Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6503 Discussions

always show the error message when call get_available_devices

LuckGuySam
Beginner
‎03-06-2024 06:12 PM
1,917 Views

environment: window 10
openvino version: 2023.3

I execute the openvino sample program hello_query_device
Then I found that an error message always pops up. After pressing OK, the program can be executed smoothly, but my device does not have an NPU device.
How can I avoid pop-up error messages when querying devices?

 

error message about npuopenvino_error.png

 

device no npu

manager.png

 

 

run result

[ INFO ] Build ................................. 2023.3.0-13775-ceeafaf64f3-releases/2023/3
[ INFO ]
[ INFO ] Available devices:
[ INFO ] CPU
[ INFO ]        SUPPORTED_PROPERTIES:
[ INFO ]                Immutable: AVAILABLE_DEVICES : ""
[ INFO ]                Immutable: RANGE_FOR_ASYNC_INFER_REQUESTS : 1 1 1
[ INFO ]                Immutable: RANGE_FOR_STREAMS : 1 12
[ INFO ]                Immutable: FULL_DEVICE_NAME : Intel(R) Core(TM) i7-8750H CPU @ 2.20GHz
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : FP32 FP16 INT8 BIN EXPORT_IMPORT
[ INFO ]                Mutable: NUM_STREAMS : 1
[ INFO ]                Mutable: AFFINITY : NONE
[ INFO ]                Mutable: INFERENCE_NUM_THREADS : 0
[ INFO ]                Mutable: PERF_COUNT : NO
[ INFO ]                Mutable: INFERENCE_PRECISION_HINT : f32
[ INFO ]                Mutable: PERFORMANCE_HINT : LATENCY
[ INFO ]                Mutable: EXECUTION_MODE_HINT : PERFORMANCE
[ INFO ]                Mutable: PERFORMANCE_HINT_NUM_REQUESTS : 0
[ INFO ]                Mutable: ENABLE_CPU_PINNING : YES
[ INFO ]                Mutable: SCHEDULING_CORE_TYPE : ANY_CORE
[ INFO ]                Mutable: ENABLE_HYPER_THREADING : YES
[ INFO ]                Mutable: DEVICE_ID : ""
[ INFO ]                Mutable: CPU_DENORMALS_OPTIMIZATION : NO
[ INFO ]                Mutable: CPU_SPARSE_WEIGHTS_DECOMPRESSION_RATE : 1
[ INFO ]
[ INFO ] GNA
[ INFO ]        SUPPORTED_PROPERTIES:
[ INFO ]                Immutable: AVAILABLE_DEVICES : GNA_SW
[ INFO ]                Immutable: OPTIMAL_NUMBER_OF_INFER_REQUESTS : 1
[ INFO ]                Immutable: RANGE_FOR_ASYNC_INFER_REQUESTS : 1 1 1
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : INT16 INT8 EXPORT_IMPORT
[ INFO ]                Immutable: FULL_DEVICE_NAME : GNA_SW
[ INFO ]                Immutable: GNA_LIBRARY_FULL_VERSION : 3.5.0.2116
[ INFO ]                Mutable: GNA_DEVICE_MODE : GNA_SW_EXACT
[ INFO ]                Mutable: PERFORMANCE_HINT : LATENCY
[ INFO ]                Mutable: LOG_LEVEL : LOG_NONE
[ INFO ]                Immutable: EXECUTION_DEVICES : GNA
[ INFO ]                Mutable: GNA_SCALE_FACTOR_PER_INPUT : ""
[ INFO ]                Mutable: GNA_FIRMWARE_MODEL_IMAGE : ""
[ INFO ]                Mutable: GNA_HW_EXECUTION_TARGET : UNDEFINED
[ INFO ]                Mutable: GNA_HW_COMPILE_TARGET : UNDEFINED
[ INFO ]                Mutable: GNA_PWL_DESIGN_ALGORITHM : UNDEFINED
[ INFO ]                Mutable: GNA_PWL_MAX_ERROR_PERCENT : 1.000000
[ INFO ]                Mutable: INFERENCE_PRECISION_HINT : undefined
[ INFO ]                Mutable: EXECUTION_MODE_HINT : ACCURACY
[ INFO ]                Mutable: PERFORMANCE_HINT_NUM_REQUESTS : 1
[ INFO ]
[ INFO ] GPU.0
[ INFO ]        SUPPORTED_PROPERTIES:
[ INFO ]                Immutable: AVAILABLE_DEVICES : 0 1
[ INFO ]                Immutable: RANGE_FOR_ASYNC_INFER_REQUESTS : 1 2 1
[ INFO ]                Immutable: RANGE_FOR_STREAMS : 1 2
[ INFO ]                Immutable: OPTIMAL_BATCH_SIZE : 1
[ INFO ]                Immutable: MAX_BATCH_SIZE : 1
[ INFO ]                Immutable: DEVICE_ARCHITECTURE : GPU: vendor=0x8086 arch=Intel(R) UHD Graphics 630
[ INFO ]                Immutable: FULL_DEVICE_NAME : Intel(R) UHD Graphics 630 (iGPU)
