Please provide the following info (tick the boxes after creating this topic): Software Version
DRIVE OS 6.0.8.1
DRIVE OS 6.0.6
DRIVE OS 6.0.5
DRIVE OS 6.0.4 (rev. 1)
DRIVE OS 6.0.4 SDK
other
Target Operating System
Linux
QNX
other
Hardware Platform
DRIVE AGX Orin Developer Kit (940-63710-0010-300)
DRIVE AGX Orin Developer Kit (940-63710-0010-200)
DRIVE AGX Orin Developer Kit (940-63710-0010-100)
DRIVE AGX Orin Developer Kit (940-63710-0010-D00)
DRIVE AGX Orin Developer Kit (940-63710-0010-C00)
DRIVE AGX Orin Developer Kit (not sure its number)
other
SDK Manager Version
1.9.3.10904
other
Host Machine Version
native Ubuntu Linux 20.04 Host installed with SDK Manager
native Ubuntu Linux 20.04 Host installed with DRIVE OS Docker Containers
native Ubuntu Linux 18.04 Host installed with DRIVE OS Docker Containers
other
Hello, I have been able to write my own CGF example, composed of three nodes cascade connected (one output is connected to the previous node’s input) and managed to run it successfully.
However, I noticed that once i launch my CGF example, each time a node is called, both the SETUP and TEARDOWN phase are executed together with the PROCESS.
Do you know if it is possible to set the stmcompiler so to execute the SETUP and TEARDOWN of each node just once and so using CPUs resoruces to just run PROCESS phase?
Dear @antonio.iovine,
Could you share details about the usecase? Are you using node multiple times in application graph? Generally the workflow is setup-> process->teardown.
Yes, by mistake i had called the node multiple time, as you suggested to check, and now SETUP passes are executed just once per node at the beginning as expected, as well TEARDOWN ones at the end of the execution.