* MOTOROLA MICROPROCESSOR & MEMORY TECHNOLOGY GROUP
* M68000 Hi-Performance Microprocessor Division
* M68040 Software Package
*
* M68040 Software Package Copyright (c) 1993, 1994 Motorola Inc.
* All rights reserved.
*
* THE SOFTWARE is provided on an "AS IS" basis and without warranty.
* To the maximum extent permitted by applicable law,
* MOTOROLA DISCLAIMS ALL WARRANTIES WHETHER EXPRESS OR IMPLIED,
* INCLUDING IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A
* PARTICULAR PURPOSE and any warranty against infringement with
* regard to the SOFTWARE (INCLUDING ANY MODIFIED VERSIONS THEREOF)
* and any accompanying written materials.
*
* To the maximum extent permitted by applicable law,
* IN NO EVENT SHALL MOTOROLA BE LIABLE FOR ANY DAMAGES WHATSOEVER
* (INCLUDING WITHOUT LIMITATION, DAMAGES FOR LOSS OF BUSINESS
* PROFITS, BUSINESS INTERRUPTION, LOSS OF BUSINESS INFORMATION, OR
* OTHER PECUNIARY LOSS) ARISING OF THE USE OR INABILITY TO USE THE
* SOFTWARE. Motorola assumes no responsibility for the maintenance
* and support of the SOFTWARE.
*
* You are hereby granted a copyright license to use, modify, and
* distribute the SOFTWARE so long as this entire notice is retained
* without alteration in any modified and/or redistributed versions,
* and that such modified versions are clearly identified as such.
* No licenses are granted by implication, estoppel or otherwise
* under any patents or trademarks of Motorola, Inc.
*
* util.sa 3.7 7/29/91
*
* This file contains routines used by other programs.
*
* ovf_res: used by overflow to force the correct
* result. ovf_r_k, ovf_r_x2, ovf_r_x3 are
* derivatives of this routine.
* get_fline: get user's opcode word
* g_dfmtou: returns the destination format.
* g_opcls: returns the opclass of the float instruction.
* g_rndpr: returns the rounding precision.
* reg_dest: write byte, word, or long data to Dn
*
UTIL IDNT 2,1 Motorola 040 Floating Point Software Package
*
* Final result table for ovf_res. Note that the negative counterparts
* are unnecessary as ovf_res always returns the sign separately from
* the exponent.
* ;+inf
EXT_PINF dc.l $7fff0000,$00000000,$00000000,$00000000
* ;largest +ext
EXT_PLRG dc.l $7ffe0000,$ffffffff,$ffffffff,$00000000
* ;largest magnitude +sgl in ext
SGL_PLRG dc.l $407e0000,$ffffff00,$00000000,$00000000
* ;largest magnitude +dbl in ext
DBL_PLRG dc.l $43fe0000,$ffffffff,$fffff800,$00000000
* ;largest -ext
*
* ovf_r_k --- overflow result calculation
*
* This entry point is used by kernel_ex.
*
* This forces the destination precision to be extended
*
* Input: operand in ETEMP
* Output: a result is in ETEMP (internal extended format)
*
xdef ovf_r_k
ovf_r_k:
lea ETEMP(a6),a0 ;a0 points to source operand
bclr.b #sign_bit,ETEMP_EX(a6)
sne ETEMP_SGN(a6) ;convert to internal IEEE format
*
* ovf_r_x2 --- overflow result calculation
*
* This entry point used by x_ovfl. (opclass 0 and 2)
*
* Input a0 points to an operand in the internal extended format
* Output a0 points to the result in the internal extended format
*
* This sets the round precision according to the user's FPCR unless the
* instruction is fsgldiv or fsglmul or fsadd, fdadd, fsub, fdsub, fsmul,
* fdmul, fsdiv, fddiv, fssqrt, fsmove, fdmove, fsabs, fdabs, fsneg, fdneg.
