Analog Devices ADSP-BF53x Blackfin Reference page 58

Glossary
Some instructions for this processor support biased and unbiased round-
ing. The
RND_MOD
which mode is used. See the Blackfin Processor Hardware Reference for your
specific product for more details on the
Another common way to reduce the significant bits representing a number
is to simply mask off the N-M lower bits. This process is known as trunca-
tion and results in a relatively large bias.
Figure 1-3 shows other examples of rounding and truncation methods.
0 1
0 1
0 1
0 1
0 1
0 1
0 1
0 1
Figure 1-3. 8-Bit Number Reduced to 4 Bits of Precision
1-20 ADSP-BF53x/BF56x Blackfin Processor Programming Reference
bit in the Arithmetic Status (
0 0 1 0
0 1
0 0
0 0
0 0 1 0
0 1
0 1
0 0
) Register determines
ASTAT
Register.
ASTAT
0 0 original 8-bit number (0.5625)
4-bit biased rounding (0.625)
4-bit unbiased rounding (0.5)
4-bit truncation (0.5)
1 0 original 8-bit number (0.578125)
4-bit biased rounding (0.625)
4-bit unbiased rounding (0.625)
4-bit truncation (0.5)