Cuda Failure: Status=700 (Reference Graph)

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi, I have downloaded the reference graph on my pc (gpu rtx 2080) and encountered this error while executing the graph. Am i missing something? Any assistance would be much appreciated.

Cuda failure: status=1 in cuResData at line 316
Cuda failure: status=1 in cuResData at line 348
nvbufsurface: NvBufSurfaceSysToHWCopy: failed in mem copy
ERROR: nvdsinfer_context_impl.cpp:341 Failed to make stream wait on event, cuda err_no:700, err_str:cudaErrorIllegalAddress
ERROR: nvdsinfer_context_impl.cpp:1619 Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:00.930358892 10315 0x7fa8a800b4a0 WARN nvinfer gstnvinfer.cpp:1324:gst_nvinfer_input_queue_loop:<nvinfer_bin_nvinfer> error: Failed to queue input batch for inferencing
2022-02-18 01:00:46.988 ERROR extensions/nvdsbase/nvds_scheduler.cpp@309: Error from /GstPipeline:NvDsScheduler-Pipeline/GstDsNvInferBin:NvDsInferVideo…5080/nv_ds_infer10…2748/GstNvInfer:nvinfer_bin_nvinfer: Failed to queue input batch for inferencing
2022-02-18 01:00:46.988 ERROR extensions/nvdsbase/nvds_scheduler.cpp@311: Debug info:
gstnvinfer.cpp(1324): gst_nvinfer_input_queue_loop (): /GstPipeline:NvDsScheduler-Pipeline/GstDsNvInferBin:NvDsInferVideo…5080/nv_ds_infer10…2748/GstNvInfer:nvinfer_bin_nvinfer
Source 0: Frame Number = 0 Total objects = 0
Returned, stopping playback
cuCtxCreate failed with error(700) gst_eglglessink_cuda_init
Cuda failure: status=700
Error(-1) in buffer allocation

** (gxe:10315): CRITICAL **: 01:00:47.030: gst_nvds_buffer_pool_alloc_buffer: assertion ‘mem’ failed

End deepstream-test1.yaml

3

Sorry for the late response, is this still an issue to support? Thanks

4

Hi, yes.

Here is the latest error message.

Cuda failure: status=1 in cuResData at line 316
Cuda failure: status=1 in cuResData at line 348
Cuda failure: status=700 in cuResData at line 316
Cuda failure: status=700 in cuResData at line 348
ERROR: nvdsinfer_context_impl.cpp:341 Failed to make stream wait on event, cuda err_no:700, err_str:cudaErrorIllegalAddress
nvbufsurface: NvBufSurfaceSysToHWCopy: failed in mem copy
ERROR: nvdsinfer_context_impl.cpp:1619 Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:00.888039088 5632 0x7f972800b4a0 WARN nvinfer gstnvinfer.cpp:1324:gst_nvinfer_input_queue_loop:<nvinfer_bin_nvinfer> error: Failed to queue input batch for inferencing
/opt/nvidia/graph-composer/execute_graph.sh: line 320: 5632 Segmentation fault (core dumped) ${RUN_PREFIX} ${GXE_PATH} -app “${GRAPH_FILES}” -manifest “${MANIFEST_FILE}”

5

Please make sure your deepstream has been installed correctly as Quickstart Guide — DeepStream 6.1.1 Release documentation

6

Hi Fiona, yes I have installed deepstream according to the guide.

7

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

8

• Hardware Platform (Jetson / GPU) dGPU (RTX 2080)
• DeepStream Version 6.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.0.1
• NVIDIA GPU Driver Version (valid for GPU only) 470.63.01
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

9

Can local deepstream work well? Have you run the deepstream-test1 sample to test deepstream?

10

I run the deepstream-test1 sample just now and this is the error message

Cuda failure: status=1 in cuResData at line 316
Cuda failure: status=1 in cuResData at line 316
Cuda failure: status=700 in cuResData at line 316
Cuda failure: status=700 in cuResData at line 348
Segmentation fault (core dumped)

11

Hi, the issue has been solved by reinstalling the deepstream. Thanks.

13

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.