* If the instruction is fsgldiv of fsglmul, the rounding precision must be
* extended. If the instruction is not fsgldiv or fsglmul but a force-
* precision instruction, the rounding precision is then set to the force
* precision.
xdef ovf_r_x2
ovf_r_x2:
btst.b #E3,E_BYTE(a6) ;check for nu exception
beq.l ovf_e1_exc ;it is cu exception
ovf_e3_exc:
move.w CMDREG3B(a6),d0 ;get the command word
andi.w #$00000060,d0 ;clear all bits except 6 and 5
cmpi.l #$00000040,d0
beq.l ovff_sgl ;force precision is single
cmpi.l #$00000060,d0
beq.l ovff_dbl ;force precision is double
move.w CMDREG3B(a6),d0 ;get the command word again
andi.l #$7f,d0 ;clear all except operation
cmpi.l #$33,d0
beq.l ovf_fsgl ;fsglmul or fsgldiv
cmpi.l #$30,d0
beq.l ovf_fsgl
bra ovf_fpcr ;instruction is none of the above
* ;use FPCR
ovf_e1_exc:
move.w CMDREG1B(a6),d0 ;get command word
andi.l #$00000044,d0 ;clear all bits except 6 and 2
cmpi.l #$00000040,d0
beq.l ovff_sgl ;the instruction is force single
cmpi.l #$00000044,d0
beq.l ovff_dbl ;the instruction is force double
move.w CMDREG1B(a6),d0 ;again get the command word
andi.l #$0000007f,d0 ;clear all except the op code
cmpi.l #$00000027,d0
beq.l ovf_fsgl ;fsglmul
cmpi.l #$00000024,d0
beq.l ovf_fsgl ;fsgldiv
bra ovf_fpcr ;none of the above, use FPCR
*
*
* Inst is either fsgldiv or fsglmul. Force extended precision.
*
ovf_fsgl:
clr.l d0
bra.b short_ovf_res
ovff_sgl:
move.l #$00000001,d0 ;set single
bra.b short_ovf_res
ovff_dbl:
move.l #$00000002,d0 ;set double
bra.b short_ovf_res
*
* The precision is in the fpcr.
*
ovf_fpcr:
bfextu FPCR_MODE(a6){0:2},d0 ;set round precision
bra.b short_ovf_res
*
*
* ovf_r_x3 --- overflow result calculation
*
* This entry point used by x_ovfl. (opclass 3 only)
*
* Input a0 points to an operand in the internal extended format
* Output a0 points to the result in the internal extended format
*
* This sets the round precision according to the destination size.
*
xdef ovf_r_x3
ovf_r_x3:
bsr g_dfmtou ;get dest fmt in d0{1:0}
* ;for fmovout, the destination format
* ;is the rounding precision
*
* ovf_res --- overflow result calculation
*
* Input:
* a0 points to operand in internal extended format
* Output:
* a0 points to result in internal extended format
*
xdef ovf_res
ovf_res:
short_ovf_res:
lsl.l #2,d0 ;move round precision to d0{3:2}
bfextu FPCR_MODE(a6){2:2},d1 ;set round mode
or.l d1,d0 ;index is fmt:mode in d0{3:0}
lea.l tblovfl,a1 ;load a1 with table address
move.l (a1,d0*4),a1 ;use d0 as index to the table
jmp (a1) ;go to the correct routine
*
*case DEST_FMT = EXT
*
EXT_RN:
lea.l EXT_PINF,a1 ;answer is +/- infinity
bset.b #inf_bit,FPSR_CC(a6)
bra set_sign ;now go set the sign
EXT_RZ:
lea.l EXT_PLRG,a1 ;answer is +/- large number
bra set_sign ;now go set the sign
EXT_RM:
tst.b LOCAL_SGN(a0) ;if negative overflow
beq.b e_rm_pos
e_rm_neg:
lea.l EXT_PINF,a1 ;answer is negative infinity
or.l #neginf_mask,USER_FPSR(a6)
bra end_ovfr
e_rm_pos:
lea.l EXT_PLRG,a1 ;answer is large positive number
bra end_ovfr
EXT_RP:
