Chainer - Python - CUDA_ERROR_INVALID_SOURCE

I have a machine with two different GPUs (one RTX and one Titan V) and often it fails to run tasks. This behaviour is mostly observed in GPU with id=1.

The same task can be run successfully in a different machine or GPU with id=0.

The precise stack is the following:

  File "cupy/core/core.pyx", line 1689, in cupy.core.core.ndarray.__setitem__
  File "cupy/core/core.pyx", line 3598, in cupy.core.core._scatter_op
  File "cupy/core/_kernel.pyx", line 828, in cupy.core._kernel.ufunc.__call__
  File "cupy/util.pyx", line 48, in cupy.util.memoize.decorator.ret
  File "cupy/core/_kernel.pyx", line 617, in cupy.core._kernel._get_ufunc_kernel
  File "cupy/core/_kernel.pyx", line 51, in cupy.core._kernel._get_simple_elementwise_kernel
  File "cupy/core/carray.pxi", line 164, in cupy.core.core.compile_with_cache
  File "[miniconda]/envs/[env_name]/lib/python3.5/site-packages/cupy/cuda/compiler.py", line 161, in compile_with_cache
    mod.load(cubin)
  File "cupy/cuda/function.pyx", line 181, in cupy.cuda.function.Module.load
  File "cupy/cuda/function.pyx", line 183, in cupy.cuda.function.Module.load
  File "cupy/cuda/driver.pyx", line 185, in cupy.cuda.driver.moduleLoadData
  File "cupy/cuda/driver.pyx", line 81, in cupy.cuda.driver.check_status
cupy.cuda.driver.CUDADriverError: CUDA_ERROR_INVALID_SOURCE: device kernel image is invalid

My setup is the following:

chainer                   5.2.0                     <pip>
chainercv                 0.12.0                    <pip>
cupy-cuda100              5.2.0                     <pip>

The same problem shows up in chainer 5.3 (i created a new conda environment from scratch).

I believe that this is somehow connected with multi-threading, but I could not find how to turn it off in cupy or how to avoid the problem altogether.

Some potentially irrelevant information: This is a rather stochastic process. In GPU id=1, eight times out of ten it fails to run with the aforementioned error.

Any ideas?