search

openvinotoolkit / openvino

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
https://docs.openvino.ai
Apache License 2.0
6.57k stars 2.12k forks source link

[Bug] 11th gen iGPU hangs on simple model #4969

Closed dmenig closed 3 years ago

dmenig commented 3 years ago
System information (version)
Detailed description

Openvino code hangs on this hardware using the iGPU, but it works with the CPU, on a very common model.

Steps to reproduce

First run this to export the onnx model.

import torch
import torchvision.models as models

dummy_input = torch.randn(1, 3, 224, 224)
model = models.resnet18()

with torch.no_grad();
    torch.onnx.export(
        model,
        dummy_input,
        "resnet.onnx",
        verbose=True,
    )

Then I enter the official container for openvino : docker run --name openvino -it --device /dev/dri:/dev/dri --device-cgroup-rule='c 189:* rmw' -v /dev/bus/usb:/dev/bus/usb --rm openvino/ubuntu20_dev:latest

Then I run the conversion script : 

cd /opt/intel/openvino_2021.2.185/deployment_tools/model_optimizer
python3 mo.py --input_model /home/openvino/resnet.onnx  --output_dir /home/openvino/ --data_type FP16

Then simply loading the model hangs : 

from openvino.inference_engine import IECore

model_bin = "resnet.bin"
# Loading the Inference Engine API
ie = IECore()
ie.available_devices
# Loading IR files
net = ie.read_network(model="resnet.xml", weights=model_bin)
# Loading the network to the inference engine
exec_net = ie.load_network(network=net, device_name="GPU")
** and it hangs here **

I verified that the same code works with CPU, or that it works with another iGPU (i3-7200U).

Although such a script still shows the GPU is available : 

>>> from openvino.inference_engine import IECore
>>> 
>>> # Loading the Inference Engine API
>>> ie = IECore()
>>> ie.available_devices
[E:] [BSL] found 0 ioexpander device
['CPU', 'GNA', 'GPU']
dmenig commented 3 years ago

To give another use case, maybe easier to reproduce : When I run this

docker run -it -u 0 --device /dev/dri:/dev/dri --device-cgroup-rule='c 189:* rmw' -v /dev/bus/usb:/dev/bus/usb --rm openvino/ubuntu20_dev:latest 
/bin/bash -c "apt update && apt install sudo && deployment_tools/demo/demo_security_barrier_camera.sh -d GPU -sample-options -no_show"

It eventually hangs here : 

[ 92%] Building CXX object security_barrier_camera_demo/cpp/CMakeFiles/security_barrier_camera_demo.dir/main.cpp.o
[100%] Linking CXX executable ../../intel64/Release/security_barrier_camera_demo
[100%] Built target security_barrier_camera_demo

###################################################

Run Inference Engine security_barrier_camera demo

Run ./security_barrier_camera_demo -d GPU -d_va GPU -d_lpr GPU -i /opt/intel/openvino_2021.3.394/deployment_tools/demo/car_1.bmp -m /root/openvino_models/ir/intel/vehicle-license-plate-detection-barrier-0106/FP16/vehicle-license-plate-detection-barrier-0106.xml -m_lpr /root/openvino_models/ir/intel/license-plate-recognition-barrier-0001/FP16/license-plate-recognition-barrier-0001.xml -m_va /root/openvino_models/ir/intel/vehicle-attributes-recognition-barrier-0039/FP16/vehicle-attributes-recognition-barrier-0039.xml -no_show

[ INFO ] InferenceEngine:       API version ......... 2.1
        Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Files were added: 1
[ INFO ]     /opt/intel/openvino_2021.3.394/deployment_tools/demo/car_1.bmp
[ INFO ] Loading device GPU
[ INFO ]        GPU
        clDNNPlugin version ......... 2.1
        Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading detection model to the GPU plugin
*** hangs ***
dmenig commented 3 years ago

When it hangs, one cpu core is constantly at 100% and a process named "tracker-miner-fs" seems to be responsible.

zulkifli-halim commented 3 years ago

Your host system is Ubuntu 20, please follow the Configuration Guide for the Intel® Graphics Compute Runtime for OpenCL™ on Ubuntu* 20.04..

