AICORE Diagnosis

Function

Diagnose AICORE errors and output the diagnosis result.

**Table 1** Diagnostic items
Item	Time Required	Whether NPU Training or Inference Is Affected	Application Scenario
AICORE diagnosis	3min~8min	Yes	During the inspection and rollout of a training or inference job, perform AI Core diagnosis for three times. If all the three rounds are passed, the diagnosis result is normal. If EMERGENCY_WARN is displayed in any round of the diagnosis, the processor is faulty, and the hardware needs to be replaced.

The AICORE stress test and AICORE diagnosis apply to different scenarios. For details, see Table 1. Perform the AICORE stress test and AICORE diagnosis as required.
If you want to conduct the AICORE, full on-chip memory, and P2P stress tests at the same time, refer to One-Click Diagnosis.

Parameters

Table 2 lists only test-specific parameters. For details about other common parameters, see Common Parameters.

**Table 2** Parameter description
Parameter	Description	Mandatory
[-i, --items]	Specifies the diagnosis check item. aicore: AICORE error diagnosis	Yes
[-sc, --sc, --stress-count]	Specifies the number of AICORE diagnoses. This parameter takes effect only when items is set to aicore. If this parameter is not specified, the default value 1 is used. The value range is [1, 100].	No

Example

ascend-dmi -dg -i aicore -q

[***@***]# ascend-dmi -dg -i aicore  -q
Stress test is being performed, please wait.
Summary:
    Arch: aarch64
    Mode: ******
    Time: 20250529-19:35:34
 
Hardware:
    aicore:
        PASS

Fault Check Items

**Table 3** Fault check items
Command Output	Description
PASS	The diagnosis result is normal.
SKIP	The product or scenario does not support AICORE diagnosis.
EMERGENCY_WARN	Emergency warning. You are advised to replace the hardware.
FAIL	The AICORE diagnosis fails. Contact Huawei technical support or locate the fault by referring to FAQs.

Parent topic: Stress Test