sparc32: Kill off software 32-bit multiply/divide routines.
For the explicit calls to .udiv/.umul in assembler, I made a
mechanical (read as: safe) transformation. I didn't attempt
to make any simplifications.
In particular, __ndelay and __udelay can be simplified significantly.
Some of the %y reads are unnecessary and these routines have no need
any longer for allocating a register window, they can be leaf
functions.
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 33d8d85..ead6df2 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -4,7 +4,7 @@
asflags-y := -ansi -DST_DIV0=0x02
ccflags-y := -Werror
-lib-$(CONFIG_SPARC32) += mul.o rem.o sdiv.o udiv.o umul.o urem.o ashrdi3.o
+lib-$(CONFIG_SPARC32) += ashrdi3.o
lib-$(CONFIG_SPARC32) += memcpy.o memset.o
lib-y += strlen.o
lib-y += checksum_$(BITS).o
diff --git a/arch/sparc/lib/divdi3.S b/arch/sparc/lib/divdi3.S
index d74bc09..9614b48 100644
--- a/arch/sparc/lib/divdi3.S
+++ b/arch/sparc/lib/divdi3.S
@@ -19,7 +19,6 @@
.text
.align 4
- .global .udiv
.globl __divdi3
__divdi3:
save %sp,-104,%sp
@@ -83,8 +82,9 @@
bne .LL85
mov %i0,%o2
mov 1,%o0
- call .udiv,0
mov 0,%o1
+ wr %g0, 0, %y
+ udiv %o0, %o1, %o0
mov %o0,%o4
mov %i0,%o2
.LL85:
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 1bc8972..2dc3087 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -61,16 +61,6 @@
extern void ___rw_read_exit(void);
extern void ___rw_write_enter(void);
-/* Alias functions whose names begin with "." and export the aliases.
- * The module references will be fixed up by module_frob_arch_sections.
- */
-extern int _Div(int, int);
-extern int _Mul(int, int);
-extern int _Rem(int, int);
-extern unsigned _Udiv(unsigned, unsigned);
-extern unsigned _Umul(unsigned, unsigned);
-extern unsigned _Urem(unsigned, unsigned);
-
/* Networking helper routines. */
EXPORT_SYMBOL(__csum_partial_copy_sparc_generic);
@@ -95,13 +85,6 @@
EXPORT_SYMBOL(__lshrdi3);
EXPORT_SYMBOL(__muldi3);
EXPORT_SYMBOL(__divdi3);
-
-EXPORT_SYMBOL(_Rem);
-EXPORT_SYMBOL(_Urem);
-EXPORT_SYMBOL(_Mul);
-EXPORT_SYMBOL(_Umul);
-EXPORT_SYMBOL(_Div);
-EXPORT_SYMBOL(_Udiv);
#endif
/*
diff --git a/arch/sparc/lib/mul.S b/arch/sparc/lib/mul.S
deleted file mode 100644
index c45470d..0000000
--- a/arch/sparc/lib/mul.S
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- * mul.S: This routine was taken from glibc-1.09 and is covered
- * by the GNU Library General Public License Version 2.
- */
-
-/*
- * Signed multiply, from Appendix E of the Sparc Version 8
- * Architecture Manual.
- */
-
-/*
- * Returns %o0 * %o1 in %o1%o0 (i.e., %o1 holds the upper 32 bits of
- * the 64-bit product).
- *
- * This code optimizes short (less than 13-bit) multiplies.
- */
-
- .globl .mul
- .globl _Mul
-.mul:
-_Mul: /* needed for export */
- mov %o0, %y ! multiplier -> Y
- andncc %o0, 0xfff, %g0 ! test bits 12..31
- be Lmul_shortway ! if zero, can do it the short way
- andcc %g0, %g0, %o4 ! zero the partial product and clear N and V
-
- /*
- * Long multiply. 32 steps, followed by a final shift step.
- */
- mulscc %o4, %o1, %o4 ! 1
- mulscc %o4, %o1, %o4 ! 2
- mulscc %o4, %o1, %o4 ! 3
- mulscc %o4, %o1, %o4 ! 4
- mulscc %o4, %o1, %o4 ! 5
- mulscc %o4, %o1, %o4 ! 6
- mulscc %o4, %o1, %o4 ! 7
- mulscc %o4, %o1, %o4 ! 8
- mulscc %o4, %o1, %o4 ! 9
- mulscc %o4, %o1, %o4 ! 10
- mulscc %o4, %o1, %o4 ! 11
- mulscc %o4, %o1, %o4 ! 12
- mulscc %o4, %o1, %o4 ! 13
- mulscc %o4, %o1, %o4 ! 14
- mulscc %o4, %o1, %o4 ! 15
- mulscc %o4, %o1, %o4 ! 16
- mulscc %o4, %o1, %o4 ! 17
- mulscc %o4, %o1, %o4 ! 18
- mulscc %o4, %o1, %o4 ! 19
- mulscc %o4, %o1, %o4 ! 20
- mulscc %o4, %o1, %o4 ! 21
- mulscc %o4, %o1, %o4 ! 22
- mulscc %o4, %o1, %o4 ! 23
- mulscc %o4, %o1, %o4 ! 24
- mulscc %o4, %o1, %o4 ! 25
- mulscc %o4, %o1, %o4 ! 26
- mulscc %o4, %o1, %o4 ! 27
- mulscc %o4, %o1, %o4 ! 28
- mulscc %o4, %o1, %o4 ! 29
- mulscc %o4, %o1, %o4 ! 30
- mulscc %o4, %o1, %o4 ! 31
- mulscc %o4, %o1, %o4 ! 32
- mulscc %o4, %g0, %o4 ! final shift
-
- ! If %o0 was negative, the result is
- ! (%o0 * %o1) + (%o1 << 32))
- ! We fix that here.
-
-#if 0
- tst %o0
- bge 1f
- rd %y, %o0
-
- ! %o0 was indeed negative; fix upper 32 bits of result by subtracting
- ! %o1 (i.e., return %o4 - %o1 in %o1).
