Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

Compilation Error

See original GitHub issue

CuPy version: 8.0.0
OS/Platform: Ubuntu
CUDA version: 10.2
cuDNN/NCCL version: 7.6.5.32/ 2.9.8.1

I am running code from the following recently popular repository, and I am getting the following error:

 File "/homes/rs2517/fast/lib/python3.7/site-packages/cupy/cuda/compiler.py", line 516, in compile
    nvrtc.compileProgram(self.ptr, options)
  File "cupy_backends/cuda/libs/nvrtc.pyx", line 108, in cupy_backends.cuda.libs.nvrtc.compileProgram
  File "cupy_backends/cuda/libs/nvrtc.pyx", line 120, in cupy_backends.cuda.libs.nvrtc.compileProgram
  File "cupy_backends/cuda/libs/nvrtc.pyx", line 58, in cupy_backends.cuda.libs.nvrtc.check_status
cupy_backends.cuda.libs.nvrtc.NVRTCError: NVRTC_ERROR_COMPILATION (6)

During handling of the above exception, another exception occurred:
(...)
File "/homes/rs2517/fast/lib/python3.7/site-packages/cupy/cuda/compiler.py", line 528, in compile
    'nvrtc' if not runtime.is_hip else 'hiprtc')
cupy.cuda.compiler.CompileException: /tmp/tmp_x85h7rr/fc895e636bcac603ee7f359ed7f249db_2.cubin.cu(6): error: identifier "None" is undefined

/tmp/tmp_x85h7rr/fc895e636bcac603ee7f359ed7f249db_2.cubin.cu(6): error: identifier "None" is undefined

/tmp/tmp_x85h7rr/fc895e636bcac603ee7f359ed7f249db_2.cubin.cu(6): error: identifier "None" is undefined

/tmp/tmp_x85h7rr/fc895e636bcac603ee7f359ed7f249db_2.cubin.cu(13): error: identifier "None" is undefined

4 errors detected in the compilation of "/tmp/tmp_x85h7rr/fc895e636bcac603ee7f359ed7f249db_2.cubin.cu".

I was wondering if this issue is due to my installation or due to an issue with this specific code (I can import cupy and initialize an array on python, so it works to some extent, I’m not sure what else to try) . Would appreciate any help if anyone has had a similar issue in the past. Thanks!

Issue Analytics

State:
Created 2 years ago
Comments:5 (2 by maintainers)

Top GitHub Comments

1reaction

kmaehashicommented, May 19, 2021

Try setting export CUPY_DUMP_CUDA_SOURCE_ON_ERROR=1 (docs) and rerun the code to see the full code causing the compilation error. My guess is that None is injected for some reason instead of literal when generating a CUDA code.

https://github.com/d-li14/involution/blob/21c3158fcbb4ecda8ed4626fcae8b01be511a598/det/mmdet/models/utils/involution_cuda.py#L26

I’d suggest you report this issue to the involution repository along with the full command line.

0reactions

rhj0103commented, Apr 7, 2022

请问您是怎么解决这个问题的呢?