linux-sg2042/arch/m68k/fpsp040/do_func.S

|
|	do_func.sa 3.4 2/18/91
|
| Do_func performs the unimplemented operation.  The operation
| to be performed is determined from the lower 7 bits of the
| extension word (except in the case of fmovecr and fsincos).
| The opcode and tag bits form an index into a jump table in
| tbldo.sa.  Cases of zero, infinity and NaN are handled in
| do_func by forcing the default result.  Normalized and
| denormalized (there are no unnormalized numbers at this
| point) are passed onto the emulation code.
|
| CMDREG1B and STAG are extracted from the fsave frame
| and combined to form the table index.  The function called
| will start with a0 pointing to the ETEMP operand.  Dyadic
| functions can find FPTEMP at -12(a0).
|
| Called functions return their result in fp0.  Sincos returns
| sin(x) in fp0 and cos(x) in fp1.
|

|		Copyright (C) Motorola, Inc. 1990
|			All Rights Reserved
|
|       For details on the license for this file, please see the
|       file, README, in this same directory.

DO_FUNC:	|idnt    2,1 | Motorola 040 Floating Point Software Package

	|section	8

#include "fpsp.h"

	|xref	t_dz2
	|xref	t_operr
	|xref	t_inx2
	|xref	t_resdnrm
	|xref	dst_nan
	|xref	src_nan
	|xref	nrm_set
	|xref	sto_cos

	|xref	tblpre
	|xref	slognp1,slogn,slog10,slog2
	|xref	slognd,slog10d,slog2d
	|xref	smod,srem
	|xref	sscale
	|xref	smovcr

PONE:	.long	0x3fff0000,0x80000000,0x00000000	|+1
MONE:	.long	0xbfff0000,0x80000000,0x00000000	|-1
PZERO:	.long	0x00000000,0x00000000,0x00000000	|+0
MZERO:	.long	0x80000000,0x00000000,0x00000000	|-0
PINF:	.long	0x7fff0000,0x00000000,0x00000000	|+inf
MINF:	.long	0xffff0000,0x00000000,0x00000000	|-inf
QNAN:	.long	0x7fff0000,0xffffffff,0xffffffff	|non-signaling nan
PPIBY2:  .long	0x3FFF0000,0xC90FDAA2,0x2168C235	|+PI/2
MPIBY2:  .long	0xbFFF0000,0xC90FDAA2,0x2168C235	|-PI/2

	.global	do_func
do_func:
	clrb	CU_ONLY(%a6)
|
| Check for fmovecr.  It does not follow the format of fp gen
| unimplemented instructions.  The test is on the upper 6 bits;
| if they are $17, the inst is fmovecr.  Call entry smovcr
| directly.
|
	bfextu	CMDREG1B(%a6){#0:#6},%d0 |get opclass and src fields
	cmpil	#0x17,%d0		|if op class and size fields are $17,
|				;it is FMOVECR; if not, continue
	bnes	not_fmovecr
	jmp	smovcr		|fmovecr; jmp directly to emulation

