1.SDK Version: SDK 7.01
2. Board: Custom Board
3. CSI-Tx setting
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
/* CSITX Config initialization */
tivx_csitx_params_init(&csitxObj->csitx_params);
csitxObj->csitx_params.numInst = 1U;
csitxObj->csitx_params.numCh = NUM_CHANNELS;
csitxObj->csitx_params.instId[0U] = CSITX_INST_ID;
csitxObj->csitx_params.instCfg[0U].rxCompEnable = (uint32_t)vx_true_e;
csitxObj->csitx_params.instCfg[0U].rxv1p3MapEnable = (uint32_t)vx_true_e;
csitxObj->csitx_params.instCfg[0U].laneBandSpeed = TIVX_CSITX_LANE_BAND_SPEED_770_TO_870_MBPS;
csitxObj->csitx_params.instCfg[0U].numDataLanes = 4U;
for (loopCnt = 0U; loopCnt <csitxObj-> csitx_params.instCfg[0U].numDataLanes; loopCnt++)
{
csitxObj->csitx_params.instCfg[0U].lanePolarityCtrl[loopCnt] = 0u;
}
for (loopCnt = 0U; loopCnt <NUM_CHANNELS; loopCnt++)
{
csitxObj->csitx_params.chVcNum[loopCnt] = loopCnt;
csitxObj->csitx_params.chInstMap[loopCnt] = CSITX_INST_ID;
}
csitxObj->csitx_params_obj = vxCreateUserDataObject(context, "tivx_csitx_params_t",sizeof(tivx_csitx_params_t),&csitxObj->csitx_params);
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Good morning. Experts.
I now want to transmit the camera image to another board through the CSI-Tx node through the 4 channel camera input via the VISS and LDC node.
The graph looks like this:
<Capture Node> - <VISS Node> - <LDC Node> - <CSI-Tx Node>
When the CSI-Tx node receiving 4 channels was allocated to the MCU2_0 (IPU0) core and checked the performance,
the execution time was 66ms, and the same measured 66ms in the MCU2_1 (IPU1) core.
Also, I tried changing the "TIVX_CSITX_LANE_BAND_SPEED_770_TO_870_MBPS" value to a faster speed, but the CSI-Tx execution time did not decrease.
The overall graph execution time is about 21 FPS. I want to optimize this execution time (to 30fps), how can I reduce the execution time of the CSI-Tx node?
