Hello,
I am trying to use some ready microcode on my DSP for filter but results
for eg Highpass filter differ . Manual says
> For these architectures (e.g. Blackfin and Coldfire), a better approach
> is to implement those
> functions as direct form I (DF1), which is easier to express in terms of
> MAC. When doing that however, it is important to
> make sure that the DF1 implementation still behaves like the original DF2T
> behaviour when it comes to filter values.
> This is necessary because the filter is time-varrying and must compute
> exactly the same value (not countingmachine rounding)
> on any encoder or decoder.
However floating point differs from fixed . Should results be identical ?
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://lists.xiph.org/pipermail/speex-dev/attachments/20141029/0fc0b63f/attachment.htm