- retl
- sub %o4, %o1, %o1
-
-1:
- retl
- mov %o4, %o1
-#else
- /* Faster code adapted from tege@sics.se's code for umul.S. */
- sra %o0, 31, %o2 ! make mask from sign bit
- and %o1, %o2, %o2 ! %o2 = 0 or %o1, depending on sign of %o0
- rd %y, %o0 ! get lower half of product
- retl
- sub %o4, %o2, %o1 ! subtract compensation
- ! and put upper half in place
-#endif
-
-Lmul_shortway:
- /*
- * Short multiply. 12 steps, followed by a final shift step.
- * The resulting bits are off by 12 and (32-12) = 20 bit positions,
- * but there is no problem with %o0 being negative (unlike above).
- */
- mulscc %o4, %o1, %o4 ! 1
- mulscc %o4, %o1, %o4 ! 2
- mulscc %o4, %o1, %o4 ! 3
- mulscc %o4, %o1, %o4 ! 4
- mulscc %o4, %o1, %o4 ! 5
- mulscc %o4, %o1, %o4 ! 6
- mulscc %o4, %o1, %o4 ! 7
- mulscc %o4, %o1, %o4 ! 8
- mulscc %o4, %o1, %o4 ! 9
- mulscc %o4, %o1, %o4 ! 10
- mulscc %o4, %o1, %o4 ! 11
- mulscc %o4, %o1, %o4 ! 12
- mulscc %o4, %g0, %o4 ! final shift
-
- /*
- * %o4 has 20 of the bits that should be in the low part of the
- * result; %y has the bottom 12 (as %y's top 12). That is:
- *
- * %o4 %y
- * +----------------+----------------+
- * | -12- | -20- | -12- | -20- |
- * +------(---------+------)---------+
- * --hi-- ----low-part----
- *
- * The upper 12 bits of %o4 should be sign-extended to form the
- * high part of the product (i.e., highpart = %o4 >> 20).
- */
-
- rd %y, %o5
- sll %o4, 12, %o0 ! shift middle bits left 12
- srl %o5, 20, %o5 ! shift low bits right 20, zero fill at left
- or %o5, %o0, %o0 ! construct low part of result
- retl
- sra %o4, 20, %o1 ! ... and extract high part of result
-
- .globl .mul_patch
-.mul_patch:
- smul %o0, %o1, %o0
- retl
- rd %y, %o1
- nop
diff --git a/arch/sparc/lib/muldi3.S b/arch/sparc/lib/muldi3.S
index 7f17872..9794939 100644
--- a/arch/sparc/lib/muldi3.S
+++ b/arch/sparc/lib/muldi3.S
@@ -63,12 +63,12 @@
rd %y, %o1
mov %o1, %l3
mov %i1, %o0
- call .umul
mov %i2, %o1
+ umul %o0, %o1, %o0
mov %o0, %l0
mov %i0, %o0
- call .umul
mov %i3, %o1
+ umul %o0, %o1, %o0
add %l0, %o0, %l0
mov %l2, %i0
add %l2, %l0, %i0
diff --git a/arch/sparc/lib/rem.S b/arch/sparc/lib/rem.S
deleted file mode 100644
index 42fb862..0000000
--- a/arch/sparc/lib/rem.S
+++ /dev/null
@@ -1,384 +0,0 @@
-/*
- * rem.S: This routine was taken from glibc-1.09 and is covered
- * by the GNU Library General Public License Version 2.
- */
-
-
-/* This file is generated from divrem.m4; DO NOT EDIT! */
-/*
- * Division and remainder, from Appendix E of the Sparc Version 8
- * Architecture Manual, with fixes from Gordon Irlam.
- */
-
-/*
- * Input: dividend and divisor in %o0 and %o1 respectively.
- *
- * m4 parameters:
- * .rem name of function to generate
- * rem rem=div => %o0 / %o1; rem=rem => %o0 % %o1
- * true true=true => signed; true=false => unsigned
- *
- * Algorithm parameters:
- * N how many bits per iteration we try to get (4)
- * WORDSIZE total number of bits (32)
- *
- * Derived constants:
- * TOPBITS number of bits in the top decade of a number
- *
- * Important variables:
- * Q the partial quotient under development (initially 0)
- * R the remainder so far, initially the dividend
- * ITER number of main division loop iterations required;
- * equal to ceil(log2(quotient) / N). Note that this
- * is the log base (2^N) of the quotient.
- * V the current comparand, initially divisor*2^(ITER*N-1)
- *
- * Cost:
- * Current estimate for non-large dividend is
- * ceil(log2(quotient) / N) * (10 + 7N/2) + C
- * A large dividend is one greater than 2^(31-TOPBITS) and takes a
- * different path, as the upper bits of the quotient must be developed
- * one bit at a time.
- */
-
-
- .globl .rem
- .globl _Rem
-.rem:
-_Rem: /* needed for export */
- ! compute sign of result; if neither is negative, no problem
- orcc %o1, %o0, %g0 ! either negative?
- bge 2f ! no, go do the divide
- mov %o0, %g2 ! compute sign in any case
-
- tst %o1
- bge 1f
- tst %o0
- ! %o1 is definitely negative; %o0 might also be negative
- bge 2f ! if %o0 not negative...
- sub %g0, %o1, %o1 ! in any case, make %o1 nonneg
-1: ! %o0 is negative, %o1 is nonnegative
- sub %g0, %o0, %o0 ! make %o0 nonnegative
-2:
-
- ! Ready to divide. Compute size of quotient; scale comparand.
- orcc %o1, %g0, %o5
- bne 1f
- mov %o0, %o3
-
- ! Divide by zero trap. If it returns, return 0 (about as
- ! wrong as possible, but that is what SunOS does...).
- ta ST_DIV0
- retl
- clr %o0
-
-1:
- cmp %o3, %o5 ! if %o1 exceeds %o0, done
- blu Lgot_result ! (and algorithm fails otherwise)
- clr %o2
-
- sethi %hi(1 << (32 - 4 - 1)), %g1
-
- cmp %o3, %g1
- blu Lnot_really_big
- clr %o4
-
- ! Here the dividend is >= 2**(31-N) or so. We must be careful here,
- ! as our usual N-at-a-shot divide step will cause overflow and havoc.
