lib1funcs.asm

GCC编译器源代码

! r0: Result
!
! Destroys:
!
! (none)
!
	.global	___lshrsi3
	.align	2
___lshrsi3:
	mov	#31,r0
	and	r0,r5
	mova	LOCAL(lshrsi3_table),r0
	mov.b	@(r0,r5),r5
#ifdef __sh1__
	add	r5,r0
	jmp	@r0
#else
	braf	r5
#endif
	mov	r4,r0

	.align	2
LOCAL(lshrsi3_table):
	.byte		LOCAL(lshrsi3_0)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_1)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_2)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_3)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_4)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_5)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_6)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_7)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_8)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_9)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_10)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_11)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_12)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_13)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_14)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_15)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_16)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_17)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_18)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_19)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_20)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_21)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_22)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_23)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_24)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_25)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_26)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_27)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_28)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_29)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_30)-LOCAL(lshrsi3_table)
	.byte		LOCAL(lshrsi3_31)-LOCAL(lshrsi3_table)

LOCAL(lshrsi3_6):
	shlr2	r0
LOCAL(lshrsi3_4):
	shlr2	r0
LOCAL(lshrsi3_2):
	rts
	shlr2	r0

LOCAL(lshrsi3_7):
	shlr2	r0
LOCAL(lshrsi3_5):
	shlr2	r0
LOCAL(lshrsi3_3):
	shlr2	r0
LOCAL(lshrsi3_1):
	rts
	shlr	r0

LOCAL(lshrsi3_14):
	shlr2	r0
LOCAL(lshrsi3_12):
	shlr2	r0
LOCAL(lshrsi3_10):
	shlr2	r0
LOCAL(lshrsi3_8):
	rts
	shlr8	r0

LOCAL(lshrsi3_15):
	shlr2	r0
LOCAL(lshrsi3_13):
	shlr2	r0
LOCAL(lshrsi3_11):
	shlr2	r0
LOCAL(lshrsi3_9):
	shlr8	r0
	rts
	shlr	r0

LOCAL(lshrsi3_22):
	shlr2	r0
LOCAL(lshrsi3_20):
	shlr2	r0
LOCAL(lshrsi3_18):
	shlr2	r0
LOCAL(lshrsi3_16):
	rts
	shlr16	r0

LOCAL(lshrsi3_23):
	shlr2	r0
LOCAL(lshrsi3_21):
	shlr2	r0
LOCAL(lshrsi3_19):
	shlr2	r0
LOCAL(lshrsi3_17):
	shlr16	r0
	rts
	shlr	r0

LOCAL(lshrsi3_30):
	shlr2	r0
LOCAL(lshrsi3_28):
	shlr2	r0
LOCAL(lshrsi3_26):
	shlr2	r0
LOCAL(lshrsi3_24):
	shlr16	r0
	rts
	shlr8	r0

LOCAL(lshrsi3_31):
	shlr2	r0
LOCAL(lshrsi3_29):
	shlr2	r0
LOCAL(lshrsi3_27):
	shlr2	r0
LOCAL(lshrsi3_25):
	shlr16	r0
	shlr8	r0
	rts
	shlr	r0

LOCAL(lshrsi3_0):
	rts
	nop

#endif

#ifdef L_movstr
	.text
! done all the large groups, do the remainder

! jump to movstr+
done:
	add	#64,r5
	mova	___movstrSI0,r0
	shll2	r6
	add	r6,r0
	jmp	@r0
	add	#64,r4
	.align	4
	.global	___movstrSI64
___movstrSI64:
	mov.l	@(60,r5),r0
	mov.l	r0,@(60,r4)
	.global	___movstrSI60
___movstrSI60:
	mov.l	@(56,r5),r0
	mov.l	r0,@(56,r4)
	.global	___movstrSI56
___movstrSI56:
	mov.l	@(52,r5),r0
	mov.l	r0,@(52,r4)
	.global	___movstrSI52
___movstrSI52:
	mov.l	@(48,r5),r0
	mov.l	r0,@(48,r4)
	.global	___movstrSI48
___movstrSI48:
	mov.l	@(44,r5),r0
	mov.l	r0,@(44,r4)
	.global	___movstrSI44
___movstrSI44:
	mov.l	@(40,r5),r0
	mov.l	r0,@(40,r4)
	.global	___movstrSI40
___movstrSI40:
	mov.l	@(36,r5),r0
	mov.l	r0,@(36,r4)
	.global	___movstrSI36
___movstrSI36:
	mov.l	@(32,r5),r0
	mov.l	r0,@(32,r4)
	.global	___movstrSI32
___movstrSI32:
	mov.l	@(28,r5),r0
	mov.l	r0,@(28,r4)
	.global	___movstrSI28
___movstrSI28:
	mov.l	@(24,r5),r0
	mov.l	r0,@(24,r4)
	.global	___movstrSI24
___movstrSI24:
	mov.l	@(20,r5),r0
	mov.l	r0,@(20,r4)
	.global	___movstrSI20
___movstrSI20:
	mov.l	@(16,r5),r0
	mov.l	r0,@(16,r4)
	.global	___movstrSI16
___movstrSI16:
	mov.l	@(12,r5),r0
	mov.l	r0,@(12,r4)
	.global	___movstrSI12
___movstrSI12:
	mov.l	@(8,r5),r0
	mov.l	r0,@(8,r4)
	.global	___movstrSI8
___movstrSI8:
	mov.l	@(4,r5),r0
	mov.l	r0,@(4,r4)
	.global	___movstrSI4
___movstrSI4:
	mov.l	@(0,r5),r0
	mov.l	r0,@(0,r4)
___movstrSI0:
	rts
	or	r0,r0,r0

