Question: cycle count of 65536 MKL FFT DftiComputeForward(C++)

My code as followings:

fft_mkl(int M,float * InputData,float * OutputData)

{

MKL_LONG status;

DFTI_DESCRIPTOR my_desc1_handle;
DftiCreateDescriptor( &my_desc1_handle, DFTI_SINGLE,DFTI_COMPLEX, 1, M);
DftiSetValue( my_desc1_handle, DFTI_PLACEMENT, DFTI_NOT_INPLACE);
DftiCommitDescriptor( my_desc1_handle );
status = DftiComputeForward( my_desc1_handle, InputData, OutputData);
status = DftiFreeDescriptor(&my_desc1_handle);

}

float *test = new float [65536*2];

float *test_out = new float [65536*2];

memset(test,85,4*32768);

memset(test,0,4*(65536*2-32768));

fft_mkl(65536,test,test_out);

Actually ,the result is wrong. It is different from fftw wrapper with 65536. But 32768 is right.Why?

MKL version:10.2.4.032

Thanks in advance!

Ziren C.