- ! The number of bits in the result here is N*ITER+SC, where SC <= N.
- ! Compute ITER in an unorthodox manner: know we need to shift V into
- ! the top decade: so do not even bother to compare to R.
- 1:
- cmp %o5, %g1
- bgeu 3f
- mov 1, %g7
-
- sll %o5, 4, %o5
-
- b 1b
- add %o4, 1, %o4
-
- ! Now compute %g7.
- 2:
- addcc %o5, %o5, %o5
-
- bcc Lnot_too_big
- add %g7, 1, %g7
-
- ! We get here if the %o1 overflowed while shifting.
- ! This means that %o3 has the high-order bit set.
- ! Restore %o5 and subtract from %o3.
- sll %g1, 4, %g1 ! high order bit
- srl %o5, 1, %o5 ! rest of %o5
- add %o5, %g1, %o5
-
- b Ldo_single_div
- sub %g7, 1, %g7
-
- Lnot_too_big:
- 3:
- cmp %o5, %o3
- blu 2b
- nop
-
- be Ldo_single_div
- nop
- /* NB: these are commented out in the V8-Sparc manual as well */
- /* (I do not understand this) */
- ! %o5 > %o3: went too far: back up 1 step
- ! srl %o5, 1, %o5
- ! dec %g7
- ! do single-bit divide steps
- !
- ! We have to be careful here. We know that %o3 >= %o5, so we can do the
- ! first divide step without thinking. BUT, the others are conditional,
- ! and are only done if %o3 >= 0. Because both %o3 and %o5 may have the high-
- ! order bit set in the first step, just falling into the regular
- ! division loop will mess up the first time around.
- ! So we unroll slightly...
- Ldo_single_div:
- subcc %g7, 1, %g7
- bl Lend_regular_divide
- nop
-
- sub %o3, %o5, %o3
- mov 1, %o2
-
- b Lend_single_divloop
- nop
- Lsingle_divloop:
- sll %o2, 1, %o2
-
- bl 1f
- srl %o5, 1, %o5
- ! %o3 >= 0
- sub %o3, %o5, %o3
-
- b 2f
- add %o2, 1, %o2
- 1: ! %o3 < 0
- add %o3, %o5, %o3
- sub %o2, 1, %o2
- 2:
- Lend_single_divloop:
- subcc %g7, 1, %g7
- bge Lsingle_divloop
- tst %o3
-
- b,a Lend_regular_divide
-
-Lnot_really_big:
-1:
- sll %o5, 4, %o5
- cmp %o5, %o3
- bleu 1b
- addcc %o4, 1, %o4
- be Lgot_result
- sub %o4, 1, %o4
-
- tst %o3 ! set up for initial iteration
-Ldivloop:
- sll %o2, 4, %o2
- ! depth 1, accumulated bits 0
- bl L.1.16
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 2, accumulated bits 1
- bl L.2.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 3, accumulated bits 3
- bl L.3.19
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits 7
- bl L.4.23
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
-
- b 9f
- add %o2, (7*2+1), %o2
-
-L.4.23:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (7*2-1), %o2
-
-L.3.19:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits 5
- bl L.4.21
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (5*2+1), %o2
-
-L.4.21:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (5*2-1), %o2
-
-L.2.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 3, accumulated bits 1
- bl L.3.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits 3
- bl L.4.19
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (3*2+1), %o2
-
-L.4.19:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (3*2-1), %o2
-
-L.3.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits 1
- bl L.4.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (1*2+1), %o2
-
-L.4.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (1*2-1), %o2
-
-L.1.16:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 2, accumulated bits -1
- bl L.2.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 3, accumulated bits -1
- bl L.3.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits -1
- bl L.4.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-1*2+1), %o2
-
-L.4.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-1*2-1), %o2
-
-L.3.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits -3
- bl L.4.13
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-3*2+1), %o2
-
-L.4.13:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-3*2-1), %o2
-
-L.2.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 3, accumulated bits -3
- bl L.3.13
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits -5
- bl L.4.11
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-5*2+1), %o2
-
-L.4.11:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-5*2-1), %o2
-
-
-L.3.13:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits -7
- bl L.4.9
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-7*2+1), %o2
-
-L.4.9:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-7*2-1), %o2
-
- 9:
-Lend_regular_divide:
- subcc %o4, 1, %o4
- bge Ldivloop
- tst %o3
-
- bl,a Lgot_result
- ! non-restoring fixup here (one instruction only!)
- add %o3, %o1, %o3
-
-Lgot_result:
- ! check to see if answer should be < 0
- tst %g2
- bl,a 1f
- sub %g0, %o3, %o3
-1:
- retl
- mov %o3, %o0
-
- .globl .rem_patch
-.rem_patch:
- sra %o0, 0x1f, %o4
- wr %o4, 0x0, %y
- nop
- nop
- nop
- sdivcc %o0, %o1, %o2
- bvs,a 1f
- xnor %o2, %g0, %o2
-1: smul %o2, %o1, %o2
- retl
- sub %o0, %o2, %o0
- nop
diff --git a/arch/sparc/lib/sdiv.S b/arch/sparc/lib/sdiv.S
deleted file mode 100644
index f0a0d4e..0000000
--- a/arch/sparc/lib/sdiv.S
+++ /dev/null
@@ -1,381 +0,0 @@
-/*
- * sdiv.S: This routine was taken from glibc-1.09 and is covered
- * by the GNU Library General Public License Version 2.
- */
-
-
-/* This file is generated from divrem.m4; DO NOT EDIT! */
-/*
- * Division and remainder, from Appendix E of the Sparc Version 8
- * Architecture Manual, with fixes from Gordon Irlam.
- */
-
-/*
- * Input: dividend and divisor in %o0 and %o1 respectively.
