kctess5 / range_libc

A collection of optimized ray cast methods for 2D occupancy grids including the CDDT algorithm. Written in C++ and CUDA with Python wrappers.
Other
86 stars 50 forks source link

Error when compile with CUDA on Jetson TX2 #9

Open vietanhle0101 opened 4 years ago

vietanhle0101 commented 4 years ago

I get the below error when running compile_with_cuda.sh on my Jetson TX2

nvcc fatal   : Value 'sm_20' is not defined for option 'gpu-architecture'
error: command '/usr/local/cuda/bin/nvcc' failed with exit status 1

Do you know this problem?

tianyilim commented 1 year ago

If you're still stuck on this, take a look here.

sm_20 refers to a (very) old NVIDIA GPU architecture. If you're using a Jetson TX2, you likely need to change this value to sm_62. For anyone else looking at this, you could try to change the SM version based on your own GPU.

Take a look at this PR on the same repo. In the source file you can see where to make the change.