divdi3.c

File system using stacked.

/* 64-bit multiplication and division
   Copyright (C) 1989, 1992-1999, 2000, 2001, 2002, 2003
   Free Software Foundation, Inc.
   This file is part of the GNU C Library.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, write to the Free
   Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
   02111-1307 USA.  */

//#include <stdlib.h>
//#include <bits/wordsize.h>
#include "db.h"
//#include "longlong.h"

#define __BITS4 (W_TYPE_SIZE / 4)
#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2))
#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1))
#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2))

#ifndef W_TYPE_SIZE
#define W_TYPE_SIZE	32
#define UWtype		USItype
#define UHWtype		USItype
#define UDWtype		UDItype
#endif

/* Define auxiliary asm macros.

   1) umul_ppmm(high_prod, low_prod, multipler, multiplicand) multiplies two
   UWtype integers MULTIPLER and MULTIPLICAND, and generates a two UWtype
   word product in HIGH_PROD and LOW_PROD.

   2) __umulsidi3(a,b) multiplies two UWtype integers A and B, and returns a
   UDWtype product.  This is just a variant of umul_ppmm.

   3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
   denominator) divides a UDWtype, composed by the UWtype integers
   HIGH_NUMERATOR and LOW_NUMERATOR, by DENOMINATOR and places the quotient
   in QUOTIENT and the remainder in REMAINDER.  HIGH_NUMERATOR must be less
   than DENOMINATOR for correct operation.  If, in addition, the most
   significant bit of DENOMINATOR must be 1, then the pre-processor symbol
   UDIV_NEEDS_NORMALIZATION is defined to 1.

   4) sdiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
   denominator).  Like udiv_qrnnd but the numbers are signed.  The quotient
   is rounded towards 0.

   5) count_leading_zeros(count, x) counts the number of zero-bits from the
   msb to the first nonzero bit in the UWtype X.  This is the number of
   steps X needs to be shifted left to set the msb.  Undefined for X == 0,
   unless the symbol COUNT_LEADING_ZEROS_0 is defined to some value.

   6) count_trailing_zeros(count, x) like count_leading_zeros, but counts
   from the least significant end.

   7) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1,
   high_addend_2, low_addend_2) adds two UWtype integers, composed by
   HIGH_ADDEND_1 and LOW_ADDEND_1, and HIGH_ADDEND_2 and LOW_ADDEND_2
   respectively.  The result is placed in HIGH_SUM and LOW_SUM.  Overflow
   (i.e. carry out) is not stored anywhere, and is lost.

   8) sub_ddmmss(high_difference, low_difference, high_minuend, low_minuend,
   high_subtrahend, low_subtrahend) subtracts two two-word UWtype integers,
   composed by HIGH_MINUEND_1 and LOW_MINUEND_1, and HIGH_SUBTRAHEND_2 and
   LOW_SUBTRAHEND_2 respectively.  The result is placed in HIGH_DIFFERENCE
   and LOW_DIFFERENCE.  Overflow (i.e. carry out) is not stored anywhere,
   and is lost.

   If any of these macros are left undefined for a particular CPU,
   C macros are used.  */

/* The CPUs come in alphabetical order below.

   Please add support for more CPUs here, or improve the current support
   for the CPUs below!
   (E.g. WE32100, IBM360.)  */


