| Copyright (C) Motorola, Inc. 1990
| All Rights Reserved
|
-| THIS IS UNPUBLISHED PROPRIETARY SOURCE CODE OF MOTOROLA
-| The copyright notice above does not evidence any
+| THIS IS UNPUBLISHED PROPRIETARY SOURCE CODE OF MOTOROLA
+| The copyright notice above does not evidence any
| actual or intended publication of such source code.
|ROUND idnt 2,1 | Motorola 040 Floating Point Software Package
|
| round --- round result according to precision/mode
|
-| a0 points to the input operand in the internal extended format
+| a0 points to the input operand in the internal extended format
| d1(high word) contains rounding precision:
| ext = $0000xxxx
| sgl = $0001xxxx
.global round
round:
-| If g=r=s=0 then result is exact and round is done, else set
-| the inex flag in status reg and continue.
+| If g=r=s=0 then result is exact and round is done, else set
+| the inex flag in status reg and continue.
|
- bsrs ext_grs |this subroutine looks at the
-| :rounding precision and sets
+ bsrs ext_grs |this subroutine looks at the
+| :rounding precision and sets
| ;the appropriate g-r-s bits.
tstl %d0 |if grs are zero, go force
bne rnd_cont |lower bits to zero for size
-
+
swap %d1 |set up d1.w for round prec.
bra truncate
| If sign of fp number = 0 (positive), then add 1 to l.
|
rnd_plus:
- swap %d1 |set up d1 for round prec.
+ swap %d1 |set up d1 for round prec.
tstb LOCAL_SGN(%a0) |check for sign
bmi truncate |if positive then truncate
movel #0xffffffff,%d0 |force g,r,s to be all f's
| If sign of fp number = 1 (negative), then add 1 to l.
|
rnd_mnus:
- swap %d1 |set up d1 for round prec.
- tstb LOCAL_SGN(%a0) |check for sign
+ swap %d1 |set up d1 for round prec.
+ tstb LOCAL_SGN(%a0) |check for sign
bpl truncate |if negative then truncate
movel #0xffffffff,%d0 |force g,r,s to be all f's
lea add_to_l,%a1
|
| Always truncate.
rnd_zero:
- swap %d1 |set up d1 for round prec.
+ swap %d1 |set up d1 for round prec.
bra truncate
|
|
| Note that this will round to even in case of a tie.
|
rnd_near:
- swap %d1 |set up d1 for round prec.
+ swap %d1 |set up d1 for round prec.
asll #1,%d0 |shift g-bit to c-bit
bcc truncate |if (g=1) then
lea add_to_l,%a1
| ext_grs --- extract guard, round and sticky bits
|
| Input: d1 = PREC:ROUND
-| Output: d0{31:29}= guard, round, sticky
+| Output: d0{31:29}= guard, round, sticky
|
| The ext_grs extract the guard/round/sticky bits according to the
| selected rounding precision. It is called by the round subroutine
-| only. All registers except d0 are kept intact. d0 becomes an
+| only. All registers except d0 are kept intact. d0 becomes an
| updated guard,round,sticky in d0{31:29}
|
| Notes: the ext_grs uses the round PREC, and therefore has to swap d1
cmpiw #0,%d1
bnes sgl_or_dbl
bras end_ext_grs
-
+
sgl_or_dbl:
moveml %d2/%d3,-(%a7) |make some temp registers
cmpiw #1,%d1
movel #30,%d2 |of the sgl prec. limits
lsll %d2,%d3 |shift g-r bits to MSB of d3
movel LOCAL_HI(%a0),%d2 |get word 2 for s-bit test
- andil #0x0000003f,%d2 |s bit is the or of all other
+ andil #0x0000003f,%d2 |s bit is the or of all other
bnes st_stky |bits to the right of g-r
tstl LOCAL_LO(%a0) |test lower mantissa
bnes st_stky |if any are set, set sticky
tstl %d0 |test original g,r,s
bnes st_stky |if any are set, set sticky
bras end_sd |if words 3 and 4 are clr, exit
-grs_dbl:
+grs_dbl:
bfextu LOCAL_LO(%a0){#21:#2},%d3 |dbl-prec. g-r are 2 bits right
movel #30,%d2 |of the dbl prec. limits
lsll %d2,%d3 |shift g-r bits to the MSB of d3
movel LOCAL_LO(%a0),%d2 |get lower mantissa for s-bit test
- andil #0x000001ff,%d2 |s bit is the or-ing of all
+ andil #0x000001ff,%d2 |s bit is the or-ing of all
bnes st_stky |other bits to the right of g-r
tstl %d0 |test word original g,r,s
bnes st_stky |if any are set, set sticky
|
| NORMALIZE
|
-| These routines (nrm_zero & nrm_set) normalize the unnorm. This
-| is done by shifting the mantissa left while decrementing the
+| These routines (nrm_zero & nrm_set) normalize the unnorm. This
+| is done by shifting the mantissa left while decrementing the
| exponent.
