Error: identifier "cudaGetCurrentGraphExec" is undefined

The code in CUDA programming guide mentioned a function cudaGetCurrentGraphExec in the sample code, but when I tried to use it, this error occurs. I was compiling the code using the option -code=sm_86 -arch=compute_86.

Is there a header file missing or the version I am using does not support this function?

Which version are you using?

nvcc --version

Built on Tue_May__3_19:00:59_Pacific_Daylight_Time_2022
Cuda compilation tools, release 11.7, V11.7.64
Build cuda_11.7.r11.7/compiler.31294372_0

Device graphs were introduced with CUDA 12. You cannot use them with CUDA 11.7

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.