sparcv9a-mont.pl

著名的开源密码源代码

	std	$nlod,[%sp+$bias+$frame+24]

	addcc	$j,8,$j
	bnz,pt	%icc,.L1st
	add	$tp,8,$tp

.L1stskip:
	fdtox	$dota,$dota
	fdtox	$dotb,$dotb

	ldx	[%sp+$bias+$frame+0],%o0
	ldx	[%sp+$bias+$frame+8],%o1
	ldx	[%sp+$bias+$frame+16],%o2
	ldx	[%sp+$bias+$frame+24],%o3

	srlx	%o0,16,%o7
	std	$dota,[%sp+$bias+$frame+32]
	add	%o7,%o1,%o1
	std	$dotb,[%sp+$bias+$frame+40]
	srlx	%o1,16,%o7
	add	%o7,%o2,%o2
	srlx	%o2,16,%o7
	add	%o7,%o3,%o3		! %o3.%o2[0..15].%o1[0..15].%o0[0..15]
	and	%o0,$mask,%o0
	and	%o1,$mask,%o1
	and	%o2,$mask,%o2
	sllx	%o1,16,%o1
	sllx	%o2,32,%o2
	sllx	%o3,48,%o7
	or	%o1,%o0,%o0
	or	%o2,%o0,%o0
	or	%o7,%o0,%o0		! 64-bit result
	ldx	[%sp+$bias+$frame+32],%o4
	addcc	%g1,%o0,%o0
	ldx	[%sp+$bias+$frame+40],%o5
	srlx	%o3,16,%g1		! 34-bit carry
	bcs,a	%xcc,.+8
	add	%g1,1,%g1

	stx	%o0,[$tp]		! tp[j-1]=
	add	$tp,8,$tp

	srlx	%o4,16,%o7
	add	%o7,%o5,%o5
	and	%o4,$mask,%o4
	sllx	%o5,16,%o7
	or	%o7,%o4,%o4
	addcc	%g1,%o4,%o4
	srlx	%o5,48,%g1
	bcs,a	%xcc,.+8
	add	%g1,1,%g1

	mov	%g1,$carry
	stx	%o4,[$tp]		! tp[num-1]=

	ba	.Louter
	add	$i,8,$i
.align	32
.Louter:
	sub	%g0,$num,$j		! j=-num
	add	%sp,$bias+$frame+$locals,$tp

	add	$ap,$j,%o3
	add	$bp,$i,%o4

	ld	[%o3+4],%g1		! bp[i]
	ld	[%o3+0],%o0
	ld	[%o4+4],%g5		! ap[0]
	sllx	%g1,32,%g1
	ld	[%o4+0],%o1
	sllx	%g5,32,%g5
	or	%g1,%o0,%o0
	or	%g5,%o1,%o1

	ldx	[$tp],%o2		! tp[0]
	mulx	%o1,%o0,%o0
	addcc	%o2,%o0,%o0
	mulx	$n0,%o0,%o0		! (ap[0]*bp[i]+t[0])*n0
	stx	%o0,[%sp+$bias+$frame+0]

	! transfer b[i] to FPU as 4x16-bit values
	ldda	[%o4+2]%asi,$ba
	ldda	[%o4+0]%asi,$bb
	ldda	[%o4+6]%asi,$bc
	ldda	[%o4+4]%asi,$bd

	! transfer (ap[0]*b[i]+t[0])*n0 to FPU as 4x16-bit values
	ldda	[%sp+$bias+$frame+6]%asi,$na
	fxtod	$ba,$ba
	ldda	[%sp+$bias+$frame+4]%asi,$nb
	fxtod	$bb,$bb
	ldda	[%sp+$bias+$frame+2]%asi,$nc
	fxtod	$bc,$bc
	ldda	[%sp+$bias+$frame+0]%asi,$nd
	fxtod	$bd,$bd
	ldd	[$ap_l+$j],$alo		! load a[j] in double format
	fxtod	$na,$na
	ldd	[$ap_h+$j],$ahi
	fxtod	$nb,$nb
	ldd	[$np_l+$j],$nlo		! load n[j] in double format
	fxtod	$nc,$nc
	ldd	[$np_h+$j],$nhi
	fxtod	$nd,$nd

