Difference in output of Intel IPP fir and convolution functions

Question

I am working with Intel IPP 7.1 (composer XE 2013) and noticed difference in tail end of output samples between IPP 'fir' and 'convolution' calls. So in the calls below

status = ippsFIR_Direct_64f(pSrc, pDst_f, N+M-1, pTaps,M, pDlyLine,&pDlyLineIndex);
status = ippsConv_64f(pSrc, N, pTaps, M, pDst);

with M=7, N=11 and pDlyLine initialized to all zeros, everything else being same:

pDst_f and p_Dst differ in last three indices i.e pDst_f[k]!=pDst[k] for k=14,15,16

I expected them to be exactly equal with third parameter (number of iterations)=N+M-1 in the fir call. Any ideas?

Answer 1

Looks like there is indeed a problem with Intel IPP fir function, please look at this thread on Intel Developer site.

http://software.intel.com/en-us/forums/topic/331143