Computer Hardware User's Guide

Floating-Point Conversion (IEEE Std. 754)
5-18
Example 5–4.IEEE-to-TMS320C3x Conversion (Fast Version) (Continued)
* NOTE: SINCE THE STACK POINTER SP IS USED, MAKE SURE TO
* INITIALIZE IT IN THE CALLING PROGRAM.
*
*
* CYCLES: 12 (WORST CASE) WORDS: 12
*
.global FMIEEE
*
FMIEEE AND3 R0,*AR1,R1 ; Replace fraction with 0
BND NEG ; Test sign
ADDI R0,R1 ; Shift sign
; and exponent inserting 0
LDIZ *+AR1(1),R1 ; If all 0, generate C30 0
SUBI *+AR1(2),R1 ; Unbias exponent
PUSH R1
POPF R0 ; Load this as a flt. pt. number
RETS
*
NEG PUSH R1
POPF R0 ; Load this as a flt. pt. number
NEGF R0,R0 ; Negate if orig. sign is negative
RETS
Example 5–5 shows the complete conversion between IEEE and ’C3x formats.
In addition to the general case and the 0s, it handles the special cases as follows:
If NaN (e = 255, f< >0), the number is returned intact.
If infinity (e = 255, f = 0), the output is saturated to the most positive or nega-
tive number, respectively.
If denormalized (e = 0, f< >0), two cases are considered. If the MSB of f is
1, the number is converted to ’C3x format. Otherwise an underflow occurs,
and the number is set to 0.