|
-| NRM_SET shifts and decrements until there is a 1 set in the integer
+| NRM_SET shifts and decrements until there is a 1 set in the integer
| bit of the mantissa (msb in d1).
|
-| NRM_ZERO shifts and decrements until there is a 1 set in the integer
-| bit of the mantissa (msb in d1) unless this would mean the exponent
-| would go less than 0. In that case the number becomes a denorm - the
-| exponent (d0) is set to 0 and the mantissa (d1 & d2) is not
+| NRM_ZERO shifts and decrements until there is a 1 set in the integer
+| bit of the mantissa (msb in d1) unless this would mean the exponent
+| would go less than 0. In that case the number becomes a denorm - the
+| exponent (d0) is set to 0 and the mantissa (d1 & d2) is not
| normalized.
|
-| Note that both routines have been optimized (for the worst case) and
+| Note that both routines have been optimized (for the worst case) and
| therefore do not have the easy to follow decrement/shift loop.
|
| NRM_ZERO
.global nrm_zero
nrm_zero:
movew LOCAL_EX(%a0),%d0
- cmpw #64,%d0 |see if exp > 64
+ cmpw #64,%d0 |see if exp > 64
bmis d0_less
- bsr nrm_set |exp > 64 so exp won't exceed 0
+ bsr nrm_set |exp > 64 so exp won't exceed 0
rts
d0_less:
moveml %d2/%d3/%d5/%d6,-(%a7)
movel LOCAL_HI(%a0),%d1
movel LOCAL_LO(%a0),%d2
- bfffo %d1{#0:#32},%d3 |get the distance to the first 1
+ bfffo %d1{#0:#32},%d3 |get the distance to the first 1
| ;in ms mant
beqs ms_clr |branch if no bits were set
cmpw %d3,%d0 |of X>Y
- bmis greater |then exp will go past 0 (neg) if
+ bmis greater |then exp will go past 0 (neg) if
| ;it is just shifted
bsr nrm_set |else exp won't go past 0
moveml (%a7)+,%d2/%d3/%d5/%d6
- rts
+ rts
greater:
movel %d2,%d6 |save ls mant in d6
lsll %d0,%d2 |shift ls mant by count
lsll %d0,%d1 |shift ms mant by count
movel #32,%d5
- subl %d0,%d5 |make op a denorm by shifting bits
- lsrl %d5,%d6 |by the number in the exp, then
+ subl %d0,%d5 |make op a denorm by shifting bits
+ lsrl %d5,%d6 |by the number in the exp, then
| ;set exp = 0.
orl %d6,%d1 |shift the ls mant bits into the ms mant
- movel #0,%d0 |same as if decremented exp to 0
+ movel #0,%d0 |same as if decremented exp to 0
| ;while shifting
movew %d0,LOCAL_EX(%a0)
movel %d1,LOCAL_HI(%a0)
rts
|
-| We get here if ms mant was = 0, and we assume ls mant has bits
+| We get here if ms mant was = 0, and we assume ls mant has bits
| set (otherwise this would have been tagged a zero not a denorm).
|
lower:
|
| Used by underflow.
