-cublas or -cufft problems In emulation mode

Accelerated Computing CUDA CUDA Programming and Performance
1

Hello, I have created a very simple test file:

// test.cu
#include <stdio.h>
int main(void)
{
printf(“Hello world!\n”);
return 0;
}

If I compile this code using any of the following, then it works as expected:

$ nvcc test.cu
$ 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!

2

Hello, I have created a very simple test file:

// test.cu
#include <stdio.h>
int main(void)
{
printf(“Hello world!\n”);
return 0;
}

If I compile this code using any of the following, then it works as expected:

$ nvcc test.cu
$ 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!

3

try with cublasemu and cufftemu,

hope this help!