[Bug]: Core-dump while running hello_query_device application due to double free or corruption

[js333031]

OpenVINO Version

2025.1.0.18503

Operating System

Other (Please specify in description)

Device used for inference

CPU

Framework

None

Model used

NA

Issue description

While running hello_query_device application, double free causes a core dump. See the attached logs, along with system details.

(openvino_env) apl@apl-Broxton-P:~/openvino_cpp_samples_build/intel64/Release$ ./hello_query_device
[ INFO ] Build ................................. 2025.1.0-18503-6fec06580ab-releases/2025/1
[ 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 4
[ INFO ]                Immutable: EXECUTION_DEVICES : CPU
[ INFO ]                Immutable: FULL_DEVICE_NAME : Intel(R) Atom(TM) Processor E3950 @ 1.60GHz
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : FP32 INT8 BIN EXPORT_IMPORT
[ INFO ]                Immutable: DEVICE_TYPE : integrated
[ INFO ]                Immutable: DEVICE_ARCHITECTURE : intel64
[ INFO ]                Mutable: NUM_STREAMS : 1
[ 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: ENABLE_CPU_RESERVATION : NO
[ INFO ]                Mutable: SCHEDULING_CORE_TYPE : ANY_CORE
[ INFO ]                Mutable: MODEL_DISTRIBUTION_POLICY : ""
[ INFO ]                Mutable: ENABLE_HYPER_THREADING : YES
[ INFO ]                Mutable: DEVICE_ID : ""
[ INFO ]                Mutable: CPU_DENORMALS_OPTIMIZATION : NO
[ INFO ]                Mutable: LOG_LEVEL : LOG_NONE
[ INFO ]                Mutable: CPU_SPARSE_WEIGHTS_DECOMPRESSION_RATE : 1
[ INFO ]                Mutable: DYNAMIC_QUANTIZATION_GROUP_SIZE : 32
[ INFO ]                Mutable: KV_CACHE_PRECISION : u8
[ INFO ]                Mutable: KEY_CACHE_PRECISION : u8
[ INFO ]                Mutable: VALUE_CACHE_PRECISION : u8
[ INFO ]                Mutable: KEY_CACHE_GROUP_SIZE : 0
[ INFO ]                Mutable: VALUE_CACHE_GROUP_SIZE : 0
[ INFO ]
[ INFO ] GPU
[ INFO ]        SUPPORTED_PROPERTIES:
[ INFO ]                Immutable: AVAILABLE_DEVICES : 0
[ 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=v9.3.0
[ INFO ]                Immutable: FULL_DEVICE_NAME : Intel(R) HD Graphics 505 (iGPU)
[ INFO ]                Immutable: DEVICE_UUID : 8680845a0d0000000002000000000000
[ INFO ]                Immutable: DEVICE_LUID : 409a0000499a0000
[ INFO ]                Immutable: DEVICE_TYPE : integrated
[ INFO ]                Immutable: DEVICE_GOPS : {f16:374.4,f32:187.2,i8:187.2,u8:187.2}
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : FP32 BIN FP16 EXPORT_IMPORT
[ INFO ]                Immutable: GPU_DEVICE_TOTAL_MEM_SIZE : 4037267456
[ INFO ]                Immutable: GPU_UARCH_VERSION : 9.3.0
[ INFO ]                Immutable: GPU_EXECUTION_UNITS_COUNT : 18
[ 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_SDPA_OPTIMIZATION : YES
[ 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 : 4
[ 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: ENABLE_CPU_RESERVATION : NO
[ INFO ]                Mutable: DEVICE_ID : 0
[ INFO ]                Mutable: DYNAMIC_QUANTIZATION_GROUP_SIZE : 0
[ INFO ]                Mutable: ACTIVATIONS_SCALE_FACTOR : -1
[ INFO ]                Mutable: WEIGHTS_PATH : ""
[ INFO ]                Mutable: CACHE_ENCRYPTION_CALLBACKS : ""
[ INFO ]                Mutable: KV_CACHE_PRECISION : dynamic
[ INFO ]                Mutable: MODEL_PTR : 0
[ INFO ]
double free or corruption (out)
Aborted (core dumped)
(openvino_env) apl@apl-Broxton-P:~/openvino_cpp_samples_build/intel64/Release$

sysinfo.txt
hello_query.txt
hello_query_gdb.txt

Step-by-step reproduction

No response

Relevant log output

Issue submission checklist

• I'm reporting an issue. It's not a question.
• I checked the problem with the documentation, FAQ, open issues, Stack Overflow, etc., and have not found a solution.
• There is reproducer code and related data files such as images, videos, models, etc.