- *
- * m4 parameters:
- * .div name of function to generate
- * div div=div => %o0 / %o1; div=rem => %o0 % %o1
- * true true=true => signed; true=false => unsigned
- *
- * Algorithm parameters:
- * N how many bits per iteration we try to get (4)
- * WORDSIZE total number of bits (32)
- *
- * Derived constants:
- * TOPBITS number of bits in the top decade of a number
- *
- * Important variables:
- * Q the partial quotient under development (initially 0)
- * R the remainder so far, initially the dividend
- * ITER number of main division loop iterations required;
- * equal to ceil(log2(quotient) / N). Note that this
- * is the log base (2^N) of the quotient.
- * V the current comparand, initially divisor*2^(ITER*N-1)
- *
- * Cost:
- * Current estimate for non-large dividend is
- * ceil(log2(quotient) / N) * (10 + 7N/2) + C
- * A large dividend is one greater than 2^(31-TOPBITS) and takes a
- * different path, as the upper bits of the quotient must be developed
- * one bit at a time.
- */
-
-
- .globl .div
- .globl _Div
-.div:
-_Div: /* needed for export */
- ! compute sign of result; if neither is negative, no problem
- orcc %o1, %o0, %g0 ! either negative?
- bge 2f ! no, go do the divide
- xor %o1, %o0, %g2 ! compute sign in any case
-
- tst %o1
- bge 1f
- tst %o0
- ! %o1 is definitely negative; %o0 might also be negative
- bge 2f ! if %o0 not negative...
- sub %g0, %o1, %o1 ! in any case, make %o1 nonneg
-1: ! %o0 is negative, %o1 is nonnegative
- sub %g0, %o0, %o0 ! make %o0 nonnegative
-2:
-
- ! Ready to divide. Compute size of quotient; scale comparand.
- orcc %o1, %g0, %o5
- bne 1f
- mov %o0, %o3
-
- ! Divide by zero trap. If it returns, return 0 (about as
- ! wrong as possible, but that is what SunOS does...).
- ta ST_DIV0
- retl
- clr %o0
-
-1:
- cmp %o3, %o5 ! if %o1 exceeds %o0, done
- blu Lgot_result ! (and algorithm fails otherwise)
- clr %o2
-
- sethi %hi(1 << (32 - 4 - 1)), %g1
-
- cmp %o3, %g1
- blu Lnot_really_big
- clr %o4
-
- ! Here the dividend is >= 2**(31-N) or so. We must be careful here,
- ! as our usual N-at-a-shot divide step will cause overflow and havoc.
- ! The number of bits in the result here is N*ITER+SC, where SC <= N.
- ! Compute ITER in an unorthodox manner: know we need to shift V into
- ! the top decade: so do not even bother to compare to R.
- 1:
- cmp %o5, %g1
- bgeu 3f
- mov 1, %g7
-
- sll %o5, 4, %o5
-
- b 1b
- add %o4, 1, %o4
-
- ! Now compute %g7.
- 2:
- addcc %o5, %o5, %o5
- bcc Lnot_too_big
- add %g7, 1, %g7
-
- ! We get here if the %o1 overflowed while shifting.
- ! This means that %o3 has the high-order bit set.
- ! Restore %o5 and subtract from %o3.
- sll %g1, 4, %g1 ! high order bit
- srl %o5, 1, %o5 ! rest of %o5
- add %o5, %g1, %o5
-
- b Ldo_single_div
- sub %g7, 1, %g7
-
- Lnot_too_big:
- 3:
- cmp %o5, %o3
- blu 2b
- nop
-
- be Ldo_single_div
- nop
- /* NB: these are commented out in the V8-Sparc manual as well */
- /* (I do not understand this) */
- ! %o5 > %o3: went too far: back up 1 step
- ! srl %o5, 1, %o5
- ! dec %g7
- ! do single-bit divide steps
- !
- ! We have to be careful here. We know that %o3 >= %o5, so we can do the
- ! first divide step without thinking. BUT, the others are conditional,
- ! and are only done if %o3 >= 0. Because both %o3 and %o5 may have the high-
- ! order bit set in the first step, just falling into the regular
- ! division loop will mess up the first time around.
- ! So we unroll slightly...
- Ldo_single_div:
- subcc %g7, 1, %g7
- bl Lend_regular_divide
- nop
-
- sub %o3, %o5, %o3
- mov 1, %o2
-
- b Lend_single_divloop
- nop
- Lsingle_divloop:
- sll %o2, 1, %o2
-
- bl 1f
- srl %o5, 1, %o5
- ! %o3 >= 0
- sub %o3, %o5, %o3
-
- b 2f
- add %o2, 1, %o2
- 1: ! %o3 < 0
- add %o3, %o5, %o3
- sub %o2, 1, %o2
- 2:
- Lend_single_divloop:
- subcc %g7, 1, %g7
- bge Lsingle_divloop
- tst %o3
-
- b,a Lend_regular_divide
-
-Lnot_really_big:
-1:
- sll %o5, 4, %o5
- cmp %o5, %o3
- bleu 1b
- addcc %o4, 1, %o4
-
- be Lgot_result
- sub %o4, 1, %o4
-
- tst %o3 ! set up for initial iteration
-Ldivloop:
- sll %o2, 4, %o2
- ! depth 1, accumulated bits 0
- bl L.1.16
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 2, accumulated bits 1
- bl L.2.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 3, accumulated bits 3
- bl L.3.19
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits 7
- bl L.4.23
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (7*2+1), %o2
-
-L.4.23:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (7*2-1), %o2
-
-L.3.19:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits 5
- bl L.4.21
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (5*2+1), %o2
-
-L.4.21:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (5*2-1), %o2
-
-L.2.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 3, accumulated bits 1
- bl L.3.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits 3
- bl L.4.19
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (3*2+1), %o2
-
-L.4.19:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (3*2-1), %o2
-
-
-L.3.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits 1
- bl L.4.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (1*2+1), %o2
-
-L.4.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (1*2-1), %o2
-
-L.1.16:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 2, accumulated bits -1
- bl L.2.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 3, accumulated bits -1
- bl L.3.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits -1
- bl L.4.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-1*2+1), %o2
-
-L.4.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-1*2-1), %o2
-
-L.3.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits -3
- bl L.4.13
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-3*2+1), %o2
-
-L.4.13:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-3*2-1), %o2
-
-L.2.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 3, accumulated bits -3
- bl L.3.13
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits -5
- bl L.4.11
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-5*2+1), %o2
-
-L.4.11:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-5*2-1), %o2
-
-L.3.13:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits -7
- bl L.4.9
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-7*2+1), %o2
-
-L.4.9:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-7*2-1), %o2
-
- 9:
-Lend_regular_divide:
- subcc %o4, 1, %o4
- bge Ldivloop
- tst %o3
-
- bl,a Lgot_result
- ! non-restoring fixup here (one instruction only!)
