Size of a prepared data queue. It is generated when AI CPU is enabled in the data offloading scenario.

Product	Supported
Ascend 950PR/Ascend 950DT	√
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	√
Atlas inference products	√
Atlas training products	√

The following is an example of the content format of the aicpu_mi_*.csv file:

Figure 1 aicpu_mi_*.csv

**Table 1** Field description
Field	Description
Device_id	Device ID.
Node Name	Name of a prepared data queue.
Start Time(us)	Start time of data reading, in μs.
End Time(us)	End time of data reading, in μs.
Queue Size	Queue size.

aicpu_mi (Prepared Data Queue)