# The problem was caused by not setting the CUDA_VISIBLE_DEVICES variable within the shell correctly.
# To specify CUDA device 1 for example, you would set the CUDA_VISIBLE_DEVICES using
export CUDA_VISIBLE_DEVICES=1
# or
CUDA_VISIBLE_DEVICES=1 ./cuda_executable
# The former sets the variable for the life of the current shell, the latter only for the lifespan of that particular executable invocation.
# If you want to specify more than one device, use
export CUDA_VISIBLE_DEVICES=0,1
# or
CUDA_VISIBLE_DEVICES=0,1 ./cuda_executable