- sub %o2, 1, %o2
-
-Lgot_result:
- ! check to see if answer should be < 0
- tst %g2
- bl,a 1f
- sub %g0, %o2, %o2
-1:
- retl
- mov %o2, %o0
-
- .globl .div_patch
-.div_patch:
- sra %o0, 0x1f, %o2
- wr %o2, 0x0, %y
- nop
- nop
- nop
- sdivcc %o0, %o1, %o0
- bvs,a 1f
- xnor %o0, %g0, %o0
-1: retl
- nop
diff --git a/arch/sparc/lib/udiv.S b/arch/sparc/lib/udiv.S
deleted file mode 100644
index 2101405..0000000
--- a/arch/sparc/lib/udiv.S
+++ /dev/null
@@ -1,357 +0,0 @@
-/*
- * udiv.S: This routine was taken from glibc-1.09 and is covered
- * by the GNU Library General Public License Version 2.
- */
-
-
-/* This file is generated from divrem.m4; DO NOT EDIT! */
-/*
- * Division and remainder, from Appendix E of the Sparc Version 8
- * Architecture Manual, with fixes from Gordon Irlam.
- */
-
-/*
- * Input: dividend and divisor in %o0 and %o1 respectively.
- *
- * m4 parameters:
- * .udiv name of function to generate
- * div div=div => %o0 / %o1; div=rem => %o0 % %o1
- * false false=true => signed; false=false => unsigned
- *
- * Algorithm parameters:
- * N how many bits per iteration we try to get (4)
- * WORDSIZE total number of bits (32)
- *
- * Derived constants:
- * TOPBITS number of bits in the top decade of a number
- *
- * Important variables:
- * Q the partial quotient under development (initially 0)
- * R the remainder so far, initially the dividend
- * ITER number of main division loop iterations required;
- * equal to ceil(log2(quotient) / N). Note that this
- * is the log base (2^N) of the quotient.
- * V the current comparand, initially divisor*2^(ITER*N-1)
- *
- * Cost:
- * Current estimate for non-large dividend is
- * ceil(log2(quotient) / N) * (10 + 7N/2) + C
- * A large dividend is one greater than 2^(31-TOPBITS) and takes a
- * different path, as the upper bits of the quotient must be developed
- * one bit at a time.
- */
-
-
- .globl .udiv
- .globl _Udiv
-.udiv:
-_Udiv: /* needed for export */
-
- ! Ready to divide. Compute size of quotient; scale comparand.
- orcc %o1, %g0, %o5
- bne 1f
- mov %o0, %o3
-
- ! Divide by zero trap. If it returns, return 0 (about as
- ! wrong as possible, but that is what SunOS does...).
- ta ST_DIV0
- retl
- clr %o0
-
-1:
- cmp %o3, %o5 ! if %o1 exceeds %o0, done
- blu Lgot_result ! (and algorithm fails otherwise)
- clr %o2
-
- sethi %hi(1 << (32 - 4 - 1)), %g1
-
- cmp %o3, %g1
- blu Lnot_really_big
- clr %o4
-
- ! Here the dividend is >= 2**(31-N) or so. We must be careful here,
- ! as our usual N-at-a-shot divide step will cause overflow and havoc.
- ! The number of bits in the result here is N*ITER+SC, where SC <= N.
- ! Compute ITER in an unorthodox manner: know we need to shift V into
- ! the top decade: so do not even bother to compare to R.
- 1:
- cmp %o5, %g1
- bgeu 3f
- mov 1, %g7
-
- sll %o5, 4, %o5
-
- b 1b
- add %o4, 1, %o4
-
- ! Now compute %g7.
- 2:
- addcc %o5, %o5, %o5
- bcc Lnot_too_big
- add %g7, 1, %g7
-
- ! We get here if the %o1 overflowed while shifting.
- ! This means that %o3 has the high-order bit set.
- ! Restore %o5 and subtract from %o3.
- sll %g1, 4, %g1 ! high order bit
- srl %o5, 1, %o5 ! rest of %o5
- add %o5, %g1, %o5
-
- b Ldo_single_div
- sub %g7, 1, %g7
-
- Lnot_too_big:
- 3:
- cmp %o5, %o3
- blu 2b
- nop
-
- be Ldo_single_div
- nop
- /* NB: these are commented out in the V8-Sparc manual as well */
- /* (I do not understand this) */
- ! %o5 > %o3: went too far: back up 1 step
- ! srl %o5, 1, %o5
- ! dec %g7
- ! do single-bit divide steps
- !
- ! We have to be careful here. We know that %o3 >= %o5, so we can do the
- ! first divide step without thinking. BUT, the others are conditional,
- ! and are only done if %o3 >= 0. Because both %o3 and %o5 may have the high-
- ! order bit set in the first step, just falling into the regular
- ! division loop will mess up the first time around.
- ! So we unroll slightly...