#if (defined (__i386__) || defined (__i486__)) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
  __asm__ ("addl %5,%1\n\tadcl %3,%0"					\
	   : "=r" ((USItype) (sh)),					\
	     "=&r" ((USItype) (sl))					\
	   : "%0" ((USItype) (ah)),					\
	     "g" ((USItype) (bh)),					\
	     "%1" ((USItype) (al)),					\
	     "g" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
  __asm__ ("subl %5,%1\n\tsbbl %3,%0"					\
	   : "=r" ((USItype) (sh)),					\
	     "=&r" ((USItype) (sl))					\
	   : "0" ((USItype) (ah)),					\
	     "g" ((USItype) (bh)),					\
	     "1" ((USItype) (al)),					\
	     "g" ((USItype) (bl)))
#define umul_ppmm(w1, w0, u, v) \
  __asm__ ("mull %3"							\
	   : "=a" ((USItype) (w0)),					\
	     "=d" ((USItype) (w1))					\
	   : "%0" ((USItype) (u)),					\
	     "rm" ((USItype) (v)))
#define udiv_qrnnd(q, r, n1, n0, dv) \
  __asm__ ("divl %4"							\
	   : "=a" ((USItype) (q)),					\
	     "=d" ((USItype) (r))					\
	   : "0" ((USItype) (n0)),					\
	     "1" ((USItype) (n1)),					\
	     "rm" ((USItype) (dv)))
#define count_leading_zeros(count, x) \
  do {									\
    USItype __cbtmp;							\
    __asm__ ("bsrl %1,%0"						\
	     : "=r" (__cbtmp) : "rm" ((USItype) (x)));			\
    (count) = __cbtmp ^ 31;						\
  } while (0)
#define count_trailing_zeros(count, x) \
  __asm__ ("bsfl %1,%0" : "=r" (count) : "rm" ((USItype)(x)))
#define UMUL_TIME 40
#define UDIV_TIME 40
#endif /* 80x86 */

#ifndef UDIV_NEEDS_NORMALIZATION
#define UDIV_NEEDS_NORMALIZATION 0
#endif


static UDWtype
__udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp)
{
  DWunion ww;
  DWunion nn, dd;
  DWunion rr;
  unsigned int  d0, d1, n0, n1, n2;
  UWtype q0, q1;
  UWtype b, bm;

  nn.ll = n;
  dd.ll = d;

  d0 = dd.s.low;
  d1 = dd.s.high;
  n0 = nn.s.low;
  n1 = nn.s.high;

#if !UDIV_NEEDS_NORMALIZATION
  if (d1 == 0)
    {
      if (d0 > n1)
	{
	  /* 0q = nn / 0D */

	  udiv_qrnnd (q0, n0, n1, n0, d0);
	  q1 = 0;

	  /* Remainder in n0.  */
	}
      else
	{
	  /* qq = NN / 0d */

	  if (d0 == 0)
	    d0 = 1 / d0;	/* Divide intentionally by zero.  */

	  udiv_qrnnd (q1, n1, 0, n1, d0);
	  udiv_qrnnd (q0, n0, n1, n0, d0);

	  /* Remainder in n0.  */
	}

      if (rp != 0)
	{
	  rr.s.low = n0;
	  rr.s.high = 0;
	  *rp = rr.ll;
	}
    }

#else /* UDIV_NEEDS_NORMALIZATION */

  if (d1 == 0)
    {
      if (d0 > n1)
	{
	  /* 0q = nn / 0D */

	  count_leading_zeros (bm, d0);

	  if (bm != 0)
	    {
	      /* Normalize, i.e. make the most significant bit of the
		 denominator set.  */

	      d0 = d0 << bm;
	      n1 = (n1 << bm) | (n0 >> (W_TYPE_SIZE - bm));
	      n0 = n0 << bm;
	    }

	  udiv_qrnnd (q0, n0, n1, n0, d0);
	  q1 = 0;

	  /* Remainder in n0 >> bm.  */
	}
      else
	{
	  /* qq = NN / 0d */

	  if (d0 == 0)
	    d0 = 1 / d0;	/* Divide intentionally by zero.  */

	  count_leading_zeros (bm, d0);

	  if (bm == 0)
	    {
	      /* From (n1 >= d0) /\ (the most significant bit of d0 is set),
		 conclude (the most significant bit of n1 is set) /\ (the
		 leading quotient digit q1 = 1).

		 This special case is necessary, not an optimization.
		 (Shifts counts of W_TYPE_SIZE are undefined.)  */

	      n1 -= d0;
	      q1 = 1;
	    }
	  else
	    {
	      /* Normalize.  */

	      b = W_TYPE_SIZE - bm;

	      d0 = d0 << bm;
	      n2 = n1 >> b;
	      n1 = (n1 << bm) | (n0 >> b);
	      n0 = n0 << bm;

	      udiv_qrnnd (q1, n1, n2, n1, d0);
	    }

	  /* n1 != d0...  */

	  udiv_qrnnd (q0, n0, n1, n0, d0);

