op_statistic (Operator Calling Times and Time Consumption)

There is no timeline information of the calling times and time consumption of AI Core and AI CPU operators. The summary information is summarized in the op_statistic_*.csv file.

Applicability

For details about the mapping between AI processors and Ascend products, see Ascend Product Form Description.

AI Processor Type	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product/Atlas A3 inference product	√
Atlas A2 training product/Atlas A2 inference product	√
Atlas 200I/500 A2 inference product	√
Atlas inference product	√
Atlas training product	√
Atlas 350 Accelerator Card	√

Data Description of the op_statistic_*.csv File

Analyze the total calling time and total number of calls of each type of operators, check whether there are any operators with long total execution time, and analyze whether there is any optimization space for these operators.

Figure 1 op_statistic_*.csv

**Table 1** Field description
Field	Description
Device_id	Device ID.
Model Name	Model name. It may be left empty if no related data is collected. (This field is not displayed by default or in the single-operator scenario.)
OP Type	Operator type.
Core Type	Core type, such as AI_CORE, AI_VECTOR_CORE, or AI_CPU.
Count	Number of calls to an operator.
Total Time(us)	Time taken by the calls to an operator, in μs.
Avg Time(us), Min Time(us), Max Time(us)	Average, minimum, and maximum duration of the calls to an operator, in μs.
Ratio(%)	Percentage of duration of the operator calls in the model.

Parent topic: Profile Data File References