Computer Hardware User's Guide

Rounding (RND Instruction)
5-39
Data Formats and Floating-Point Operation
5.8 Rounding (RND Instruction)
The RND instruction rounds a number from the extended-precision floating-
point format to the single-precision floating-point format. Rounding is similar to
floating-point addition. Given the number
a
to be rounded, the following opera-
tion is performed first.
c
= α(
man
) × 2
α(
exp
)
+ (1 × 2
α(
exp
)–24
)
Next, a conversion from extended-precision floating-point to single-precision
floating-point format is performed. Given the extended-precision floating-point
value, the rounding, rnd( ), is performed as shown in Figure 5–19.
Note:
RND,
src
,
dst
—where (
src
) = 0—does not set the 0 conditions flag (bit 2 in
the status register). Instead, it sets the underflow condition flag (bit 4 in the
status register). When required, check for the underflow condition instead of
the 0 condition.