		fmuld	$alo,$ba,$aloa
		fmuld	$nlo,$na,$nloa
		fmuld	$alo,$bb,$alob
		fmuld	$nlo,$nb,$nlob
		fmuld	$alo,$bc,$aloc
	faddd	$aloa,$nloa,$nloa
		fmuld	$nlo,$nc,$nloc
		fmuld	$alo,$bd,$alod
	faddd	$alob,$nlob,$nlob
		fmuld	$nlo,$nd,$nlod
		fmuld	$ahi,$ba,$ahia
	faddd	$aloc,$nloc,$nloc
		fmuld	$nhi,$na,$nhia
		fmuld	$ahi,$bb,$ahib
	faddd	$alod,$nlod,$nlod
		fmuld	$nhi,$nb,$nhib
		fmuld	$ahi,$bc,$ahic
	faddd	$ahia,$nhia,$nhia
		fmuld	$nhi,$nc,$nhic
		fmuld	$ahi,$bd,$ahid
	faddd	$ahib,$nhib,$nhib
		fmuld	$nhi,$nd,$nhid

	faddd	$ahic,$nhic,$dota	! $nhic
	faddd	$ahid,$nhid,$dotb	! $nhid

	faddd	$nloc,$nhia,$nloc
	faddd	$nlod,$nhib,$nlod

	fdtox	$nloa,$nloa
	fdtox	$nlob,$nlob
	fdtox	$nloc,$nloc
	fdtox	$nlod,$nlod

	std	$nloa,[%sp+$bias+$frame+0]
	std	$nlob,[%sp+$bias+$frame+8]
	std	$nloc,[%sp+$bias+$frame+16]
	add	$j,8,$j
	std	$nlod,[%sp+$bias+$frame+24]

	ldd	[$ap_l+$j],$alo		! load a[j] in double format
	ldd	[$ap_h+$j],$ahi
	ldd	[$np_l+$j],$nlo		! load n[j] in double format
	ldd	[$np_h+$j],$nhi

		fmuld	$alo,$ba,$aloa
		fmuld	$nlo,$na,$nloa
		fmuld	$alo,$bb,$alob
		fmuld	$nlo,$nb,$nlob
		fmuld	$alo,$bc,$aloc
	ldx	[%sp+$bias+$frame+0],%o0
		faddd	$aloa,$nloa,$nloa
		fmuld	$nlo,$nc,$nloc
	ldx	[%sp+$bias+$frame+8],%o1
		fmuld	$alo,$bd,$alod
	ldx	[%sp+$bias+$frame+16],%o2
		faddd	$alob,$nlob,$nlob
		fmuld	$nlo,$nd,$nlod
	ldx	[%sp+$bias+$frame+24],%o3
		fmuld	$ahi,$ba,$ahia

	srlx	%o0,16,%o7
		faddd	$aloc,$nloc,$nloc
		fmuld	$nhi,$na,$nhia
	add	%o7,%o1,%o1
		fmuld	$ahi,$bb,$ahib
	srlx	%o1,16,%o7
		faddd	$alod,$nlod,$nlod
		fmuld	$nhi,$nb,$nhib
	add	%o7,%o2,%o2
		fmuld	$ahi,$bc,$ahic
	srlx	%o2,16,%o7
		faddd	$ahia,$nhia,$nhia
		fmuld	$nhi,$nc,$nhic
	add	%o7,%o3,%o3		! %o3.%o2[0..15].%o1[0..15].%o0[0..15]
	! why?
	and	%o0,$mask,%o0
		fmuld	$ahi,$bd,$ahid
	and	%o1,$mask,%o1
	and	%o2,$mask,%o2
		faddd	$ahib,$nhib,$nhib
		fmuld	$nhi,$nd,$nhid
	sllx	%o1,16,%o1
		faddd	$dota,$nloa,$nloa
	sllx	%o2,32,%o2
		faddd	$dotb,$nlob,$nlob
	sllx	%o3,48,%o7
	or	%o1,%o0,%o0
		faddd	$ahic,$nhic,$dota	! $nhic
	or	%o2,%o0,%o0
		faddd	$ahid,$nhid,$dotb	! $nhid
	or	%o7,%o0,%o0		! 64-bit result
	ldx	[$tp],%o7
		faddd	$nloc,$nhia,$nloc
	addcc	%o7,%o0,%o0
	! end-of-why?
		faddd	$nlod,$nhib,$nlod
	srlx	%o3,16,%g1		! 34-bit carry
		fdtox	$nloa,$nloa
	bcs,a	%xcc,.+8
	add	%g1,1,%g1

	fdtox	$nlob,$nlob
	fdtox	$nloc,$nloc
	fdtox	$nlod,$nlod

	std	$nloa,[%sp+$bias+$frame+0]
	std	$nlob,[%sp+$bias+$frame+8]
	addcc	$j,8,$j
	std	$nloc,[%sp+$bias+$frame+16]
	bz,pn	%icc,.Linnerskip
	std	$nlod,[%sp+$bias+$frame+24]