	  /* Remainder in n0 >> bm.  */
	}

      if (rp != 0)
	{
	  rr.s.low = n0 >> bm;
	  rr.s.high = 0;
	  *rp = rr.ll;
	}
    }
#endif /* UDIV_NEEDS_NORMALIZATION */

  else
    {
      if (d1 > n1)
	{
	  /* 00 = nn / DD */

	  q0 = 0;
	  q1 = 0;

	  /* Remainder in n1n0.  */
	  if (rp != 0)
	    {
	      rr.s.low = n0;
	      rr.s.high = n1;
	      *rp = rr.ll;
	    }
	}
      else
	{
	  /* 0q = NN / dd */

	  count_leading_zeros (bm, d1);
	  if (bm == 0)
	    {
	      /* From (n1 >= d1) /\ (the most significant bit of d1 is set),
		 conclude (the most significant bit of n1 is set) /\ (the
		 quotient digit q0 = 0 or 1).

		 This special case is necessary, not an optimization.  */

	      /* The condition on the next line takes advantage of that
		 n1 >= d1 (true due to program flow).  */
	      if (n1 > d1 || n0 >= d0)
		{
		  q0 = 1;
		  sub_ddmmss (n1, n0, n1, n0, d1, d0);
		}
	      else
		q0 = 0;

	      q1 = 0;

	      if (rp != 0)
		{
		  rr.s.low = n0;
		  rr.s.high = n1;
		  *rp = rr.ll;
		}
	    }
	  else
	    {
	      UWtype m1, m0;
	      /* Normalize.  */

	      b = W_TYPE_SIZE - bm;

	      d1 = (d1 << bm) | (d0 >> b);
	      d0 = d0 << bm;
	      n2 = n1 >> b;
	      n1 = (n1 << bm) | (n0 >> b);
	      n0 = n0 << bm;

	      udiv_qrnnd (q0, n1, n2, n1, d1);
	      umul_ppmm (m1, m0, q0, d0);

	      if (m1 > n1 || (m1 == n1 && m0 > n0))
		{
		  q0--;
		  sub_ddmmss (m1, m0, m1, m0, d1, d0);
		}

	      q1 = 0;

	      /* Remainder in (n1n0 - m1m0) >> bm.  */
	      if (rp != 0)
		{
		  sub_ddmmss (n1, n0, n1, n0, m1, m0);
		  rr.s.low = (n1 << b) | (n0 >> bm);
		  rr.s.high = n1 >> bm;
		  *rp = rr.ll;
		}
	    }
	}
    }

  ww.s.low = q0;
  ww.s.high = q1;
  return ww.ll;
}

DWtype
__divdi3 (DWtype u, DWtype v)
{
  Wtype c = 0;
  DWtype w;

  if (u < 0)
    {
      c = ~c;
      u = -u;
    }
  if (v < 0)
    {
      c = ~c;
      v = -v;
    }
  w = __udivmoddi4 (u, v, NULL);
  if (c)
    w = -w;
  return w;
}

DWtype
__moddi3 (DWtype u, DWtype v)
{
  Wtype c = 0;
  DWtype w;

  if (u < 0)
    {
      c = ~c;
      u = -u;
    }
  if (v < 0)
    v = -v;
  __udivmoddi4 (u, v, &w);
  if (c)
    w = -w;
  return w;
}

UDWtype
__udivdi3 (UDWtype u, UDWtype v)
{
  return __udivmoddi4 (u, v, NULL);
}

UDWtype
__umoddi3 (UDWtype u, UDWtype v)
{
  UDWtype w;

  __udivmoddi4 (u, v, &w);
  return w;
}

/* We declare these with compat_symbol so that they are not visible at
   link time.  Programs must use the functions from libgcc.  */
#if defined HAVE_ELF && defined SHARED && defined DO_VERSIONING
# include <shlib-compat.h>
compat_symbol (libc, __divdi3, __divdi3, GLIBC_2_0);
compat_symbol (libc, __moddi3, __moddi3, GLIBC_2_0);
compat_symbol (libc, __udivdi3, __udivdi3, GLIBC_2_0);
compat_symbol (libc, __umoddi3, __umoddi3, GLIBC_2_0);
#endif