Intel® Graphics Compute Runtime for OpenCL™ driver components are required to use a GPU plugin and write custom layers for Intel® Integrated Graphics. The driver is installed in the OpenVINO™ Docker image but you need to activate it in the container for a non-root user if you have Ubuntu 20.04 on your host. To access GPU capabilities, you need to have correct permissions on the host and Docker container.

dmenig commented 3 years ago

Are you sure ? The code snippets I used do work on Ubuntu 20 for intel GPU coming with i3-7200U.

dmenig commented 3 years ago

Anyways I have tried the first method on the page you linked : 

docker run -it --rm --device /dev/dri --group-add=$(stat -c "%g" /dev/dri/render*) openvino/ubuntu20_dev:latest

It doesn't work : it prints this : 

groups: cannot find name for group ID 109
[setupvars.sh] OpenVINO environment initialized
openvino@1816ceaf7710:/opt/intel/openvino_2021.3.394$

And then same hanging problem on the scripts mentionned above.

dmenig commented 3 years ago

Using the second method at least works but doesn't solve the hanging problem.

veesion@slartibartfast:~$ docker run -it --rm --user root --device /dev/dri --name openvino openvino/ubuntu20_dev:latest
[setupvars.sh] OpenVINO environment initialized                                                      
root@c8786dcda200:/opt/intel/openvino_2021.3.394# ls -l /dev/dri/      
total 0                                      
crw-rw---- 1 root video 226,   0 Mar 30 11:33 card0
crw-rw---- 1 root   109 226, 128 Mar 30 11:33 renderD128
root@c8786dcda200:/opt/intel/openvino_2021.3.394# addgroup --gid 109 render                           
addgroup: The group `render' already exists.
root@c8786dcda200:/opt/intel/openvino_2021.3.394# delgroup render                                                                                                                                          Removing group `render' ...                      
Done.                                                                                                                                                                                                      
root@c8786dcda200:/opt/intel/openvino_2021.3.394# addgroup --gid 109 render                           
Adding group `render' (GID 109) ...                                                                  
Done.                           
root@c8786dcda200:/opt/intel/openvino_2021.3.394# ls -l /dev/dri/                                     
total 0             
crw-rw---- 1 root video  226,   0 Mar 30 11:33 card0                  
crw-rw---- 1 root render 226, 128 Mar 30 11:33 renderD128
root@c8786dcda200:/opt/intel/openvino_2021.3.394# usermod -a -G render openvino
root@c8786dcda200:/opt/intel/openvino_2021.3.394# id openvino
uid=1000(openvino) gid=1000(openvino) groups=1000(openvino),44(video),100(users),109(render)
root@c8786dcda200:/opt/intel/openvino_2021.3.394# su openvino
[setupvars.sh] OpenVINO environment initialized

And then same hanging problem on the scripts mentionned above.

zulkifli-halim commented 3 years ago

Have you test the demo on OpenVINO with iGPU on regular OpenVINO installation or test it without using Docker?

dmenig commented 3 years ago

Have you test the demo on OpenVINO with iGPU on regular OpenVINO installation or test it without using Docker?

I only tested with docker.

dmenig commented 3 years ago

I tried installing openvino myself after your message following these steps https://docs.openvinotoolkit.org/latest/openvino_docs_install_guides_installing_openvino_apt.html Then the "Steps for Intel® Processor Graphics (GPU)" in here https://docs.openvinotoolkit.org/latest/openvino_docs_install_guides_installing_openvino_linux.html

GPU is properly listed in available devices aftewards. But I still have the same hang problem.

dmenig commented 3 years ago

I also tried building from source with this cmake command 

cmake -DCMAKE_BUILD_TYPE=Release -DENABLE_MKL_DNN=OFF -DENABLE_CLDNN=ON   -DENABLE_NGRAPH=ON \
  -DENABLE_OPENCV=OFF  -DENABLE_PYTHON=ON -DPYTHON_EXECUTABLE=/usr/bin/python3 \
  -DPYTHON_LIBRARY=/usr/lib/x86_64-linux-gnu/libpython3.8.so -DPYTHON_INCLUDE_DIR=/usr/include/python3.8  ..