tst.b LOCAL_SGN(a0) ;if negative overflow
beq.b e_rp_pos
e_rp_neg:
lea.l EXT_PLRG,a1 ;answer is large negative number
bset.b #neg_bit,FPSR_CC(a6)
bra end_ovfr
e_rp_pos:
lea.l EXT_PINF,a1 ;answer is positive infinity
bset.b #inf_bit,FPSR_CC(a6)
bra end_ovfr
*
*case DEST_FMT = DBL
*
DBL_RN:
lea.l EXT_PINF,a1 ;answer is +/- infinity
bset.b #inf_bit,FPSR_CC(a6)
bra set_sign
DBL_RZ:
lea.l DBL_PLRG,a1 ;answer is +/- large number
bra set_sign ;now go set the sign
DBL_RM:
tst.b LOCAL_SGN(a0) ;if negative overflow
beq.b d_rm_pos
d_rm_neg:
lea.l EXT_PINF,a1 ;answer is negative infinity
or.l #neginf_mask,USER_FPSR(a6)
bra end_ovfr ;inf is same for all precisions (ext,dbl,sgl)
d_rm_pos:
lea.l DBL_PLRG,a1 ;answer is large positive number
bra end_ovfr
DBL_RP:
tst.b LOCAL_SGN(a0) ;if negative overflow
beq.b d_rp_pos
d_rp_neg:
lea.l DBL_PLRG,a1 ;answer is large negative number
bset.b #neg_bit,FPSR_CC(a6)
bra end_ovfr
d_rp_pos:
lea.l EXT_PINF,a1 ;answer is positive infinity
bset.b #inf_bit,FPSR_CC(a6)
bra end_ovfr
*
*case DEST_FMT = SGL
*
SGL_RN:
lea.l EXT_PINF,a1 ;answer is +/- infinity
bset.b #inf_bit,FPSR_CC(a6)
bra.b set_sign
SGL_RZ:
lea.l SGL_PLRG,a1 ;anwer is +/- large number
bra.b set_sign
SGL_RM:
tst.b LOCAL_SGN(a0) ;if negative overflow
beq.b s_rm_pos
s_rm_neg:
lea.l EXT_PINF,a1 ;answer is negative infinity
or.l #neginf_mask,USER_FPSR(a6)
bra.b end_ovfr
s_rm_pos:
lea.l SGL_PLRG,a1 ;answer is large positive number
bra.b end_ovfr
SGL_RP:
tst.b LOCAL_SGN(a0) ;if negative overflow
beq.b s_rp_pos
s_rp_neg:
lea.l SGL_PLRG,a1 ;answer is large negative number
bset.b #neg_bit,FPSR_CC(a6)
bra.b end_ovfr
s_rp_pos:
lea.l EXT_PINF,a1 ;answer is positive infinity
bset.b #inf_bit,FPSR_CC(a6)
bra.b end_ovfr
*
* ERROR
*
error:
rts
*
* get_fline --- get f-line opcode of interrupted instruction
*
* Returns opcode in the low word of d0.
*
get_fline:
move.l USER_FPIAR(a6),a0 ;opcode address
clr.l -(a7) ;reserve a word on the stack
lea.l 2(a7),a1 ;point to low word of temporary
move.l #2,d0 ;count
bsr.l mem_read
move.l (a7)+,d0
rts
*
* g_rndpr --- put rounding precision in d0{1:0}
*
* valid return codes are:
* 00 - extended
* 01 - single
* 10 - double
*
* begin
* get rounding precision (cmdreg3b{6:5})
* begin
* case opclass = 011 (move out)
* get destination format - this is the also the rounding precision
*
* case opclass = 0x0
* if E3
* *case RndPr(from cmdreg3b{6:5} = 11 then RND_PREC = DBL
* *case RndPr(from cmdreg3b{6:5} = 10 then RND_PREC = SGL
* case RndPr(from cmdreg3b{6:5} = 00 | 01
* use precision from FPCR{7:6}
* case 00 then RND_PREC = EXT
* case 01 then RND_PREC = SGL
* case 10 then RND_PREC = DBL
* else E1
* use precision in FPCR{7:6}
* case 00 then RND_PREC = EXT
* case 01 then RND_PREC = SGL
* case 10 then RND_PREC = DBL
* end
*
g_rndpr:
bsr.w g_opcls ;get opclass in d0{2:0}
cmp.w #$0003,d0 ;check for opclass 011
bne.b op_0x0
*
* For move out instructions (opclass 011) the destination format
* is the same as the rounding precision. Pass results from g_dfmtou.