not_fmovecr:
	movew	CMDREG1B(%a6),%d0
	andl	#0x7F,%d0
	cmpil	#0x38,%d0		|if the extension is >= $38,
	bge	serror		|it is illegal
	bfextu	STAG(%a6){#0:#3},%d1
	lsll	#3,%d0		|make room for STAG
	addl	%d1,%d0		|combine for final index into table
	leal	tblpre,%a1	|start of monster jump table
	movel	(%a1,%d0.w*4),%a1	|real target address
	leal	ETEMP(%a6),%a0	|a0 is pointer to src op
	movel	USER_FPCR(%a6),%d1
	andl	#0xFF,%d1		| discard all but rounding mode/prec
	fmovel	#0,%fpcr
	jmp	(%a1)
|
|	ERROR
|
	.global	serror
serror:
	st	STORE_FLG(%a6)
	rts
|
| These routines load forced values into fp0.  They are called
| by index into tbldo.
|
| Load a signed zero to fp0 and set inex2/ainex
|
	.global	snzrinx
snzrinx:
	btstb	#sign_bit,LOCAL_EX(%a0)	|get sign of source operand
	bnes	ld_mzinx	|if negative, branch
	bsr	ld_pzero	|bsr so we can return and set inx
	bra	t_inx2		|now, set the inx for the next inst
ld_mzinx:
	bsr	ld_mzero	|if neg, load neg zero, return here
	bra	t_inx2		|now, set the inx for the next inst
|
| Load a signed zero to fp0; do not set inex2/ainex
|
	.global	szero
szero:
	btstb	#sign_bit,LOCAL_EX(%a0) |get sign of source operand
	bne	ld_mzero	|if neg, load neg zero
	bra	ld_pzero	|load positive zero
|
| Load a signed infinity to fp0; do not set inex2/ainex
|
	.global	sinf
sinf:
	btstb	#sign_bit,LOCAL_EX(%a0)	|get sign of source operand
	bne	ld_minf			|if negative branch
	bra	ld_pinf
|
| Load a signed one to fp0; do not set inex2/ainex
|
	.global	sone
sone:
	btstb	#sign_bit,LOCAL_EX(%a0)	|check sign of source
	bne	ld_mone
	bra	ld_pone
|
| Load a signed pi/2 to fp0; do not set inex2/ainex
|
	.global	spi_2
spi_2:
	btstb	#sign_bit,LOCAL_EX(%a0)	|check sign of source
	bne	ld_mpi2
	bra	ld_ppi2
|
| Load either a +0 or +inf for plus/minus operand
|
	.global	szr_inf
szr_inf:
	btstb	#sign_bit,LOCAL_EX(%a0)	|check sign of source
	bne	ld_pzero
	bra	ld_pinf
|
| Result is either an operr or +inf for plus/minus operand
| [Used by slogn, slognp1, slog10, and slog2]
|
	.global	sopr_inf
sopr_inf:
	btstb	#sign_bit,LOCAL_EX(%a0)	|check sign of source
	bne	t_operr
	bra	ld_pinf
|
|	FLOGNP1
|
	.global	sslognp1
sslognp1:
	fmovemx (%a0),%fp0-%fp0
	fcmpb	#-1,%fp0
	fbgt	slognp1
	fbeq	t_dz2		|if = -1, divide by zero exception
	fmovel	#0,%FPSR		|clr N flag
	bra	t_operr		|take care of operands < -1
|
|	FETOXM1
|
	.global	setoxm1i
setoxm1i:
	btstb	#sign_bit,LOCAL_EX(%a0)	|check sign of source
	bne	ld_mone
	bra	ld_pinf
|
|	FLOGN
|
| Test for 1.0 as an input argument, returning +zero.  Also check
| the sign and return operr if negative.
|
	.global	sslogn
sslogn:
	btstb	#sign_bit,LOCAL_EX(%a0)
	bne	t_operr		|take care of operands < 0
	cmpiw	#0x3fff,LOCAL_EX(%a0) |test for 1.0 input
	bne	slogn
	cmpil	#0x80000000,LOCAL_HI(%a0)
	bne	slogn
	tstl	LOCAL_LO(%a0)
	bne	slogn
	fmovex	PZERO,%fp0
	rts

	.global	sslognd
sslognd:
	btstb	#sign_bit,LOCAL_EX(%a0)
	beq	slognd
	bra	t_operr		|take care of operands < 0

|
|	FLOG10
|
	.global	sslog10
sslog10:
	btstb	#sign_bit,LOCAL_EX(%a0)
	bne	t_operr		|take care of operands < 0
	cmpiw	#0x3fff,LOCAL_EX(%a0) |test for 1.0 input
	bne	slog10
	cmpil	#0x80000000,LOCAL_HI(%a0)
	bne	slog10
	tstl	LOCAL_LO(%a0)
	bne	slog10
	fmovex	PZERO,%fp0
	rts

	.global	sslog10d
sslog10d:
	btstb	#sign_bit,LOCAL_EX(%a0)
	beq	slog10d
	bra	t_operr		|take care of operands < 0

|
|	FLOG2
|
	.global	sslog2
sslog2:
	btstb	#sign_bit,LOCAL_EX(%a0)
	bne	t_operr		|take care of operands < 0
	cmpiw	#0x3fff,LOCAL_EX(%a0) |test for 1.0 input
	bne	slog2
	cmpil	#0x80000000,LOCAL_HI(%a0)
	bne	slog2
	tstl	LOCAL_LO(%a0)
	bne	slog2
	fmovex	PZERO,%fp0
	rts