- Ldo_single_div:
- subcc %g7, 1, %g7
- bl Lend_regular_divide
- nop
-
- sub %o3, %o5, %o3
- mov 1, %o2
-
- b Lend_single_divloop
- nop
- Lsingle_divloop:
- sll %o2, 1, %o2
- bl 1f
- srl %o5, 1, %o5
- ! %o3 >= 0
- sub %o3, %o5, %o3
- b 2f
- add %o2, 1, %o2
- 1: ! %o3 < 0
- add %o3, %o5, %o3
- sub %o2, 1, %o2
- 2:
- Lend_single_divloop:
- subcc %g7, 1, %g7
- bge Lsingle_divloop
- tst %o3
-
- b,a Lend_regular_divide
-
-Lnot_really_big:
-1:
- sll %o5, 4, %o5
-
- cmp %o5, %o3
- bleu 1b
- addcc %o4, 1, %o4
-
- be Lgot_result
- sub %o4, 1, %o4
-
- tst %o3 ! set up for initial iteration
-Ldivloop:
- sll %o2, 4, %o2
- ! depth 1, accumulated bits 0
- bl L.1.16
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 2, accumulated bits 1
- bl L.2.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 3, accumulated bits 3
- bl L.3.19
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits 7
- bl L.4.23
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (7*2+1), %o2
-
-L.4.23:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (7*2-1), %o2
-
-L.3.19:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits 5
- bl L.4.21
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (5*2+1), %o2
-
-L.4.21:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (5*2-1), %o2
-
-L.2.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 3, accumulated bits 1
- bl L.3.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits 3
- bl L.4.19
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (3*2+1), %o2
-
-L.4.19:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (3*2-1), %o2
-
-L.3.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits 1
- bl L.4.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (1*2+1), %o2
-
-L.4.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (1*2-1), %o2
-
-L.1.16:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 2, accumulated bits -1
- bl L.2.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 3, accumulated bits -1
- bl L.3.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits -1
- bl L.4.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-1*2+1), %o2
-
-L.4.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-1*2-1), %o2
-
-L.3.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits -3
- bl L.4.13
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-3*2+1), %o2
-
-L.4.13:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-3*2-1), %o2
-
-L.2.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 3, accumulated bits -3
- bl L.3.13
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits -5
- bl L.4.11
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-5*2+1), %o2
-
-L.4.11:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-5*2-1), %o2
-
-L.3.13:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits -7
- bl L.4.9
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-7*2+1), %o2
-
-L.4.9:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-7*2-1), %o2
-
- 9:
-Lend_regular_divide:
- subcc %o4, 1, %o4
- bge Ldivloop
- tst %o3
-
- bl,a Lgot_result
- ! non-restoring fixup here (one instruction only!)
- sub %o2, 1, %o2
-
-Lgot_result:
-
- retl
- mov %o2, %o0
-
- .globl .udiv_patch
-.udiv_patch:
- wr %g0, 0x0, %y
- nop
- nop
- retl
- udiv %o0, %o1, %o0
- nop
diff --git a/arch/sparc/lib/udivdi3.S b/arch/sparc/lib/udivdi3.S
index b430f1f..24e0a35 100644
--- a/arch/sparc/lib/udivdi3.S
+++ b/arch/sparc/lib/udivdi3.S
@@ -60,8 +60,9 @@
bne .LL77
mov %i0,%o2
mov 1,%o0
- call .udiv,0
mov 0,%o1
+ wr %g0, 0, %y
+ udiv %o0, %o1, %o0
mov %o0,%o3
mov %i0,%o2
.LL77:
diff --git a/arch/sparc/lib/umul.S b/arch/sparc/lib/umul.S
deleted file mode 100644
index 1f36ae6..0000000
--- a/arch/sparc/lib/umul.S
+++ /dev/null
@@ -1,171 +0,0 @@
-/*
- * umul.S: This routine was taken from glibc-1.09 and is covered
- * by the GNU Library General Public License Version 2.
- */
-
-
-/*
- * Unsigned multiply. Returns %o0 * %o1 in %o1%o0 (i.e., %o1 holds the
- * upper 32 bits of the 64-bit product).
- *
- * This code optimizes short (less than 13-bit) multiplies. Short
- * multiplies require 25 instruction cycles, and long ones require
- * 45 instruction cycles.
- *
- * On return, overflow has occurred (%o1 is not zero) if and only if
- * the Z condition code is clear, allowing, e.g., the following:
- *
- * call .umul
- * nop
- * bnz overflow (or tnz)
- */
-
- .globl .umul
- .globl _Umul
-.umul:
-_Umul: /* needed for export */
- or %o0, %o1, %o4
- mov %o0, %y ! multiplier -> Y
-
- andncc %o4, 0xfff, %g0 ! test bits 12..31 of *both* args
- be Lmul_shortway ! if zero, can do it the short way
- andcc %g0, %g0, %o4 ! zero the partial product and clear N and V
-
- /*
- * Long multiply. 32 steps, followed by a final shift step.
- */
- mulscc %o4, %o1, %o4 ! 1
- mulscc %o4, %o1, %o4 ! 2
- mulscc %o4, %o1, %o4 ! 3
- mulscc %o4, %o1, %o4 ! 4
- mulscc %o4, %o1, %o4 ! 5
- mulscc %o4, %o1, %o4 ! 6
- mulscc %o4, %o1, %o4 ! 7
- mulscc %o4, %o1, %o4 ! 8
- mulscc %o4, %o1, %o4 ! 9
- mulscc %o4, %o1, %o4 ! 10
- mulscc %o4, %o1, %o4 ! 11
- mulscc %o4, %o1, %o4 ! 12
- mulscc %o4, %o1, %o4 ! 13
- mulscc %o4, %o1, %o4 ! 14
- mulscc %o4, %o1, %o4 ! 15
- mulscc %o4, %o1, %o4 ! 16
- mulscc %o4, %o1, %o4 ! 17
- mulscc %o4, %o1, %o4 ! 18
- mulscc %o4, %o1, %o4 ! 19
- mulscc %o4, %o1, %o4 ! 20
- mulscc %o4, %o1, %o4 ! 21
- mulscc %o4, %o1, %o4 ! 22
- mulscc %o4, %o1, %o4 ! 23
- mulscc %o4, %o1, %o4 ! 24
- mulscc %o4, %o1, %o4 ! 25
- mulscc %o4, %o1, %o4 ! 26
- mulscc %o4, %o1, %o4 ! 27
- mulscc %o4, %o1, %o4 ! 28
- mulscc %o4, %o1, %o4 ! 29
- mulscc %o4, %o1, %o4 ! 30
- mulscc %o4, %o1, %o4 ! 31
- mulscc %o4, %o1, %o4 ! 32
- mulscc %o4, %g0, %o4 ! final shift
-
-
- /*
- * Normally, with the shift-and-add approach, if both numbers are
- * positive you get the correct result. With 32-bit two's-complement
- * numbers, -x is represented as
- *
- * x 32
- * ( 2 - ------ ) mod 2 * 2
- * 32
- * 2
- *
- * (the `mod 2' subtracts 1 from 1.bbbb). To avoid lots of 2^32s,
- * we can treat this as if the radix point were just to the left
- * of the sign bit (multiply by 2^32), and get
- *
- * -x = (2 - x) mod 2
- *
- * Then, ignoring the `mod 2's for convenience:
- *
- * x * y = xy
- * -x * y = 2y - xy
- * x * -y = 2x - xy
- * -x * -y = 4 - 2x - 2y + xy
- *
- * For signed multiplies, we subtract (x << 32) from the partial
- * product to fix this problem for negative multipliers (see mul.s).
