cl_khr_image2d_from_buffer
nikos1
Valued Contributor I
213 Views

You are welcome!

Right, I can only see CL_DEVICE_TYPE_CPU in clifno. Once you get CL_DEVICE_TYPE_GPU you should have no issues with -D GPU. Good luck!

Takeru_T_Intel
Employee
213 Views

Nikos

I referred similar issue and fix.  

https://communities.intel.com/thread/119639

OpenCL could be enabled on GPU by removed igfx driver and slightly older driver (21.20.16.4678)

Confirmed Inference Engine is working very well on GPU - Intel HD Graphics 520 with sample code.

Thanks a lot.

 

 

nikos1
Valued Contributor I
213 Views
Tsuchiya-san, you are welcome.
Glad to heat it works well on your GPU.
Best regards, 
Nikos
Reply