It succeeds and shows GPU in available devices in python, but still the same hanging problem.

jgespino commented 3 years ago

Hi @hyperfraise

Which GPU driver version are you on? You can check using clinfo.

Using your provided instructions, I was able to generate the onnx model, convert to IR and run on GPU device (9th gen). It may be specific to 11th gen, could you try to install this version 20.41.18123 and see if it works?

Regards, Jesus

dmenig commented 3 years ago

Hi. This is the initial output of clinfo : 

Number of platforms                               1
  Platform Name                                   Intel(R) OpenCL HD Graphics
  Platform Vendor                                 Intel(R) Corporation
  Platform Version                                OpenCL 2.1 
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_depth_images cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_image2d_from_buffer cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_media_block_io cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_khr_subgroups cl_khr_il_program cl_intel_spirv_device_side_avc_motion_estimation cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_unified_shared_memory_preview cl_intel_planar_yuv cl_intel_packed_yuv cl_intel_va_api_media_sharing 
  Platform Host timer resolution                  1ns
  Platform Extensions function suffix             INTEL

  Platform Name                                   Intel(R) OpenCL HD Graphics
Number of devices                                 1
  Device Name                                     Intel(R) Gen12LP HD Graphics NEO
  Device Vendor                                   Intel(R) Corporation
  Device Vendor ID                                0x8086
  Device Version                                  OpenCL 2.1 NEO 
  Driver Version                                  19.41.14441
  Device OpenCL C Version                         OpenCL C 2.0 
  Device Type                                     GPU
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               48
  Max clock frequency                             1250MHz
  Device Partition                                (core)
    Max number of sub-devices                     0
    Supported partition types                     None
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             512x512x512
  Max work group size                             512
  Preferred work group size multiple              32
  Max sub-groups per work group                   64
  Sub-group sizes (Intel)                         8, 16, 32
  Preferred / native vector sizes                 
    char                                                16 / 16      
    short                                                8 / 8       
    int                                                  4 / 4       
    long                                                 1 / 1       
    half                                                 8 / 8        (cl_khr_fp16)
    float                                                1 / 1       
    double                                               1 / 1        (n/a)
  Half-precision Floating-point support           (cl_khr_fp16)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
  Single-precision Floating-point support         (core)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
    Correctly-rounded divide and sqrt operations  No
  Double-precision Floating-point support         (n/a)
  Address bits                                    64, Little-Endian
  Global memory size                              19946344448 (18.58GiB)
  Error Correction support                        No
  Max memory allocation                           4294959104 (4GiB)
  Unified memory for Host and Device              Yes
  Shared Virtual Memory (SVM) capabilities        (core)
    Coarse-grained buffer sharing                 Yes
    Fine-grained buffer sharing                   No
    Fine-grained system sharing                   No
    Atomics                                       No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Preferred alignment for atomics                 
    SVM                                           64 bytes
    Global                                        64 bytes
    Local                                         64 bytes
  Max size for global variable                    65536 (64KiB)
  Preferred total size of global vars             4294959104 (4GiB)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        524288 (512KiB)
  Global Memory cache line size                   64 bytes
  Image support                                   Yes
    Max number of samplers per kernel             16
    Max size for 1D images from buffer            268434944 pixels
    Max 1D or 2D image array size                 2048 images
    Base address alignment for 2D image buffers   4 bytes
    Pitch alignment for 2D image buffers          4 pixels
    Max 2D image size                             16384x16384 pixels
    Max planar YUV image size                     16384x16352 pixels
    Max 3D image size                             16384x16384x2048 pixels
    Max number of read image args                 128
    Max number of write image args                128
    Max number of read/write image args           128
  Max number of pipe args                         16
  Max active pipe reservations                    1
  Max pipe packet size                            1024
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Max number of constant args                     8
  Max constant buffer size                        4294959104 (4GiB)
  Max size of kernel argument                     1024
  Queue properties (on host)                      
    Out-of-order execution                        Yes
    Profiling                                     Yes
  Queue properties (on device)                    
    Out-of-order execution                        Yes
    Profiling                                     Yes
    Preferred size                                131072 (128KiB)
    Max size                                      67108864 (64MiB)
  Max queues on device                            1
  Max events on device                            1024
  Prefer user sync for interop                    Yes
  Profiling timer resolution                      52ns
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Sub-group independent forward progress        Yes
    IL version                                    SPIR-V_1.2 
    SPIR versions                                 1.2 
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                (n/a)
  Device Extensions                               cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_depth_images cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_image2d_from_buffer cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_media_block_io cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_khr_subgroups cl_khr_il_program cl_intel_spirv_device_side_avc_motion_estimation cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_unified_shared_memory_preview cl_intel_planar_yuv cl_intel_packed_yuv cl_intel_va_api_media_sharing 