[Wan-Intel]

I have installed OpenVINO™ 2025,1 Runtime on Linux from an Archive File and I have validated Hello Query Device C++ Sample on Ubuntu 24.04 LTS

~/openvino_cpp_samples_build/intel64/Release$ ./hello_query_device
[ INFO ] Build ................................. 2025.1.0-18503-6fec06580ab-releases/2025/1
[ 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 8
[ INFO ]                Immutable: EXECUTION_DEVICES : CPU
[ INFO ]                Immutable: FULL_DEVICE_NAME : Intel(R) Core(TM) Ultra 7 258V
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : BF16 FP32 FP16 INT8 BIN EXPORT_IMPORT
[ INFO ]                Immutable: DEVICE_TYPE : integrated
[ INFO ]                Immutable: DEVICE_ARCHITECTURE : intel64
[ INFO ]                Mutable: NUM_STREAMS : 1
[ 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: ENABLE_CPU_RESERVATION : NO
[ INFO ]                Mutable: SCHEDULING_CORE_TYPE : ANY_CORE
[ INFO ]                Mutable: MODEL_DISTRIBUTION_POLICY : ""
[ INFO ]                Mutable: ENABLE_HYPER_THREADING : YES
[ INFO ]                Mutable: DEVICE_ID : ""
[ INFO ]                Mutable: CPU_DENORMALS_OPTIMIZATION : NO
[ INFO ]                Mutable: LOG_LEVEL : LOG_NONE
[ INFO ]                Mutable: CPU_SPARSE_WEIGHTS_DECOMPRESSION_RATE : 1
[ INFO ]                Mutable: DYNAMIC_QUANTIZATION_GROUP_SIZE : 32
[ INFO ]                Mutable: KV_CACHE_PRECISION : u8
[ INFO ]                Mutable: KEY_CACHE_PRECISION : u8
[ INFO ]                Mutable: VALUE_CACHE_PRECISION : u8
[ INFO ]                Mutable: KEY_CACHE_GROUP_SIZE : 0
[ INFO ]                Mutable: VALUE_CACHE_GROUP_SIZE : 0
[ INFO ]
[ INFO ] GPU
[ INFO ]        SUPPORTED_PROPERTIES:
[ INFO ]                Immutable: AVAILABLE_DEVICES : 0
[ 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=v20.4.4
[ INFO ]                Immutable: FULL_DEVICE_NAME : Intel(R) Arc(TM) Graphics (iGPU)
[ INFO ]                Immutable: DEVICE_UUID : 8680a064040000000002000000000000
[ INFO ]                Immutable: DEVICE_LUID : 409a0000499a0000
[ INFO ]                Immutable: DEVICE_TYPE : integrated
[ INFO ]                Immutable: DEVICE_GOPS : {f16:0,f32:1996.8,i8:0,u8:0}
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : FP32 BIN FP16 INT8 GPU_HW_MATMUL EXPORT_IMPORT
[ INFO ]                Immutable: GPU_DEVICE_TOTAL_MEM_SIZE : 15113515008
[ INFO ]                Immutable: GPU_UARCH_VERSION : 20.4.4
[ INFO ]                Immutable: GPU_EXECUTION_UNITS_COUNT : 64
[ 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_SDPA_OPTIMIZATION : YES
[ 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 : 8
[ 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: ENABLE_CPU_RESERVATION : NO
[ INFO ]                Mutable: DEVICE_ID : 0
[ INFO ]                Mutable: DYNAMIC_QUANTIZATION_GROUP_SIZE : 0
[ INFO ]                Mutable: ACTIVATIONS_SCALE_FACTOR : -1
[ INFO ]                Mutable: WEIGHTS_PATH : ""
[ INFO ]                Mutable: CACHE_ENCRYPTION_CALLBACKS : ""
[ INFO ]                Mutable: KV_CACHE_PRECISION : dynamic
[ INFO ]                Mutable: MODEL_PTR : 0
[ INFO ]
[ INFO ] NPU
[ INFO ]        SUPPORTED_PROPERTIES:
[ INFO ]                Immutable: AVAILABLE_DEVICES : 4000
[ INFO ]                Mutable: CACHE_DIR : ""
[ INFO ]                Mutable: COMPILATION_NUM_THREADS : 8
[ INFO ]                Immutable: DEVICE_ARCHITECTURE : 4000
[ INFO ]                Immutable: DEVICE_GOPS : {bf16:0,f16:46694.4,f32:0,i8:93388.8,u8:93388.8}
[ INFO ]                Mutable: DEVICE_ID : ""
[ INFO ]                Immutable: DEVICE_PCI_INFO : {domain: 0 bus: 0 device: 0xb function: 0}
[ INFO ]                Immutable: DEVICE_TYPE : integrated
[ INFO ]                Immutable: DEVICE_UUID : 80d1d11eb73811eab3de0242ac130004
[ INFO ]                Mutable: ENABLE_CPU_PINNING : NO
[ INFO ]                Immutable: EXECUTION_DEVICES : NPU
[ INFO ]                Mutable: EXECUTION_MODE_HINT : PERFORMANCE
[ INFO ]                Immutable: FULL_DEVICE_NAME : Intel(R) AI Boost
[ INFO ]                Mutable: INFERENCE_PRECISION_HINT : f16
[ INFO ]                Mutable: LOG_LEVEL : LOG_ERROR
[ INFO ]                Mutable: MODEL_PRIORITY : MEDIUM
[ INFO ]                Mutable: NPU_BYPASS_UMD_CACHING : NO
[ INFO ]                Mutable: NPU_COMPILATION_MODE_PARAMS : ""
[ INFO ]                Mutable: NPU_COMPILER_DYNAMIC_QUANTIZATION : NO
[ INFO ]                Immutable: NPU_COMPILER_VERSION : 458754
[ INFO ]                Mutable: NPU_DEFER_WEIGHTS_LOAD : NO
[ INFO ]                Immutable: NPU_DEVICE_ALLOC_MEM_SIZE : 0
[ INFO ]                Immutable: NPU_DEVICE_TOTAL_MEM_SIZE : 33160376320
[ INFO ]                Immutable: NPU_DRIVER_VERSION : 1743174784
[ INFO ]                Mutable: NPU_MAX_TILES : 6
[ INFO ]                Mutable: NPU_TILES : -1
[ INFO ]                Mutable: NPU_TURBO : NO
[ INFO ]                Immutable: NUM_STREAMS : 1
[ INFO ]                Immutable: OPTIMAL_NUMBER_OF_INFER_REQUESTS : 1
[ INFO ]                Immutable: OPTIMIZATION_CAPABILITIES : FP16 INT8 EXPORT_IMPORT
[ INFO ]                Mutable: PERFORMANCE_HINT : LATENCY
[ INFO ]                Mutable: PERFORMANCE_HINT_NUM_REQUESTS : 1
[ INFO ]                Mutable: PERF_COUNT : NO
[ INFO ]                Immutable: RANGE_FOR_ASYNC_INFER_REQUESTS : 1 10 1
[ INFO ]                Immutable: RANGE_FOR_STREAMS : 1 4
[ INFO ]                Mutable: WEIGHTS_PATH : ""
[ INFO ]                Mutable: WORKLOAD_TYPE : DEFAULT
[ INFO ]