- * Because of the way the shift into the partial product is calculated
- * (N xor V), this term is automatically removed for the multiplicand,
- * so we don't have to adjust.
- *
- * But for unsigned multiplies, the high order bit wasn't a sign bit,
- * and the correction is wrong. So for unsigned multiplies where the
- * high order bit is one, we end up with xy - (y << 32). To fix it
- * we add y << 32.
- */
-#if 0
- tst %o1
- bl,a 1f ! if %o1 < 0 (high order bit = 1),
- add %o4, %o0, %o4 ! %o4 += %o0 (add y to upper half)
-
-1:
- rd %y, %o0 ! get lower half of product
- retl
- addcc %o4, %g0, %o1 ! put upper half in place and set Z for %o1==0
-#else
- /* Faster code from tege@sics.se. */
- sra %o1, 31, %o2 ! make mask from sign bit
- and %o0, %o2, %o2 ! %o2 = 0 or %o0, depending on sign of %o1
- rd %y, %o0 ! get lower half of product
- retl
- addcc %o4, %o2, %o1 ! add compensation and put upper half in place
-#endif
-
-Lmul_shortway:
- /*
- * Short multiply. 12 steps, followed by a final shift step.
- * The resulting bits are off by 12 and (32-12) = 20 bit positions,
- * but there is no problem with %o0 being negative (unlike above),
- * and overflow is impossible (the answer is at most 24 bits long).
- */
- mulscc %o4, %o1, %o4 ! 1
- mulscc %o4, %o1, %o4 ! 2
- mulscc %o4, %o1, %o4 ! 3
- mulscc %o4, %o1, %o4 ! 4
- mulscc %o4, %o1, %o4 ! 5
- mulscc %o4, %o1, %o4 ! 6
- mulscc %o4, %o1, %o4 ! 7
- mulscc %o4, %o1, %o4 ! 8
- mulscc %o4, %o1, %o4 ! 9
- mulscc %o4, %o1, %o4 ! 10
- mulscc %o4, %o1, %o4 ! 11
- mulscc %o4, %o1, %o4 ! 12
- mulscc %o4, %g0, %o4 ! final shift
-
- /*
- * %o4 has 20 of the bits that should be in the result; %y has
- * the bottom 12 (as %y's top 12). That is:
- *
- * %o4 %y
- * +----------------+----------------+
- * | -12- | -20- | -12- | -20- |
- * +------(---------+------)---------+
- * -----result-----
- *
- * The 12 bits of %o4 left of the `result' area are all zero;
- * in fact, all top 20 bits of %o4 are zero.
- */
-
- rd %y, %o5
- sll %o4, 12, %o0 ! shift middle bits left 12
- srl %o5, 20, %o5 ! shift low bits right 20
- or %o5, %o0, %o0
- retl
- addcc %g0, %g0, %o1 ! %o1 = zero, and set Z
-
- .globl .umul_patch
-.umul_patch:
- umul %o0, %o1, %o0
- retl
- rd %y, %o1
- nop
diff --git a/arch/sparc/lib/urem.S b/arch/sparc/lib/urem.S
deleted file mode 100644
index 77123eb..0000000
--- a/arch/sparc/lib/urem.S
+++ /dev/null
@@ -1,357 +0,0 @@
-/*
- * urem.S: This routine was taken from glibc-1.09 and is covered
- * by the GNU Library General Public License Version 2.
- */
-
-/* This file is generated from divrem.m4; DO NOT EDIT! */
-/*
- * Division and remainder, from Appendix E of the Sparc Version 8
- * Architecture Manual, with fixes from Gordon Irlam.
- */
-
-/*
- * Input: dividend and divisor in %o0 and %o1 respectively.
- *
- * m4 parameters:
- * .urem name of function to generate
- * rem rem=div => %o0 / %o1; rem=rem => %o0 % %o1
- * false false=true => signed; false=false => unsigned
- *
- * Algorithm parameters:
- * N how many bits per iteration we try to get (4)
- * WORDSIZE total number of bits (32)
- *
- * Derived constants:
- * TOPBITS number of bits in the top decade of a number
- *
- * Important variables:
- * Q the partial quotient under development (initially 0)
- * R the remainder so far, initially the dividend
- * ITER number of main division loop iterations required;
- * equal to ceil(log2(quotient) / N). Note that this
- * is the log base (2^N) of the quotient.
- * V the current comparand, initially divisor*2^(ITER*N-1)
- *
- * Cost:
- * Current estimate for non-large dividend is
- * ceil(log2(quotient) / N) * (10 + 7N/2) + C
- * A large dividend is one greater than 2^(31-TOPBITS) and takes a
- * different path, as the upper bits of the quotient must be developed
- * one bit at a time.