NULL platform behavior
  clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  Intel(R) OpenCL HD Graphics
  clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   Success [INTEL]
  clCreateContext(NULL, ...) [default]            Success [INTEL]
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen12LP HD Graphics NEO
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen12LP HD Graphics NEO
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen12LP HD Graphics NEO

ICD loader properties
  ICD loader Name                                 OpenCL ICD Loader
  ICD loader Vendor                               OCL Icd free software
  ICD loader Version                              2.2.11
  ICD loader Profile                              OpenCL 2.1

After doing the steps over on your link, this is what clinfo prints : 

Number of platforms                               1
  Platform Name                                   Intel(R) OpenCL HD Graphics
  Platform Vendor                                 Intel(R) Corporation
  Platform Version                                OpenCL 3.0 
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_intel_subgroups_char cl_intel_subgroups_long cl_khr_il_program cl_intel_mem_force_host_memory cl_khr_subgroup_extended_types cl_khr_subgroup_non_uniform_vote cl_khr_subgroup_ballot cl_khr_subgroup_non_uniform_arithmetic cl_khr_subgroup_shuffle cl_khr_subgroup_shuffle_relative cl_khr_subgroup_clustered_reduce cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_intel_unified_shared_memory_preview cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_planar_yuv cl_intel_packed_yuv cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_image2d_from_buffer cl_khr_depth_images cl_intel_media_block_io cl_khr_3d_image_writes cl_intel_va_api_media_sharing cl_intel_subgroup_local_block_io 
  Platform Host timer resolution                  1ns
  Platform Extensions function suffix             INTEL

