As many Intel IPP functions have to meet the bit-exact requirement, general sygnal processing functions use rounding. The default rounding mode for all these functions can be described as "nearest even", that is the fixed point number x=N + α, 0 ≤ α < 0, where N is an integer number, is rounded as given by:
For example, 1.5 will be rounded to 2 and 2.5 to 2.
Some functions have additional rounding modes, which are set by the parameter roundMode.
Note
Functions for data compression, data integrity, string processing and fixed-accuracy arithmetic do not perform rounding.
Note
Functions for speech coding have special rounding modes (see Rounding Modes for Speech Codecs).