|
-| Input:
+| Input:
| a0 points to the operand to be denormalized
| (in the internal extended format)
-|
-| d0: rounding precision
+|
+| d0: rounding precision
| Output:
| a0 points to the denormalized result
| (in the internal extended format)
|
-| d0 is guard,round,sticky
+| d0 is guard,round,sticky
|
-| d0 comes into this routine with the rounding precision. It
-| is then loaded with the denormalized exponent threshold for the
+| d0 comes into this routine with the rounding precision. It
+| is then loaded with the denormalized exponent threshold for the
| rounding precision.
|
.global denorm
denorm:
btstb #6,LOCAL_EX(%a0) |check for exponents between $7fff-$4000
- beqs no_sgn_ext
+ beqs no_sgn_ext
bsetb #7,LOCAL_EX(%a0) |sign extend if it is so
no_sgn_ext:
movel %d1,%d0 |copy d1 into d0
subw LOCAL_EX(%a0),%d0 |diff = threshold - exp
cmpw #67,%d0 |if diff > 67 (mant + grs bits)
- bpls chk_stky |then branch (all bits would be
+ bpls chk_stky |then branch (all bits would be
| ; shifted off in denorm routine)
clrl %d0 |else clear the sticky flag
bsr dnrm_lp |denormalize the number
movel %d1,%d0 |copy d1 into d0
subw LOCAL_EX(%a0),%d0 |diff = threshold - exp
cmpw #67,%d0 |if diff > 67 (mant + grs bits)
- bpls chk_stky |then branch (all bits would be
+ bpls chk_stky |then branch (all bits would be
| ; shifted off in denorm routine)
clrl %d0 |else clear the sticky flag
bsr dnrm_lp |denormalize the number
movel #0x20000000,%d0 |set sticky bit in return value
clr_mant:
movew %d1,LOCAL_EX(%a0) |load exp with threshold
- movel #0,LOCAL_HI(%a0) |set d1 = 0 (ms mantissa)
+ movel #0,LOCAL_HI(%a0) |set d1 = 0 (ms mantissa)
movel #0,LOCAL_LO(%a0) |set d2 = 0 (ms mantissa)
rts
dnrm_inex:
|
| Input:
| a0 points to the operand to be denormalized
-| d0{31:29} initial guard,round,sticky
+| d0{31:29} initial guard,round,sticky
| d1{15:0} denormalization threshold
| Output:
| a0 points to the denormalized operand
|
| The LOCAL_LO and LOCAL_GRS parts of the value are copied to FP_SCR2
| so that bfext can be used to extract the new low part of the mantissa.
-| Dnrm_lp can be called with a0 pointing to ETEMP or WBTEMP and there
+| Dnrm_lp can be called with a0 pointing to ETEMP or WBTEMP and there
| is no LOCAL_GRS scratch word following it on the fsave frame.
|
.global dnrm_lp
movel %d1,%d0 |copy the denorm threshold
subw LOCAL_EX(%a0),%d1 |d1 = threshold - uns exponent
bles no_lp |d1 <= 0
- cmpw #32,%d1
- blts case_1 |0 = d1 < 32
+ cmpw #32,%d1
+ blts case_1 |0 = d1 < 32
cmpw #64,%d1
blts case_2 |32 <= d1 < 64
bra case_3 |d1 >= 64
movel %d2,LOCAL_HI(%a0) |store new LOCAL_HI
movel %d1,LOCAL_LO(%a0) |store new LOCAL_LO
clrb %d1
- bftst %d0{#2:#30}
+ bftst %d0{#2:#30}
beqs c1nstky
bsetl #rnd_stky_bit,%d0
st %d1
movel FP_SCR2+LOCAL_GRS(%a6),%d2 |restore original g,r,s
andil #0xe0000000,%d2 |clear all but G,R,S
tstl %d2 |test if original G,R,S are clear
- beqs clear_grs
+ beqs clear_grs
orl #0x20000000,%d0 |set sticky bit in d0
clear_grs:
andil #0xe0000000,%d0 |get rid of all but G,R,S
bfextu %d0{#2:#30},%d1
andil #0xc0000000,%d0
bras c3com
-
+
sixty_five:
movel LOCAL_HI(%a0),%d0
bfextu %d0{#1:#31},%d1