This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

IWR1642: Profile the time cost of sensorStart/sensorStop

Part Number: IWR1642

Hi,

I tried to profile the time cost of  sensorStart/sensorStop command in mmw demo. I found sensorStart will trigger MMWDEMO_CLI_SENSORSTART_EVT, sensorStart 0 will trigger MMWDEMO_CLI_FRAMESTART_EVT and sensorStop will trigger MMWDEMO_CLI_SENSORSTOP_EVT.

As in IWR1642 mmw demo, R4F works with DSP for these command, so I tried to profile the time from MMWDEMO_CLI_SENSORSTART_EVT start to MMWDEMO_DSS_START_COMPLETED_EVT end, MMWDEMO_CLI_FRAMESTART_EVT start to MMWDEMO_DSS_START_COMPLETED_EVT end and MMWDEMO_CLI_SENSORSTOP_EVT start to MMWDEMO_DSS_STOP_COMPLETED_EVT end at R4F side. Attached is my code for profile. Would you pls kindly help to check if it ok?

mss_main.c

I used attached file to profile the time and I found the time of MMWDEMO_CLI_SENSORSTOP_EVT to MMWDEMO_DSS_STOP_COMPLETED_EVT is changing a lot. Sometimes it is 10355us. Sometime it is 20094 us. Is this reasonable? What will effect the time of sensor stop?

  • Hello Chris,

    Looking at your code, it looks fine. We can expect the time of the sensor stop to vary based on the frame periodicity. The largest variance in the time should be roughly equal to the frame periodicity. This is because the sensor stop will wait until the end of the frame before completely disabling the sensor. Try decreasing or increasing the frame periodicity in the frameCfg of the configuration file and see if this has any affect on the variation.

  • Hello Chris,

    If you have no further questions I will be closing this thread.

    Regards,

    Adrian