	.align	4

	.global	___movstr
___movstr:
	mov.l	@(60,r5),r0
	mov.l	r0,@(60,r4)

	mov.l	@(56,r5),r0
	mov.l	r0,@(56,r4)

	mov.l	@(52,r5),r0
	mov.l	r0,@(52,r4)

	mov.l	@(48,r5),r0
	mov.l	r0,@(48,r4)

	mov.l	@(44,r5),r0
	mov.l	r0,@(44,r4)

	mov.l	@(40,r5),r0
	mov.l	r0,@(40,r4)

	mov.l	@(36,r5),r0
	mov.l	r0,@(36,r4)

	mov.l	@(32,r5),r0
	mov.l	r0,@(32,r4)

	mov.l	@(28,r5),r0
	mov.l	r0,@(28,r4)

	mov.l	@(24,r5),r0
	mov.l	r0,@(24,r4)

	mov.l	@(20,r5),r0
	mov.l	r0,@(20,r4)

	mov.l	@(16,r5),r0
	mov.l	r0,@(16,r4)

	mov.l	@(12,r5),r0
	mov.l	r0,@(12,r4)

	mov.l	@(8,r5),r0
	mov.l	r0,@(8,r4)

	mov.l	@(4,r5),r0
	mov.l	r0,@(4,r4)

	mov.l	@(0,r5),r0
	mov.l	r0,@(0,r4)

	add	#-16,r6
	cmp/pl	r6
	bf	done

	add	#64,r5
	bra	___movstr
	add	#64,r4
#endif

#ifdef L_mulsi3


	.global	___mulsi3

! r4 =       aabb
! r5 =       ccdd
! r0 = aabb*ccdd  via partial products
!
! if aa == 0 and cc = 0
! r0 = bb*dd
!
! else
! aa = bb*dd + (aa*dd*65536) + (cc*bb*65536)
!

___mulsi3:
	mulu    r4,r5		! multiply the lsws  macl=bb*dd
	mov     r5,r3		! r3 = ccdd
	swap.w  r4,r2		! r2 = bbaa
	xtrct   r2,r3		! r3 = aacc
	tst  	r3,r3		! msws zero ?
	bf      hiset
	rts			! yes - then we have the answer
	sts     macl,r0

hiset:	sts	macl,r0		! r0 = bb*dd
	mulu	r2,r5		| brewing macl = aa*dd
	sts	macl,r1
	mulu	r3,r4		| brewing macl = cc*bb
	sts	macl,r2
	add	r1,r2
	shll16	r2
	rts
	add	r2,r0


#endif
#ifdef L_sdivsi3
	.title "SH DIVIDE"
!! 4 byte integer Divide code for the Hitachi SH
!!
!! Steve Chamberlain
!! [e-mail]
!!
!!

!! args in r4 and r5, result in r0 clobber r1,r2,r3

	.global	___sdivsi3
___sdivsi3:
	mov	r4,r1
	mov	r5,r0

	tst	r0,r0
	bt	div0
	mov	#0,r2
	div0s	r2,r1
	subc	r3,r3
	subc	r2,r1
	div0s	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	div1	r0,r3
	rotcl	r1
	addc	r2,r1
	rts
	mov	r1,r0


div0:	rts
	mov	#0,r0

#endif
#ifdef L_udivsi3

	.title "SH DIVIDE"
!! 4 byte integer Divide code for the Hitachi SH
!!
!! Steve Chamberlain
!! [e-mail]
!!
!!

!! args in r4 and r5, result in r0, clobbers r4, pr, and t bit
	.global	___udivsi3

___udivsi3:
longway:
	mov	#0,r0
	div0u
	! get one bit from the msb of the numerator into the T
	! bit and divide it by whats in r5.  Put the answer bit
	! into the T bit so it can come out again at the bottom

	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0

	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
shortway:
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0

vshortway:
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4 ; div1 r5,r0
	rotcl	r4
ret:	rts
	mov	r4,r0

#endif