round.s

RTEMS (Real-Time Executive for Multiprocessor Systems) is a free open source real-time operating sys

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 
//				;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 
//				;while shifting
	movew	%d0,LOCAL_EX(%a0)
	movel	%d1,LOCAL_HI(%a0)
	movel	%d2,LOCAL_LO(%a0)
	moveml	(%a7)+,%d2/%d3/%d5/%d6
	rts
ms_clr:
	bfffo	%d2{#0:#32},%d3	//check if any bits set in ls mant
	beqs	all_clr		//branch if none set
	addw	#32,%d3
	cmpw	%d3,%d0		//if X>Y
	bmis	greater		//then branch
	bsr	nrm_set		//else exp won't go past 0
	moveml	(%a7)+,%d2/%d3/%d5/%d6
	rts
all_clr:
	movew	#0,LOCAL_EX(%a0)	//no mantissa bits set. Set exp = 0.
	moveml	(%a7)+,%d2/%d3/%d5/%d6
	rts
//
//	NRM_SET
//
	.global	nrm_set
nrm_set:
	movel	%d7,-(%a7)
	bfffo	LOCAL_HI(%a0){#0:#32},%d7 //find first 1 in ms mant to d7)
	beqs	lower		//branch if ms mant is all 0's

	movel	%d6,-(%a7)

	subw	%d7,LOCAL_EX(%a0)	//sub exponent by count
	movel	LOCAL_HI(%a0),%d0	//d0 has ms mant
	movel	LOCAL_LO(%a0),%d1 //d1 has ls mant

	lsll	%d7,%d0		//shift first 1 to j bit position
	movel	%d1,%d6		//copy ls mant into d6
	lsll	%d7,%d6		//shift ls mant by count
	movel	%d6,LOCAL_LO(%a0)	//store ls mant into memory
	moveql	#32,%d6
	subl	%d7,%d6		//continue shift
	lsrl	%d6,%d1		//shift off all bits but those that will
//				;be shifted into ms mant
	orl	%d1,%d0		//shift the ls mant bits into the ms mant
	movel	%d0,LOCAL_HI(%a0)	//store ms mant into memory
	moveml	(%a7)+,%d7/%d6	//restore registers
	rts

//
// 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:
	movew	LOCAL_EX(%a0),%d0	//d0 has exponent
	movel	LOCAL_LO(%a0),%d1	//d1 has ls mant
	subw	#32,%d0		//account for ms mant being all zeros
	bfffo	%d1{#0:#32},%d7	//find first 1 in ls mant to d7)
	subw	%d7,%d0		//subtract shift count from exp
	lsll	%d7,%d1		//shift first 1 to integer bit in ms mant
	movew	%d0,LOCAL_EX(%a0)	//store ms mant
	movel	%d1,LOCAL_HI(%a0)	//store exp
	clrl	LOCAL_LO(%a0)	//clear ls mant
	movel	(%a7)+,%d7
	rts
//
//	denorm --- denormalize an intermediate result
//
//	Used by underflow.
//
// Input: 
//	a0	 points to the operand to be denormalized
//		 (in the internal extended format)
//		 
//	d0: 	 rounding precision
// Output:
//	a0	 points to the denormalized result
//		 (in the internal extended format)
//
//	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 
// rounding precision.
//

	.global	denorm
denorm:
	btstb	#6,LOCAL_EX(%a0)	//check for exponents between $7fff-$4000
	beqs	no_sgn_ext	
	bsetb	#7,LOCAL_EX(%a0)	//sign extend if it is so
no_sgn_ext:

	cmpib	#0,%d0		//if 0 then extended precision
	bnes	not_ext		//else branch

	clrl	%d1		//load d1 with ext threshold
	clrl	%d0		//clear the sticky flag
	bsr	dnrm_lp		//denormalize the number
	tstb	%d1		//check for inex
	beq	no_inex		//if clr, no inex
	bras	dnrm_inex	//if set, set inex

not_ext:
	cmpil	#1,%d0		//if 1 then single precision
	beqs	load_sgl	//else must be 2, double prec

load_dbl:
	movew	#dbl_thresh,%d1	//put copy of threshold in d1
	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 
//				; shifted off in denorm routine)
	clrl	%d0		//else clear the sticky flag
	bsr	dnrm_lp		//denormalize the number
	tstb	%d1		//check flag
	beqs	no_inex		//if clr, no inex
	bras	dnrm_inex	//if set, set inex

load_sgl:
	movew	#sgl_thresh,%d1	//put copy of threshold in d1
	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 
//				; shifted off in denorm routine)
	clrl	%d0		//else clear the sticky flag
	bsr	dnrm_lp		//denormalize the number
	tstb	%d1		//check flag
	beqs	no_inex		//if clr, no inex
	bras	dnrm_inex	//if set, set inex

chk_stky:
	tstl	LOCAL_HI(%a0)	//check for any bits set
	bnes	set_stky
	tstl	LOCAL_LO(%a0)	//check for any bits set
	bnes	set_stky
	bras	clr_mant
set_stky:
	orl	#inx2a_mask,USER_FPSR(%a6) //set inex2/ainex
	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_LO(%a0)		//set d2 = 0 (ms mantissa)
	rts
dnrm_inex:
	orl	#inx2a_mask,USER_FPSR(%a6) //set inex2/ainex
no_inex:
	rts

