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.

TDA2EXEVM: TIDL SSD model on usecase fail

Part Number: TDA2EXEVM

Hi TIDL experts,

I use TIDL.01.01.02.00.

I have a modified jacinto SSD model with a lot of detector head.(10 heads)

It can not work properly on the usecase. it stuck and i even can not see the statistic.

IPU1-0] 16.372079 s: SYSTEM: SW Message Box Msg Pool, Free Msg Count = 1023
[IPU1-0] 16.372201 s: SYSTEM: Heap = LOCAL_DDR @ 0x00000000, Total size = 262144 B (256 KB), Free size = 243176 B (237 KB)
[IPU1-0] 16.372354 s: SYSTEM: Heap = SR_OCMC @ 0x00000000, Total size = 0 B (0 KB), Free size = 0 B (0 KB)
[IPU1-0] 16.372506 s: SYSTEM: Heap = SR_DDR_CACHED @ 0x89c03000, Total size = 368037888 B (350 MB), Free size = 239153152 B (228 MB)
[IPU1-0] 16.372689 s: SYSTEM: Heap = SR_DDR_NON_CACHED @ 0xbfb00000, Total size = 127360 B (0 MB), Free size = 92800 B (0 MB)
[IPU1-1] 16.373055 s: SYSTEM: SW Message Box Msg Pool, Free Msg Count = 1023
[IPU1-1] 16.373177 s: SYSTEM: Heap = LOCAL_DDR @ 0x00000000, Total size = 655360 B (640 KB), Free size = 643368 B (628 KB)
[HOST ] 16.373543 s: SYSTEM: SW Message Box Msg Pool, Free Msg Count = 1023
[HOST ] 16.373543 s: SYSTEM: Heap = LOCAL_DDR @ 0x00000000, Total size = 6291456 B (6144 KB), Free size = 6236464 B (6090 KB)

And i do some experiment on the model, i try to reduce the heads of the model.(start removing from the top)

It works at 8 heads eventually. and the FPS is 24 .

But it can not work if the number of heads is bigger than 9.

Is there any possible reason about it?

it should not drop from 24 to 0  FPS?

I use model import trace dump on the model , and the reuslts is proper.

I do not have debugger so i can not use testbench.

I am looking forward to your answer.

Thank you so much.

Best Regards,

Jason