  Platform Name                                   Intel(R) OpenCL HD Graphics
Number of devices                                 1
  Device Name                                     Intel(R) Gen12LP HD Graphics NEO
  Device Vendor                                   Intel(R) Corporation
  Device Vendor ID                                0x8086
  Device Version                                  OpenCL 3.0 NEO 
  Driver Version                                  20.41.18123
  Device OpenCL C Version                         OpenCL C 1.2 
  Device Type                                     GPU
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               48
  Max clock frequency                             1250MHz
  Device Partition                                (core)
    Max number of sub-devices                     0
    Supported partition types                     None
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             512x512x512
  Max work group size                             512
  Preferred work group size multiple              64
  Max sub-groups per work group                   64
  Sub-group sizes (Intel)                         8, 16, 32
  Preferred / native vector sizes                 
    char                                                16 / 16      
    short                                                8 / 8       
    int                                                  4 / 4       
    long                                                 1 / 1       
    half                                                 8 / 8        (cl_khr_fp16)
    float                                                1 / 1       
    double                                               1 / 1        (n/a)
  Half-precision Floating-point support           (cl_khr_fp16)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
  Single-precision Floating-point support         (core)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
    Correctly-rounded divide and sqrt operations  No
  Double-precision Floating-point support         (n/a)
  Address bits                                    64, Little-Endian
  Global memory size                              19946344448 (18.58GiB)
  Error Correction support                        No
  Max memory allocation                           4294959104 (4GiB)
  Unified memory for Host and Device              Yes
  Shared Virtual Memory (SVM) capabilities        (core)
    Coarse-grained buffer sharing                 Yes
    Fine-grained buffer sharing                   No
    Fine-grained system sharing                   No
    Atomics                                       No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Preferred alignment for atomics                 
    SVM                                           64 bytes
    Global                                        64 bytes
    Local                                         64 bytes
  Max size for global variable                    65536 (64KiB)
  Preferred total size of global vars             4294959104 (4GiB)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        524288 (512KiB)
  Global Memory cache line size                   64 bytes
  Image support                                   Yes
    Max number of samplers per kernel             16
    Max size for 1D images from buffer            268434944 pixels
    Max 1D or 2D image array size                 2048 images
    Base address alignment for 2D image buffers   4 bytes
    Pitch alignment for 2D image buffers          4 pixels
    Max 2D image size                             16384x16384 pixels
    Max planar YUV image size                     16384x16352 pixels
    Max 3D image size                             2048x2048x2048 pixels
    Max number of read image args                 128
    Max number of write image args                128
    Max number of read/write image args           128
  Max number of pipe args                         0
  Max active pipe reservations                    0
  Max pipe packet size                            0
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Max number of constant args                     8
  Max constant buffer size                        4294959104 (4GiB)
  Max size of kernel argument                     2048 (2KiB)
  Queue properties (on host)                      
    Out-of-order execution                        Yes
    Profiling                                     Yes
  Queue properties (on device)                    
    Out-of-order execution                        No
    Profiling                                     No
    Preferred size                                0
    Max size                                      0
  Max queues on device                            0
  Max events on device                            0
  Prefer user sync for interop                    Yes
  Profiling timer resolution                      52ns
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Sub-group independent forward progress        No
    IL version                                    SPIR-V_1.2 
    SPIR versions                                 1.2 
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                (n/a)
  Device Extensions                               cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_intel_subgroups_char cl_intel_subgroups_long cl_khr_il_program cl_intel_mem_force_host_memory cl_khr_subgroup_extended_types cl_khr_subgroup_non_uniform_vote cl_khr_subgroup_ballot cl_khr_subgroup_non_uniform_arithmetic cl_khr_subgroup_shuffle cl_khr_subgroup_shuffle_relative cl_khr_subgroup_clustered_reduce cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_intel_unified_shared_memory_preview cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_planar_yuv cl_intel_packed_yuv cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_image2d_from_buffer cl_khr_depth_images cl_intel_media_block_io cl_khr_3d_image_writes cl_intel_va_api_media_sharing cl_intel_subgroup_local_block_io 

NULL platform behavior
  clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  Intel(R) OpenCL HD Graphics
  clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   Success [INTEL]
  clCreateContext(NULL, ...) [default]            Success [INTEL]
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen12LP HD Graphics NEO
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen12LP HD Graphics NEO
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen12LP HD Graphics NEO

ICD loader properties
  ICD loader Name                                 OpenCL ICD Loader
  ICD loader Vendor                               OCL Icd free software
  ICD loader Version                              2.2.11
  ICD loader Profile                              OpenCL 2.1
    NOTE:   your OpenCL library only supports OpenCL 2.1,
        but some installed platforms support OpenCL 3.0.
        Programs using 3.0 features may crash
        or behave unexpectedly

I conclude that I updated the driver successfully. This solves the hanging problem as well (although I'm noting that the loading of the model in iGPU memory is very slow : ~2m30s).

If I may say, I believe that this incompatibility should be listed somewhere ? Or at least there should be some indication anywhere on Openvino's docs that this driver should be the most recent one, idk.

Thank you very much !

jgespino commented 3 years ago

@hyperfraise

This solves the hanging problem as well (although I'm noting that the loading of the model in iGPU memory is very slow : ~2m30s).

Was the loading time similar on the previous driver? Take a look at this support article on how to load model from cache.

Regards, Jesus

dmenig commented 3 years ago

As noted above, there couldn'tbe any loading on the previous driver : just hanging.

jgespino commented 3 years ago

@hyperfraise oh yes.... my mistake. Loading on GPU will take a bit longer as the kernel compiles, the article mentioned in my previous response should help when reloading the model after the first time.