I noticed that you have activated a virtual environment while running the Hello Query Device C++ Sample. Could you please open a new terminal and run Hello Query Device C++ Sample without activate virtual environment?

[Wan-Intel]

I have received your message via email. We will further investigate the issue, and we will provide an update as soon as possible.

[avitial]

Hi @js333031, it seems we cannot access remotely the shared system where the issue was encountered. We were not able to reproduce the issue on our end on Lunar Lake. It would be great to get more details about the environment to help us replicate the issue or regain/share access to the system issue was observed.

I see that Apollo Lake was the platform used, according to the System Requirements, Intel Atom® Processor X Series is supported by the CPU/GPU. So it should work. It may also be a regression as I recall in the past there was a similar issue reported (caused by NPU plugin), we can try to reproduce on this platform if necessary. Kindly let us know if further assistance is required, or if issue has been addressed or is no longer relevant.

[avitial]

Hi @js333031 we were able to reproduce the issue with OpenVINO 2025.0 and 2025.1, the issue does not occur with 2024.6 (tested via pip install). You could try using version 2024.6 as a possible workaround for now, we have captured this as a bug. We will provide updates as we hear back from development team.

Ref. 167357

[wangleis]

Fix PR #30803 is created

[avitial]

Issue has been addressed by PR listed above, fix should be included in the next OpenVINO release. You can try and verify the fix using the nightly package here. Closing this issue as it has been fixed.