	.global	sslog2d
sslog2d:
	btstb	#sign_bit,LOCAL_EX(%a0)
	beq	slog2d
	bra	t_operr		|take care of operands < 0

|
|	FMOD
|
pmodt:
|				;$21 fmod
|				;dtag,stag
	.long	smod		|  00,00  norm,norm = normal
	.long	smod_oper	|  00,01  norm,zero = nan with operr
	.long	smod_fpn	|  00,10  norm,inf  = fpn
	.long	smod_snan	|  00,11  norm,nan  = nan
	.long	smod_zro	|  01,00  zero,norm = +-zero
	.long	smod_oper	|  01,01  zero,zero = nan with operr
	.long	smod_zro	|  01,10  zero,inf  = +-zero
	.long	smod_snan	|  01,11  zero,nan  = nan
	.long	smod_oper	|  10,00  inf,norm  = nan with operr
	.long	smod_oper	|  10,01  inf,zero  = nan with operr
	.long	smod_oper	|  10,10  inf,inf   = nan with operr
	.long	smod_snan	|  10,11  inf,nan   = nan
	.long	smod_dnan	|  11,00  nan,norm  = nan
	.long	smod_dnan	|  11,01  nan,zero  = nan
	.long	smod_dnan	|  11,10  nan,inf   = nan
	.long	smod_dnan	|  11,11  nan,nan   = nan

	.global	pmod
pmod:
	clrb	FPSR_QBYTE(%a6) | clear quotient field
	bfextu	STAG(%a6){#0:#3},%d0 |stag = d0
	bfextu	DTAG(%a6){#0:#3},%d1 |dtag = d1

|
| Alias extended denorms to norms for the jump table.
|
	bclrl	#2,%d0
	bclrl	#2,%d1

	lslb	#2,%d1
	orb	%d0,%d1		|d1{3:2} = dtag, d1{1:0} = stag
|				;Tag values:
|				;00 = norm or denorm
|				;01 = zero
|				;10 = inf
|				;11 = nan
	lea	pmodt,%a1
	movel	(%a1,%d1.w*4),%a1
	jmp	(%a1)

smod_snan:
	bra	src_nan
smod_dnan:
	bra	dst_nan
smod_oper:
	bra	t_operr
smod_zro:
	moveb	ETEMP(%a6),%d1	|get sign of src op
	moveb	FPTEMP(%a6),%d0	|get sign of dst op
	eorb	%d0,%d1		|get exor of sign bits
	btstl	#7,%d1		|test for sign
	beqs	smod_zsn	|if clr, do not set sign big
	bsetb	#q_sn_bit,FPSR_QBYTE(%a6) |set q-byte sign bit
smod_zsn:
	btstl	#7,%d0		|test if + or -
	beq	ld_pzero	|if pos then load +0
	bra	ld_mzero	|else neg load -0

smod_fpn:
	moveb	ETEMP(%a6),%d1	|get sign of src op
	moveb	FPTEMP(%a6),%d0	|get sign of dst op
	eorb	%d0,%d1		|get exor of sign bits
	btstl	#7,%d1		|test for sign
	beqs	smod_fsn	|if clr, do not set sign big
	bsetb	#q_sn_bit,FPSR_QBYTE(%a6) |set q-byte sign bit
smod_fsn:
	tstb	DTAG(%a6)	|filter out denormal destination case
	bpls	smod_nrm	|
	leal	FPTEMP(%a6),%a0	|a0<- addr(FPTEMP)
	bra	t_resdnrm	|force UNFL(but exact) result
smod_nrm:
	fmovel USER_FPCR(%a6),%fpcr |use user's rmode and precision
	fmovex FPTEMP(%a6),%fp0	|return dest to fp0
	rts