- */
-
- .globl .urem
- .globl _Urem
-.urem:
-_Urem: /* needed for export */
-
- ! Ready to divide. Compute size of quotient; scale comparand.
- orcc %o1, %g0, %o5
- bne 1f
- mov %o0, %o3
-
- ! Divide by zero trap. If it returns, return 0 (about as
- ! wrong as possible, but that is what SunOS does...).
- ta ST_DIV0
- retl
- clr %o0
-
-1:
- cmp %o3, %o5 ! if %o1 exceeds %o0, done
- blu Lgot_result ! (and algorithm fails otherwise)
- clr %o2
-
- sethi %hi(1 << (32 - 4 - 1)), %g1
-
- cmp %o3, %g1
- blu Lnot_really_big
- clr %o4
-
- ! Here the dividend is >= 2**(31-N) or so. We must be careful here,
- ! as our usual N-at-a-shot divide step will cause overflow and havoc.
- ! The number of bits in the result here is N*ITER+SC, where SC <= N.
- ! Compute ITER in an unorthodox manner: know we need to shift V into
- ! the top decade: so do not even bother to compare to R.
- 1:
- cmp %o5, %g1
- bgeu 3f
- mov 1, %g7
-
- sll %o5, 4, %o5
-
- b 1b
- add %o4, 1, %o4
-
- ! Now compute %g7.
- 2:
- addcc %o5, %o5, %o5
- bcc Lnot_too_big
- add %g7, 1, %g7
-
- ! We get here if the %o1 overflowed while shifting.
- ! This means that %o3 has the high-order bit set.
- ! Restore %o5 and subtract from %o3.
- sll %g1, 4, %g1 ! high order bit
- srl %o5, 1, %o5 ! rest of %o5
- add %o5, %g1, %o5
-
- b Ldo_single_div
- sub %g7, 1, %g7
-
- Lnot_too_big:
- 3:
- cmp %o5, %o3
- blu 2b
- nop
-
- be Ldo_single_div
- nop
- /* NB: these are commented out in the V8-Sparc manual as well */
- /* (I do not understand this) */
- ! %o5 > %o3: went too far: back up 1 step
- ! srl %o5, 1, %o5
- ! dec %g7
- ! do single-bit divide steps
- !
- ! We have to be careful here. We know that %o3 >= %o5, so we can do the
- ! first divide step without thinking. BUT, the others are conditional,
- ! and are only done if %o3 >= 0. Because both %o3 and %o5 may have the high-
- ! order bit set in the first step, just falling into the regular
- ! division loop will mess up the first time around.
- ! So we unroll slightly...
- Ldo_single_div:
- subcc %g7, 1, %g7
- bl Lend_regular_divide
- nop
-
- sub %o3, %o5, %o3
- mov 1, %o2
-
- b Lend_single_divloop
- nop
- Lsingle_divloop:
- sll %o2, 1, %o2
- bl 1f
- srl %o5, 1, %o5
- ! %o3 >= 0
- sub %o3, %o5, %o3
- b 2f
- add %o2, 1, %o2
- 1: ! %o3 < 0
- add %o3, %o5, %o3
- sub %o2, 1, %o2
- 2:
- Lend_single_divloop:
- subcc %g7, 1, %g7
- bge Lsingle_divloop
- tst %o3
-
- b,a Lend_regular_divide
-
-Lnot_really_big:
-1:
- sll %o5, 4, %o5
-
- cmp %o5, %o3
- bleu 1b
- addcc %o4, 1, %o4
-
- be Lgot_result
- sub %o4, 1, %o4
-
- tst %o3 ! set up for initial iteration
-Ldivloop:
- sll %o2, 4, %o2
- ! depth 1, accumulated bits 0
- bl L.1.16
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 2, accumulated bits 1
- bl L.2.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 3, accumulated bits 3
- bl L.3.19
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits 7
- bl L.4.23
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (7*2+1), %o2
-
-L.4.23:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (7*2-1), %o2
-
-L.3.19:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits 5
- bl L.4.21
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (5*2+1), %o2
-
-L.4.21:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (5*2-1), %o2
-
-L.2.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 3, accumulated bits 1
- bl L.3.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits 3
- bl L.4.19
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (3*2+1), %o2
-
-L.4.19:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (3*2-1), %o2
-
-L.3.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits 1
- bl L.4.17
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (1*2+1), %o2
-
-L.4.17:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (1*2-1), %o2
-
-L.1.16:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 2, accumulated bits -1
- bl L.2.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 3, accumulated bits -1
- bl L.3.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits -1
- bl L.4.15
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-1*2+1), %o2
-
-L.4.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-1*2-1), %o2
-
-L.3.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits -3
- bl L.4.13
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-3*2+1), %o2
-
-L.4.13:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-3*2-1), %o2
-
-L.2.15:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 3, accumulated bits -3
- bl L.3.13
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- ! depth 4, accumulated bits -5
- bl L.4.11
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-5*2+1), %o2
-
-L.4.11:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-5*2-1), %o2
-
-L.3.13:
- ! remainder is negative
- addcc %o3,%o5,%o3
- ! depth 4, accumulated bits -7
- bl L.4.9
- srl %o5,1,%o5
- ! remainder is positive
- subcc %o3,%o5,%o3
- b 9f
- add %o2, (-7*2+1), %o2
-
-L.4.9:
- ! remainder is negative
- addcc %o3,%o5,%o3
- b 9f
- add %o2, (-7*2-1), %o2
-
- 9:
-Lend_regular_divide:
- subcc %o4, 1, %o4
- bge Ldivloop
- tst %o3
-
- bl,a Lgot_result
- ! non-restoring fixup here (one instruction only!)
- add %o3, %o1, %o3
-
-Lgot_result:
-
- retl
- mov %o3, %o0
-
- .globl .urem_patch
-.urem_patch:
- wr %g0, 0x0, %y
- nop
- nop
- nop
- udiv %o0, %o1, %o2
- umul %o2, %o1, %o2
- retl
- sub %o0, %o2, %o0