	ba	.Linner
	nop
.align	32
.Linner:
	ldd	[$ap_l+$j],$alo		! load a[j] in double format
	ldd	[$ap_h+$j],$ahi
	ldd	[$np_l+$j],$nlo		! load n[j] in double format
	ldd	[$np_h+$j],$nhi

		fmuld	$alo,$ba,$aloa
		fmuld	$nlo,$na,$nloa
		fmuld	$alo,$bb,$alob
		fmuld	$nlo,$nb,$nlob
		fmuld	$alo,$bc,$aloc
	ldx	[%sp+$bias+$frame+0],%o0
		faddd	$aloa,$nloa,$nloa
		fmuld	$nlo,$nc,$nloc
	ldx	[%sp+$bias+$frame+8],%o1
		fmuld	$alo,$bd,$alod
	ldx	[%sp+$bias+$frame+16],%o2
		faddd	$alob,$nlob,$nlob
		fmuld	$nlo,$nd,$nlod
	ldx	[%sp+$bias+$frame+24],%o3
		fmuld	$ahi,$ba,$ahia

	srlx	%o0,16,%o7
		faddd	$aloc,$nloc,$nloc
		fmuld	$nhi,$na,$nhia
	add	%o7,%o1,%o1
		fmuld	$ahi,$bb,$ahib
	srlx	%o1,16,%o7
		faddd	$alod,$nlod,$nlod
		fmuld	$nhi,$nb,$nhib
	add	%o7,%o2,%o2
		fmuld	$ahi,$bc,$ahic
	srlx	%o2,16,%o7
		faddd	$ahia,$nhia,$nhia
		fmuld	$nhi,$nc,$nhic
	add	%o7,%o3,%o3		! %o3.%o2[0..15].%o1[0..15].%o0[0..15]
	and	%o0,$mask,%o0
		fmuld	$ahi,$bd,$ahid
	and	%o1,$mask,%o1
	and	%o2,$mask,%o2
		faddd	$ahib,$nhib,$nhib
		fmuld	$nhi,$nd,$nhid
	sllx	%o1,16,%o1
		faddd	$dota,$nloa,$nloa
	sllx	%o2,32,%o2
		faddd	$dotb,$nlob,$nlob
	sllx	%o3,48,%o7
	or	%o1,%o0,%o0
		faddd	$ahic,$nhic,$dota	! $nhic
	or	%o2,%o0,%o0
		faddd	$ahid,$nhid,$dotb	! $nhid
	or	%o7,%o0,%o0		! 64-bit result
		faddd	$nloc,$nhia,$nloc
	addcc	%g1,%o0,%o0
	ldx	[$tp+8],%o7		! tp[j]
		faddd	$nlod,$nhib,$nlod
	srlx	%o3,16,%g1		! 34-bit carry
		fdtox	$nloa,$nloa
	bcs,a	%xcc,.+8
	add	%g1,1,%g1
		fdtox	$nlob,$nlob
	addcc	%o7,%o0,%o0
		fdtox	$nloc,$nloc
	bcs,a	%xcc,.+8
	add	%g1,1,%g1

	stx	%o0,[$tp]		! tp[j-1]
		fdtox	$nlod,$nlod

	std	$nloa,[%sp+$bias+$frame+0]
	std	$nlob,[%sp+$bias+$frame+8]
	std	$nloc,[%sp+$bias+$frame+16]
	addcc	$j,8,$j
	std	$nlod,[%sp+$bias+$frame+24]
	bnz,pt	%icc,.Linner
	add	$tp,8,$tp

.Linnerskip:
	fdtox	$dota,$dota
	fdtox	$dotb,$dotb

	ldx	[%sp+$bias+$frame+0],%o0
	ldx	[%sp+$bias+$frame+8],%o1
	ldx	[%sp+$bias+$frame+16],%o2
	ldx	[%sp+$bias+$frame+24],%o3