|
|	FREM
|
premt:
|				;$25 frem
|				;dtag,stag
	.long	srem		|  00,00  norm,norm = normal
	.long	srem_oper	|  00,01  norm,zero = nan with operr
	.long	srem_fpn	|  00,10  norm,inf  = fpn
	.long	srem_snan	|  00,11  norm,nan  = nan
	.long	srem_zro	|  01,00  zero,norm = +-zero
	.long	srem_oper	|  01,01  zero,zero = nan with operr
	.long	srem_zro	|  01,10  zero,inf  = +-zero
	.long	srem_snan	|  01,11  zero,nan  = nan
	.long	srem_oper	|  10,00  inf,norm  = nan with operr
	.long	srem_oper	|  10,01  inf,zero  = nan with operr
	.long	srem_oper	|  10,10  inf,inf   = nan with operr
	.long	srem_snan	|  10,11  inf,nan   = nan
	.long	srem_dnan	|  11,00  nan,norm  = nan
	.long	srem_dnan	|  11,01  nan,zero  = nan
	.long	srem_dnan	|  11,10  nan,inf   = nan
	.long	srem_dnan	|  11,11  nan,nan   = nan

	.global	prem
prem:
	clrb	FPSR_QBYTE(%a6)   |clear quotient field
	bfextu	STAG(%a6){#0:#3},%d0 |stag = d0
	bfextu	DTAG(%a6){#0:#3},%d1 |dtag = d1
|
| Alias extended denorms to norms for the jump table.
|
	bclr	#2,%d0
	bclr	#2,%d1

	lslb	#2,%d1
	orb	%d0,%d1		|d1{3:2} = dtag, d1{1:0} = stag
|				;Tag values:
|				;00 = norm or denorm
|				;01 = zero
|				;10 = inf
|				;11 = nan
	lea	premt,%a1
	movel	(%a1,%d1.w*4),%a1
	jmp	(%a1)

srem_snan:
	bra	src_nan
srem_dnan:
	bra	dst_nan
srem_oper:
	bra	t_operr
srem_zro:
	moveb	ETEMP(%a6),%d1	|get sign of src op
	moveb	FPTEMP(%a6),%d0	|get sign of dst op
	eorb	%d0,%d1		|get exor of sign bits
	btstl	#7,%d1		|test for sign
	beqs	srem_zsn	|if clr, do not set sign big
	bsetb	#q_sn_bit,FPSR_QBYTE(%a6) |set q-byte sign bit
srem_zsn:
	btstl	#7,%d0		|test if + or -
	beq	ld_pzero	|if pos then load +0
	bra	ld_mzero	|else neg load -0

srem_fpn:
	moveb	ETEMP(%a6),%d1	|get sign of src op
	moveb	FPTEMP(%a6),%d0	|get sign of dst op
	eorb	%d0,%d1		|get exor of sign bits
	btstl	#7,%d1		|test for sign
	beqs	srem_fsn	|if clr, do not set sign big
	bsetb	#q_sn_bit,FPSR_QBYTE(%a6) |set q-byte sign bit
srem_fsn:
	tstb	DTAG(%a6)	|filter out denormal destination case
	bpls	srem_nrm	|
	leal	FPTEMP(%a6),%a0	|a0<- addr(FPTEMP)
	bra	t_resdnrm	|force UNFL(but exact) result
srem_nrm:
	fmovel USER_FPCR(%a6),%fpcr |use user's rmode and precision
	fmovex FPTEMP(%a6),%fp0	|return dest to fp0
	rts
|
|	FSCALE
|
pscalet:
|				;$26 fscale
|				;dtag,stag
	.long	sscale		|  00,00  norm,norm = result
	.long	sscale		|  00,01  norm,zero = fpn
	.long	scl_opr		|  00,10  norm,inf  = nan with operr
	.long	scl_snan	|  00,11  norm,nan  = nan
	.long	scl_zro		|  01,00  zero,norm = +-zero
	.long	scl_zro		|  01,01  zero,zero = +-zero
	.long	scl_opr		|  01,10  zero,inf  = nan with operr
	.long	scl_snan	|  01,11  zero,nan  = nan
	.long	scl_inf		|  10,00  inf,norm  = +-inf
	.long	scl_inf		|  10,01  inf,zero  = +-inf
	.long	scl_opr		|  10,10  inf,inf   = nan with operr
	.long	scl_snan	|  10,11  inf,nan   = nan
	.long	scl_dnan	|  11,00  nan,norm  = nan
	.long	scl_dnan	|  11,01  nan,zero  = nan
	.long	scl_dnan	|  11,10  nan,inf   = nan
	.long	scl_dnan	|  11,11  nan,nan   = nan

