cutComparel2fe with double data type?

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi all,

I found CUDA indeed very powerful to perform FFT and I have modified the simpleCUFFT example to make it running with double precision data type.

I observe that the h_convolved_signal and h_convolved_signal_ref both become double2* and their x are 2.2121987206156351 and 2.2121986217226501 which are in good agreement up to 1e-7! But the cutComparel2fe() still prompts error:

“ERROR, l2-norm error -1.#IND is greater than epsilon 1e-005”
“FAILED”

Does it means cutComparel2fe() cannot works with double data type?

Here it is in the codes:

CUTBoolean res = cutCompareL2fe((float*)h_convolved_signal_ref, (float*)h_convolved_signal, 2 * SIGNAL_SIZE, 1e-5f);
printf(“%s\n”, (1 == res) ? “PASSED” : “FAILED”);

Thanks for your advice!

2

Assuming that h_convolved_signal is a double array, these casts are the problem. You can’t just cast a double pointer to a float pointer and expect the compiler to transparently change the data types. The memory layout for float and double are different. Casting a double to a float by value does what you expect in C, but pointers do not. You’ll have to rewrite cutCompareL2fe to work with double arrays.

3

Thank you very much! I shall investigate cutCompareL2fe but is it part of the runtime API? Where can I find this function? Are there any equivalent functions available in runtime API?

4

Along with all functions beginning with ‘cut’ it is part of the utilities directory of the SDK. As such, it’s not supported by NVIDIA - those routines are simply there to make writing the SDK examples easier. tmurray will be along with the baseball bat shortly…