*
bsr.w g_dfmtou
rts
op_0x0:
btst.b #E3,E_BYTE(a6)
beq.l unf_e1_exc ;branch to e1 underflow
unf_e3_exc:
move.l CMDREG3B(a6),d0 ;rounding precision in d0{10:9}
bfextu d0{9:2},d0 ;move the rounding prec bits to d0{1:0}
cmpi.l #$2,d0
beq.l unff_sgl ;force precision is single
cmpi.l #$3,d0 ;force precision is double
beq.l unff_dbl
move.w CMDREG3B(a6),d0 ;get the command word again
andi.l #$7f,d0 ;clear all except operation
cmpi.l #$33,d0
beq.l unf_fsgl ;fsglmul or fsgldiv
cmpi.l #$30,d0
beq.l unf_fsgl ;fsgldiv or fsglmul
bra unf_fpcr
unf_e1_exc:
move.l CMDREG1B(a6),d0 ;get 32 bits off the stack, 1st 16 bits
* ;are the command word
andi.l #$00440000,d0 ;clear all bits except bits 6 and 2
cmpi.l #$00400000,d0
beq.l unff_sgl ;force single
cmpi.l #$00440000,d0 ;force double
beq.l unff_dbl
move.l CMDREG1B(a6),d0 ;get the command word again
andi.l #$007f0000,d0 ;clear all bits except the operation
cmpi.l #$00270000,d0
beq.l unf_fsgl ;fsglmul
cmpi.l #$00240000,d0
beq.l unf_fsgl ;fsgldiv
bra unf_fpcr
*
* Convert to return format. The values from cmdreg3b and the return
* values are:
* cmdreg3b return precision
* -------- ------ ---------
* 00,01 0 ext
* 10 1 sgl
* 11 2 dbl
* Force single
*
unff_sgl:
move.l #1,d0 ;return 1
rts
*
* Force double
*
unff_dbl:
move.l #2,d0 ;return 2
rts
*
* Force extended
*
unf_fsgl:
clr.l d0
rts
*
* Get rounding precision set in FPCR{7:6}.
*
unf_fpcr:
move.l USER_FPCR(a6),d0 ;rounding precision bits in d0{7:6}
bfextu d0{24:2},d0 ;move the rounding prec bits to d0{1:0}
rts
*
* g_opcls --- put opclass in d0{2:0}
*
g_opcls:
btst.b #E3,E_BYTE(a6)
beq.b opc_1b ;if set, go to cmdreg1b
opc_3b:
clr.l d0 ;if E3, only opclass 0x0 is possible
rts
opc_1b:
move.l CMDREG1B(a6),d0
bfextu d0{0:3},d0 ;shift opclass bits d0{31:29} to d0{2:0}
rts
*
* g_dfmtou --- put destination format in d0{1:0}
*
* If E1, the format is from cmdreg1b{12:10}
* If E3, the format is extended.
*
* Dest. Fmt.
* extended 010 -> 00
* single 001 -> 01
* double 101 -> 10
*
g_dfmtou:
btst.b #E3,E_BYTE(a6)
beq.b op011
clr.l d0 ;if E1, size is always ext
rts
op011:
move.l CMDREG1B(a6),d0
bfextu d0{3:3},d0 ;dest fmt from cmdreg1b{12:10}
cmp.b #1,d0 ;check for single
bne.b not_sgl
move.l #1,d0
rts
not_sgl:
cmp.b #5,d0 ;check for double
bne.b not_dbl
move.l #2,d0
rts
not_dbl:
clr.l d0 ;must be extended
rts
*
*
* Final result table for unf_sub. Note that the negative counterparts
* are unnecessary as unf_sub always returns the sign separately from
* the exponent.
* ;+zero
EXT_PZRO dc.l $00000000,$00000000,$00000000,$00000000
* ;+zero
SGL_PZRO dc.l $3f810000,$00000000,$00000000,$00000000
* ;+zero
DBL_PZRO dc.l $3c010000,$00000000,$00000000,$00000000
* ;smallest +ext denorm
EXT_PSML dc.l $00000000,$00000000,$00000001,$00000000
* ;smallest +sgl denorm
SGL_PSML dc.l $3f810000,$00000100,$00000000,$00000000
* ;smallest +dbl denorm
DBL_PSML dc.l $3c010000,$00000000,$00000800,$00000000
*
* UNF_SUB --- underflow result calculation
*
* Input:
* d0 contains round precision
* a0 points to input operand in the internal extended format
*
* Output:
* a0 points to correct internal extended precision result.
*
