https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/very-different-results-from-FFT-when-using-MKL-internal/m-p/1240111#M30574 <P>the issue has been reproduced and escalated against the MKL FFT team. We will keep this thread informed when the fix will be ready to release.</P><BR /> Wed, 23 Dec 2020 08:05:20 GMT Gennady_F_Intel 2020-12-23T08:05:20Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/very-different-results-from-FFT-when-using-MKL-internal/m-p/1219790#M30184 <P>&nbsp;</P> <P>&nbsp;</P> <P>The following code returns different results (that do not seem to be down to numerical precision). depending on whether I set the mkl internal threading.</P> <P>I have attached the input (data1.txt) to reproduce the issue.</P> <P>And also the outputs:</P> <P>data1_out_4f.txt ( with&nbsp; mkl_set_num_threads(4) )</P> <P>data1_out_1f.txt ( with&nbsp; mkl_set_num_threads(1) )</P> <P>&nbsp;</P> <LI-CODE lang="fortran">program fft_issue USE MKL_DFTI implicit none include 'mkl.fi' integer length integer ntr,i,j,itr,nfft real, allocatable :: buffer(:) complex, allocatable :: buffer_out(:) complex, allocatable :: s1(:) integer status type(dfti_descriptor), pointer :: My_Desc1_Handle length = 2051 nfft = 3200 allocate(buffer(length)) allocate(buffer_out(nfft)) allocate(s1(nfft)) open(1, file = 'data1.txt') do j = 1 , 2051 read(1,*), buffer(j) enddo call mkl_set_num_threads(4) s1(:length) = cmplx(buffer(:)) s1(length+1:) = 0 status = DftiCreateDescriptor(My_Desc1_Handle,DFTI_SINGLE,DFTI_COMPLEX,1,3200) status = DftiSetValue(My_Desc1_Handle, DFTI_PLACEMENT, DFTI_NOT_INPLACE); status = DftiSetValue(My_Desc1_Handle, DFTI_NUMBER_OF_TRANSFORMS, 1); status = DftiSetValue(My_Desc1_Handle, DFTI_BACKWARD_SCALE, 1.0/nfft); status = DftiCommitDescriptor(My_Desc1_Handle); status = DftiComputeForward( My_Desc1_Handle, s1, buffer_out ) status = DftiComputeBackward( My_Desc1_Handle, buffer_out, s1 ) open(1, file = 'data1_out_4f.txt') do j = 1 , nfft write(1,*), s1(j) enddo end program </LI-CODE> <P>&nbsp;</P> <P>&nbsp;</P> <P>I am running the program on a 4-core Intel(R) Xeon(R) CPU E3-1240 v3 @ 3.40GHz</P> <P>I am using mkl 19 update 5</P> <P>My compile command as follows:</P> <P>/opt/intel/19/bin/ifort reproduce_intel.f90 -Wl,--start-group ${MKLROOT}/lib/intel64/libmkl_intel_lp64.a ${MKLROOT}/lib/intel64/libmkl_intel_thread.a ${MKLROOT}/lib/intel64/libmkl_core.a -Wl,--end-group -liomp5 -lpthread -lm -ldl -I${MKLROOT}/include</P> Wed, 21 Oct 2020 13:02:46 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/very-different-results-from-FFT-when-using-MKL-internal/m-p/1219790#M30184 cgg_distribution 2020-10-21T13:02:46Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/very-different-results-from-FFT-when-using-MKL-internal/m-p/1220044#M30189 <P>thanks, Marie for the case. At the very first glance, everything is correct with this case. We will check and get back asap.</P><BR /> Thu, 22 Oct 2020 03:36:48 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/very-different-results-from-FFT-when-using-MKL-internal/m-p/1220044#M30189 Gennady_F_Intel 2020-10-22T03:36:48Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/very-different-results-from-FFT-when-using-MKL-internal/m-p/1240111#M30574 <P>the issue has been reproduced and escalated against the MKL FFT team. We will keep this thread informed when the fix will be ready to release.</P><BR /> Wed, 23 Dec 2020 08:05:20 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/very-different-results-from-FFT-when-using-MKL-internal/m-p/1240111#M30574 Gennady_F_Intel 2020-12-23T08:05:20Z