	srlx	%o0,16,%o7
	std	$dota,[%sp+$bias+$frame+32]
	add	%o7,%o1,%o1
	std	$dotb,[%sp+$bias+$frame+40]
	srlx	%o1,16,%o7
	add	%o7,%o2,%o2
	srlx	%o2,16,%o7
	add	%o7,%o3,%o3		! %o3.%o2[0..15].%o1[0..15].%o0[0..15]
	and	%o0,$mask,%o0
	and	%o1,$mask,%o1
	and	%o2,$mask,%o2
	sllx	%o1,16,%o1
	sllx	%o2,32,%o2
	sllx	%o3,48,%o7
	or	%o1,%o0,%o0
	or	%o2,%o0,%o0
	ldx	[%sp+$bias+$frame+32],%o4
	or	%o7,%o0,%o0		! 64-bit result
	ldx	[%sp+$bias+$frame+40],%o5
	addcc	%g1,%o0,%o0
	ldx	[$tp+8],%o7		! tp[j]
	srlx	%o3,16,%g1		! 34-bit carry
	bcs,a	%xcc,.+8
	add	%g1,1,%g1

	addcc	%o7,%o0,%o0
	bcs,a	%xcc,.+8
	add	%g1,1,%g1

	stx	%o0,[$tp]		! tp[j-1]
	add	$tp,8,$tp

	srlx	%o4,16,%o7
	add	%o7,%o5,%o5
	and	%o4,$mask,%o4
	sllx	%o5,16,%o7
	or	%o7,%o4,%o4
	addcc	%g1,%o4,%o4
	srlx	%o5,48,%g1
	bcs,a	%xcc,.+8
	add	%g1,1,%g1

	addcc	$carry,%o4,%o4
	stx	%o4,[$tp]		! tp[num-1]
	mov	%g1,$carry
	bcs,a	%xcc,.+8
	add	$carry,1,$carry

	addcc	$i,8,$i
	bnz	%icc,.Louter
	nop

	add	$tp,8,$tp		! adjust tp to point at the end
	orn	%g0,%g0,%g4
	sub	%g0,$num,%o7		! n=-num
	ba	.Lsub
	subcc	%g0,%g0,%g0		! clear %icc.c

.align	32
.Lsub:
	ldx	[$tp+%o7],%o0
	add	$np,%o7,%g1
	ld	[%g1+0],%o2
	ld	[%g1+4],%o3
	srlx	%o0,32,%o1
	subccc	%o0,%o2,%o2
	add	$rp,%o7,%g1
	subccc	%o1,%o3,%o3
	st	%o2,[%g1+0]
	add	%o7,8,%o7
	brnz,pt	%o7,.Lsub
	st	%o3,[%g1+4]
	subc	$carry,0,%g4
	sub	%g0,$num,%o7		! n=-num
	ba	.Lcopy
	nop

.align	32
.Lcopy:
	ldx	[$tp+%o7],%o0
	add	$rp,%o7,%g1
	ld	[%g1+0],%o2
	ld	[%g1+4],%o3
	stx	%g0,[$tp+%o7]
	and	%o0,%g4,%o0
	srlx	%o0,32,%o1
	andn	%o2,%g4,%o2
	andn	%o3,%g4,%o3
	or	%o2,%o0,%o0
	or	%o3,%o1,%o1
	st	%o0,[%g1+0]
	add	%o7,8,%o7
	brnz,pt	%o7,.Lcopy
	st	%o1,[%g1+4]
	sub	%g0,$num,%o7		! n=-num

.Lzap:
	stx	%g0,[$ap_l+%o7]
	stx	%g0,[$ap_h+%o7]
	stx	%g0,[$np_l+%o7]
	stx	%g0,[$np_h+%o7]
	add	%o7,8,%o7
	brnz,pt	%o7,.Lzap
	nop

	ldx	[%sp+$bias+$frame+48],%o7
	wr	%g0,%o7,%asi		! restore %asi

	mov	1,%i0
.Lret:
	ret
	restore
.type   $fname,#function
.size	$fname,(.-$fname)
.asciz	"Montgomery Multipltication for UltraSPARC, CRYPTOGAMS by <appro\@openssl.org>"
.align	32
___

$code =~ s/\`([^\`]*)\`/eval($1)/gem;

# Below substitution makes it possible to compile without demanding
# VIS extentions on command line, e.g. -xarch=v9 vs. -xarch=v9a. I
# dare to do this, because VIS capability is detected at run-time now
# and this routine is not called on CPU not capable to execute it. Do
# note that fzeros is not the only VIS dependency! Another dependency
# is implicit and is just _a_ numerical value loaded to %asi register,
# which assembler can't recognize as VIS specific...
$code =~ s/fzeros\s+%f([0-9]+)/
	   sprintf(".word\t0x%x\t! fzeros %%f%d",0x81b00c20|($1<<25),$1)
	  /gem;

print $code;
# flush
close STDOUT;