//
//	dnrm_lp --- normalize exponent/mantissa to specified threshold
//
// Input:
//	a0		points to the operand to be denormalized
//	d0{31:29} 	initial guard,round,sticky
//	d1{15:0}	denormalization threshold
// Output:
//	a0		points to the denormalized operand
//	d0{31:29}	final guard,round,sticky
//	d1.b		inexact flag:  all ones means inexact result
//
// 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 
// is no LOCAL_GRS scratch word following it on the fsave frame.
//
	.global	dnrm_lp
dnrm_lp:
	movel	%d2,-(%sp)		//save d2 for temp use
	btstb	#E3,E_BYTE(%a6)		//test for type E3 exception
	beqs	not_E3			//not type E3 exception
	bfextu	WBTEMP_GRS(%a6){#6:#3},%d2	//extract guard,round, sticky  bit
	movel	#29,%d0
	lsll	%d0,%d2			//shift g,r,s to their positions
	movel	%d2,%d0
not_E3:
	movel	(%sp)+,%d2		//restore d2
	movel	LOCAL_LO(%a0),FP_SCR2+LOCAL_LO(%a6)
	movel	%d0,FP_SCR2+LOCAL_GRS(%a6)
	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	#64,%d1
	blts	case_2			//32 <= d1 < 64
	bra	case_3			//d1 >= 64
//
// No normalization necessary
//
no_lp:
	clrb	%d1			//set no inex2 reported
	movel	FP_SCR2+LOCAL_GRS(%a6),%d0	//restore original g,r,s
	rts
//
// case (0<d1<32)
//
case_1:
	movel	%d2,-(%sp)
	movew	%d0,LOCAL_EX(%a0)		//exponent = denorm threshold
	movel	#32,%d0
	subw	%d1,%d0			//d0 = 32 - d1
	bfextu	LOCAL_EX(%a0){%d0:#32},%d2
	bfextu	%d2{%d1:%d0},%d2		//d2 = new LOCAL_HI
	bfextu	LOCAL_HI(%a0){%d0:#32},%d1	//d1 = new LOCAL_LO
	bfextu	FP_SCR2+LOCAL_LO(%a6){%d0:#32},%d0	//d0 = new G,R,S
	movel	%d2,LOCAL_HI(%a0)		//store new LOCAL_HI
	movel	%d1,LOCAL_LO(%a0)		//store new LOCAL_LO
	clrb	%d1
	bftst	%d0{#2:#30}	
	beqs	c1nstky
	bsetl	#rnd_stky_bit,%d0
	st	%d1
c1nstky:
	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	grs_clear
	orl	#0x20000000,%d0		//set sticky bit in d0
grs_clear:
	andil	#0xe0000000,%d0		//clear all but G,R,S
	movel	(%sp)+,%d2
	rts
//
// case (32<=d1<64)
//
case_2:
	movel	%d2,-(%sp)
	movew	%d0,LOCAL_EX(%a0)		//unsigned exponent = threshold
	subw	#32,%d1			//d1 now between 0 and 32
	movel	#32,%d0
	subw	%d1,%d0			//d0 = 32 - d1
	bfextu	LOCAL_EX(%a0){%d0:#32},%d2
	bfextu	%d2{%d1:%d0},%d2		//d2 = new LOCAL_LO
	bfextu	LOCAL_HI(%a0){%d0:#32},%d1	//d1 = new G,R,S
	bftst	%d1{#2:#30}
	bnes	c2_sstky		//bra if sticky bit to be set
	bftst	FP_SCR2+LOCAL_LO(%a6){%d0:#32}
	bnes	c2_sstky		//bra if sticky bit to be set
	movel	%d1,%d0
	clrb	%d1
	bras	end_c2
c2_sstky:
	movel	%d1,%d0
	bsetl	#rnd_stky_bit,%d0
	st	%d1
end_c2:
	clrl	LOCAL_HI(%a0)		//store LOCAL_HI = 0
	movel	%d2,LOCAL_LO(%a0)		//store LOCAL_LO
	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		
	orl	#0x20000000,%d0		//set sticky bit in d0
clear_grs:
	andil	#0xe0000000,%d0		//get rid of all but G,R,S
	movel	(%sp)+,%d2
	rts
//
// d1 >= 64 Force the exponent to be the denorm threshold with the
// correct sign.
//
case_3:
	movew	%d0,LOCAL_EX(%a0)
	tstw	LOCAL_SGN(%a0)
	bges	c3con
c3neg:
	orl	#0x80000000,LOCAL_EX(%a0)
c3con:
	cmpw	#64,%d1
	beqs	sixty_four
	cmpw	#65,%d1
	beqs	sixty_five
//
// Shift value is out of range.  Set d1 for inex2 flag and
// return a zero with the given threshold.
//
	clrl	LOCAL_HI(%a0)
	clrl	LOCAL_LO(%a0)
	movel	#0x20000000,%d0
	st	%d1
	rts

sixty_four:
	movel	LOCAL_HI(%a0),%d0
	bfextu	%d0{#2:#30},%d1
	andil	#0xc0000000,%d0
	bras	c3com
	
sixty_five:
	movel	LOCAL_HI(%a0),%d0
	bfextu	%d0{#1:#31},%d1
	andil	#0x80000000,%d0
	lsrl	#1,%d0			//shift high bit into R bit

c3com:
	tstl	%d1
	bnes	c3ssticky
	tstl	LOCAL_LO(%a0)
	bnes	c3ssticky
	tstb	FP_SCR2+LOCAL_GRS(%a6)
	bnes	c3ssticky
	clrb	%d1
	bras	c3end

c3ssticky:
	bsetl	#rnd_stky_bit,%d0
	st	%d1
c3end:
	clrl	LOCAL_HI(%a0)
	clrl	LOCAL_LO(%a0)
	rts

	|end