[ INFO ]                Immutable: DEVICE_UUID : 00000000000000000000000000000000
[ INFO ]                Immutable: DEVICE_LUID : 0000000000000000
[ INFO ]                Immutable: DEVICE_TYPE : integrated
[ INFO ]                Immutable: DEVICE_GOPS : {f16:844.8,f32:422.4,i8:422.4,u8:422.4}
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : FP32 BIN FP16 EXPORT_IMPORT
[ INFO ]                Immutable: GPU_DEVICE_TOTAL_MEM_SIZE : 13696671744
[ INFO ]                Immutable: GPU_UARCH_VERSION : unknown
[ INFO ]                Immutable: GPU_EXECUTION_UNITS_COUNT : 24
[ INFO ]                Immutable: GPU_MEMORY_STATISTICS : ""
[ INFO ]                Mutable: PERF_COUNT : NO
[ INFO ]                Mutable: MODEL_PRIORITY : MEDIUM
[ INFO ]                Mutable: GPU_HOST_TASK_PRIORITY : MEDIUM
[ INFO ]                Mutable: GPU_QUEUE_PRIORITY : MEDIUM
[ INFO ]                Mutable: GPU_QUEUE_THROTTLE : MEDIUM
[ INFO ]                Mutable: GPU_ENABLE_LOOP_UNROLLING : YES
[ INFO ]                Mutable: GPU_DISABLE_WINOGRAD_CONVOLUTION : NO
[ INFO ]                Mutable: CACHE_DIR : ""
[ INFO ]                Mutable: CACHE_MODE : optimize_speed
[ INFO ]                Mutable: PERFORMANCE_HINT : LATENCY
[ INFO ]                Mutable: EXECUTION_MODE_HINT : PERFORMANCE
[ INFO ]                Mutable: COMPILATION_NUM_THREADS : 12
[ INFO ]                Mutable: NUM_STREAMS : 1
[ INFO ]                Mutable: PERFORMANCE_HINT_NUM_REQUESTS : 0
[ INFO ]                Mutable: INFERENCE_PRECISION_HINT : f16
[ INFO ]                Mutable: ENABLE_CPU_PINNING : NO
[ INFO ]                Mutable: DEVICE_ID : 0
[ INFO ]
[ INFO ] GPU.1
[ INFO ]        SUPPORTED_PROPERTIES:
[ INFO ]                Immutable: AVAILABLE_DEVICES : 0 1
[ INFO ]                Immutable: RANGE_FOR_ASYNC_INFER_REQUESTS : 1 2 1
[ INFO ]                Immutable: RANGE_FOR_STREAMS : 1 2
[ INFO ]                Immutable: OPTIMAL_BATCH_SIZE : 1
[ INFO ]                Immutable: MAX_BATCH_SIZE : 1
[ INFO ]                Immutable: DEVICE_ARCHITECTURE : GPU: vendor=0x10de arch=v6.1.0
[ INFO ]                Immutable: FULL_DEVICE_NAME : NVIDIA GeForce GTX 1050 Ti (dGPU)
[ INFO ]                Immutable: DEVICE_UUID : 3a2e8166fdd57a2d1ed107179784e988
[ INFO ]                Immutable: DEVICE_LUID : 3903010000000000
[ INFO ]                Immutable: DEVICE_TYPE : discrete
[ INFO ]                Immutable: DEVICE_GOPS : {f16:0,f32:0,i8:0,u8:0}
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : FP32 BIN INT8 EXPORT_IMPORT
[ INFO ]                Immutable: GPU_DEVICE_TOTAL_MEM_SIZE : 4294967296
[ INFO ]                Immutable: GPU_UARCH_VERSION : 6.1.0
[ INFO ]                Immutable: GPU_EXECUTION_UNITS_COUNT : 6
[ INFO ]                Immutable: GPU_MEMORY_STATISTICS : ""
[ INFO ]                Mutable: PERF_COUNT : NO
[ INFO ]                Mutable: MODEL_PRIORITY : MEDIUM
[ INFO ]                Mutable: GPU_HOST_TASK_PRIORITY : MEDIUM
[ INFO ]                Mutable: GPU_QUEUE_PRIORITY : MEDIUM
[ INFO ]                Mutable: GPU_QUEUE_THROTTLE : MEDIUM
[ INFO ]                Mutable: GPU_ENABLE_LOOP_UNROLLING : YES
[ INFO ]                Mutable: GPU_DISABLE_WINOGRAD_CONVOLUTION : NO
[ INFO ]                Mutable: CACHE_DIR : ""
[ INFO ]                Mutable: CACHE_MODE : optimize_speed
[ INFO ]                Mutable: PERFORMANCE_HINT : LATENCY
[ INFO ]                Mutable: EXECUTION_MODE_HINT : PERFORMANCE
[ INFO ]                Mutable: COMPILATION_NUM_THREADS : 12
[ INFO ]                Mutable: NUM_STREAMS : 1
[ INFO ]                Mutable: PERFORMANCE_HINT_NUM_REQUESTS : 0
[ INFO ]                Mutable: INFERENCE_PRECISION_HINT : f16
[ INFO ]                Mutable: ENABLE_CPU_PINNING : NO
[ INFO ]                Mutable: DEVICE_ID : 0
[ INFO ]

