Hello, I have created a very simple test file:
If I compile this code using any of the following, then it works as expected:
nvcc -lcublas -lcufft test.cu
$ nvcc -deviceemu test.cu
However, if I compile it like so:
$ nvcc -deviceemu -lcublas -lcufft test.cu
then when I attempt to execute the program, there is no output! Nothing seems to happen. But it doesn’t hang, nor does it give any errors.
Can anyone figure what the problem might be? I am using CUDA 3.0 V0.2.1221 with gcc/g++ 4.3.4 on Ubuntu.
Thanks in advance!