Operator Input Argument Errors
Symptom
The following error information is displayed in the host application log file (log/[run|debug]/plog/plog-pid _*.log) :
[ERROR] RUNTIME(85483,python):2024-04-19-18:13:17.186.318 [task_info.cc:1678]85658 PrintErrorInfoForDavinciTask:Aicore kernel execute failed, device_id=0, stream_id=2, report_stream_id=2, task_id=57783, flip_num=3, fault kernel_name=RealDiv_ee98c6628030785f610b924ab1557b31_high_precision_210000000, fault kernel info ext=none, program id=9, hash=10612039229658031084. [ERROR] RUNTIME(85483,python):2024-04-19-18:13:17.186.336 [task_info.cc:1617]85658 GetArgsInfo:[AIC_INFO] args(0 to 9) after execute:0x4f453840, 0x124201ea7400, 0x12420240cc00, 0x1241c006dc28, 0x124100011000, 0x1, 0x1, 0x1, 0,
Fault Root Causes
In the error information of the plogs, the args(xxxx) after execute part is critical. Check whether the parameter address in the args after execute part is proper. If 0 is displayed, the address allocation is incorrect.
The is on the
In
Solution
Check the training script. If division is used, for example, cpu_tensor/npu_tensor is used, the AI Core will fail to read data. The reason is that cpu_tensor is the host memory address and npu_tensor is the device memory address. In this case, you need to change these two addresses to the device memory addresses.