 

0 Kudos

Link Copied

7 Replies
Hairul_Intel
Moderator
‎03-07-2024 11:54 PM
1,899 Views

Hi LuckGuySam,

Thank you for reaching out to us.

 

Please download again the OpenVINO Runtime Archive for Windows. Next, open the command prompt as administrator and run the "setupvars.bat" file. Continue with building the C++ sample as normal.

 

If the error persists, please ensure that the "openvino_intel_npu_plugin.dll" file is located inside of the "C:\w_openvino_toolkit_windows_2023.3.0.13775.ceeafaf64f3_x86_64\runtime\bin\intel64\Release" directory.

 

 

Regards,

Hairul


0 Kudos
Copy link
LuckGuySam
Beginner
‎03-11-2024 01:00 AM
1,851 Views
In response to Hairul_Intel

Hi Hairul_Intel,

I tried to rebuild according to the suggested steps, but it still didn't solve the problem.

I changed many computers and then executed it again. Most of the computers were normal, but a few had problems. In my tests, I found that computers with abnormal problems all contain C:\Windows\System32\ze_loader.dll. However, computers without ze_loader.dll can execute normally. If ze_loader.dll exist,  openvino_intel_npu_plugin.dll will link to ze_loader.dll.  The ze_loader.dll couldn't be deleted from my computer, so I had to try updating the version (1.1.0-->1.15.0), and then it worked fine.

I try to survey about ze_loader.dll found that it also comes from intel. So is this a bug?

In response to Hairul_Intel
0 Kudos
Copy link
Hairul_Intel
Moderator
‎03-11-2024 09:22 PM
1,832 Views

Hi LuckGuySam,

Thank you for providing your information.

 

As mentioned in the Configurations for Intel® NPU with OpenVINO™ for Windows, the driver package is available through Windows Update thus, please ensure your windows is updated to the latest version.

 

However, it may also be installed manually by downloading the NPU driver package.

 

Following the NPU driver package installation, the ze_loader.dll will be updated to the 1.15.0.0 version.

 

 

Regards,

Hairul

 

0 Kudos
Copy link
LuckGuySam
Beginner
‎03-12-2024 05:23 PM
1,806 Views
In response to Hairul_Intel

Hi Hairul_Intel,

Thank you for providing the method. I also believe that installing the NPU driver can effectively solve this problem.

However, what puzzles me is that I don't intend to run it on the NPU, so I don't have an NPU device. I just want to execute it on the CPU or iGPU, but I have to install the NPU driver to avoid error messages. Isn't that strange?

In response to Hairul_Intel
0 Kudos
Copy link
Hairul_Intel
Moderator
‎03-12-2024 06:46 PM
1,793 Views

Hi LuckGuySam,

I've escalated this issue to the relevant teams for further investigation and will update you on any findings as soon as possible.

 

 

Regards,

Hairul


0 Kudos
Copy link
Megat_Intel
Moderator
‎04-15-2024 02:34 AM
1,400 Views

Hi LuckGuySam,

For your information, this issue occurs when an old ze_loader library is installed on the host. In that case, zeInit will not fail as the plugin expects when there is no NPU device in the system.

 

The plugin continues and queries other info from the driver and eventually fails in zeGetExtensionFunctionAddress with the error you observed.

 

The workaround is to update the GPU driver to the latest version (this will update the ze loader version as well) since there have been fixes made in the loader logic to manage multiple user mode drivers.

 

We will update the documentation regarding this issue for future reference. Thank you for sharing your findings with us.

 

 

Regards,

Megat


0 Kudos
Copy link
Megat_Intel
Moderator
‎04-23-2024 12:55 AM
1,210 Views

Hi LuckGuySam,

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

 

 

Regards,

Megat


0 Kudos
Copy link
Reply

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.