	.global	pscale
pscale:
	bfextu	STAG(%a6){#0:#3},%d0 |stag in d0
	bfextu	DTAG(%a6){#0:#3},%d1 |dtag in d1
	bclrl	#2,%d0		|alias  denorm into norm
	bclrl	#2,%d1		|alias  denorm into norm
	lslb	#2,%d1
	orb	%d0,%d1		|d1{4:2} = dtag, d1{1:0} = stag
|				;dtag values     stag values:
|				;000 = norm      00 = norm
|				;001 = zero	 01 = zero
|				;010 = inf	 10 = inf
|				;011 = nan	 11 = nan
|				;100 = dnrm
|
|
	leal	pscalet,%a1	|load start of jump table
	movel	(%a1,%d1.w*4),%a1	|load a1 with label depending on tag
	jmp	(%a1)		|go to the routine

scl_opr:
	bra	t_operr

scl_dnan:
	bra	dst_nan

scl_zro:
	btstb	#sign_bit,FPTEMP_EX(%a6)	|test if + or -
	beq	ld_pzero		|if pos then load +0
	bra	ld_mzero		|if neg then load -0
scl_inf:
	btstb	#sign_bit,FPTEMP_EX(%a6)	|test if + or -
	beq	ld_pinf			|if pos then load +inf
	bra	ld_minf			|else neg load -inf
scl_snan:
	bra	src_nan
|
|	FSINCOS
|
	.global	ssincosz
ssincosz:
	btstb	#sign_bit,ETEMP(%a6)	|get sign
	beqs	sincosp
	fmovex	MZERO,%fp0
	bras	sincoscom
sincosp:
	fmovex PZERO,%fp0
sincoscom:
	fmovemx PONE,%fp1-%fp1	|do not allow FPSR to be affected
	bra	sto_cos		|store cosine result

	.global	ssincosi
ssincosi:
	fmovex QNAN,%fp1	|load NAN
	bsr	sto_cos		|store cosine result
	fmovex QNAN,%fp0	|load NAN
	bra	t_operr

	.global	ssincosnan
ssincosnan:
	movel	ETEMP_EX(%a6),FP_SCR1(%a6)
	movel	ETEMP_HI(%a6),FP_SCR1+4(%a6)
	movel	ETEMP_LO(%a6),FP_SCR1+8(%a6)
	bsetb	#signan_bit,FP_SCR1+4(%a6)
	fmovemx FP_SCR1(%a6),%fp1-%fp1
	bsr	sto_cos
	bra	src_nan
|
| This code forces default values for the zero, inf, and nan cases
| in the transcendentals code.  The CC bits must be set in the
| stacked FPSR to be correctly reported.
|
|**Returns +PI/2
	.global	ld_ppi2
ld_ppi2:
	fmovex PPIBY2,%fp0		|load +pi/2
	bra	t_inx2			|set inex2 exc

|**Returns -PI/2
	.global	ld_mpi2
ld_mpi2:
	fmovex MPIBY2,%fp0		|load -pi/2
	orl	#neg_mask,USER_FPSR(%a6)	|set N bit
	bra	t_inx2			|set inex2 exc

|**Returns +inf
	.global	ld_pinf
ld_pinf:
	fmovex PINF,%fp0		|load +inf
	orl	#inf_mask,USER_FPSR(%a6)	|set I bit
	rts

|**Returns -inf
	.global	ld_minf
ld_minf:
	fmovex MINF,%fp0		|load -inf
	orl	#neg_mask+inf_mask,USER_FPSR(%a6)	|set N and I bits
	rts

|**Returns +1
	.global	ld_pone
ld_pone:
	fmovex PONE,%fp0		|load +1
	rts

|**Returns -1
	.global	ld_mone
ld_mone:
	fmovex MONE,%fp0		|load -1
	orl	#neg_mask,USER_FPSR(%a6)	|set N bit
	rts

|**Returns +0
	.global	ld_pzero
ld_pzero:
	fmovex PZERO,%fp0		|load +0
	orl	#z_mask,USER_FPSR(%a6)	|set Z bit
	rts

|**Returns -0
	.global	ld_mzero
ld_mzero:
	fmovex MZERO,%fp0		|load -0
	orl	#neg_mask+z_mask,USER_FPSR(%a6)	|set N and Z bits
	rts

	|end