/* longlong.h -- definitions for mixed size 32/64 bit arithmetic.
 * Modified by No Such Labs. (C) 2015. See README.
 *
 * This file was originally part of Gnu Privacy Guard (GPG), ver. 1.4.10,
 * SHA256(gnupg-1.4.10.tar.gz):
 *        0bfd74660a2f6cedcf7d8256db4a63c996ffebbcdc2cf54397bfb72878c5a85a
 * (C) 1994-2005 Free Software Foundation, Inc.
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program 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 General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
*/

/* You have to define the following before including this file:

   UWtype -- An unsigned type, default type for operations (typically a "word")
   UHWtype -- An unsigned type, at least half the size of UWtype.
   UDWtype -- An unsigned type, at least twice as large a UWtype
   W_TYPE_SIZE -- size in bits of UWtype

   SItype, USItype -- Signed and unsigned 32 bit types.
   DItype, UDItype -- Signed and unsigned 64 bit types.

   On a 32 bit machine UWtype should typically be USItype;
   on a 64 bit machine, UWtype should typically be UDItype.
*/

#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))

/* This is used to make sure no undesirable sharing between different libraries
   that use this file takes place.  */
#ifndef __MPN
#define __MPN(x) __##x
#endif

/***************************************
 ***********  Generic Versions	********
 ***************************************/
#if !defined (umul_ppmm) && defined (__umulsidi3)
#define umul_ppmm(ph, pl, m0, m1) \
  {									\
    UDWtype __ll = __umulsidi3 (m0, m1);				\
    ph = (UWtype) (__ll >> W_TYPE_SIZE);				\
    pl = (UWtype) __ll; 						\
  }
#endif

#if !defined (__umulsidi3)
#define __umulsidi3(u, v) \
  ({UWtype __hi, __lo;							\
    umul_ppmm (__hi, __lo, u, v);					\
    ((UDWtype) __hi << W_TYPE_SIZE) | __lo; })
#endif

/* If this machine has no inline assembler, use C macros.  */

#if !defined (add_ssaaaa)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
  do {									\
    UWtype __x; 							\
    __x = (al) + (bl);							\
    (sh) = (ah) + (bh) + (__x < (al));					\
    (sl) = __x; 							\
  } while (0)
#endif

#if !defined (sub_ddmmss)
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
  do {									\
    UWtype __x; 							\
    __x = (al) - (bl);							\
    (sh) = (ah) - (bh) - (__x > (al));					\
    (sl) = __x; 							\
  } while (0)
#endif

#if !defined (umul_ppmm)
#define umul_ppmm(w1, w0, u, v) 					\
  do {									\
    UWtype __x0, __x1, __x2, __x3;					\
    UHWtype __ul, __vl, __uh, __vh;					\
    UWtype __u = (u), __v = (v);					\
									\
    __ul = __ll_lowpart (__u);						\
    __uh = __ll_highpart (__u); 					\
    __vl = __ll_lowpart (__v);						\
    __vh = __ll_highpart (__v); 					\
									\
    __x0 = (UWtype) __ul * __vl;					\
    __x1 = (UWtype) __ul * __vh;					\
    __x2 = (UWtype) __uh * __vl;					\
    __x3 = (UWtype) __uh * __vh;					\
									\
    __x1 += __ll_highpart (__x0);/* this can't give carry */            \
    __x1 += __x2;		/* but this indeed can */		\
    if (__x1 < __x2)		/* did we get it? */			\
      __x3 += __ll_B;		/* yes, add it in the proper pos. */	\
									\
    (w1) = __x3 + __ll_highpart (__x1); 				\
    (w0) = (__ll_lowpart (__x1) << W_TYPE_SIZE/2) + __ll_lowpart (__x0);\
  } while (0)
#endif

#if !defined (umul_ppmm)
#define smul_ppmm(w1, w0, u, v) 					\
  do {									\
    UWtype __w1;							\
    UWtype __m0 = (u), __m1 = (v);					\
    umul_ppmm (__w1, w0, __m0, __m1);					\
    (w1) = __w1 - (-(__m0 >> (W_TYPE_SIZE - 1)) & __m1) 		\
		- (-(__m1 >> (W_TYPE_SIZE - 1)) & __m0);		\
  } while (0)
#endif

/* Define this unconditionally, so it can be used for debugging.  */
#define __udiv_qrnnd_c(q, r, n1, n0, d) \
  do {									\
    UWtype __d1, __d0, __q1, __q0, __r1, __r0, __m;			\
    __d1 = __ll_highpart (d);						\
    __d0 = __ll_lowpart (d);						\
									\
    __r1 = (n1) % __d1; 						\
    __q1 = (n1) / __d1; 						\
    __m = (UWtype) __q1 * __d0; 					\
    __r1 = __r1 * __ll_B | __ll_highpart (n0);				\
    if (__r1 < __m)							\
      { 								\
	__q1--, __r1 += (d);						\
	if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\
	  if (__r1 < __m)						\
	    __q1--, __r1 += (d);					\
      } 								\
    __r1 -= __m;							\
									\
    __r0 = __r1 % __d1; 						\
    __q0 = __r1 / __d1; 						\
    __m = (UWtype) __q0 * __d0; 					\
    __r0 = __r0 * __ll_B | __ll_lowpart (n0);				\
    if (__r0 < __m)							\
      { 								\
	__q0--, __r0 += (d);						\
	if (__r0 >= (d))						\
	  if (__r0 < __m)						\
	    __q0--, __r0 += (d);					\
      } 								\
    __r0 -= __m;							\
									\
    (q) = (UWtype) __q1 * __ll_B | __q0;				\
    (r) = __r0; 							\
  } while (0)

/* If the processor has no udiv_qrnnd but sdiv_qrnnd, go through
   __udiv_w_sdiv (defined in libgcc or elsewhere).  */
#if !defined (udiv_qrnnd) && defined (sdiv_qrnnd)
#define udiv_qrnnd(q, r, nh, nl, d) \
  do {									\
    UWtype __r; 							\
    (q) = __MPN(udiv_w_sdiv) (&__r, nh, nl, d); 			\
    (r) = __r;								\
  } while (0)
#endif

/* If udiv_qrnnd was not defined for this processor, use __udiv_qrnnd_c.  */
#if !defined (udiv_qrnnd)
#define UDIV_NEEDS_NORMALIZATION 1
#define udiv_qrnnd __udiv_qrnnd_c
#endif

#if !defined (count_leading_zeros)
extern
#ifdef __STDC__
const
#endif
unsigned char __clz_tab[];
#define MPI_INTERNAL_NEED_CLZ_TAB 1
#define count_leading_zeros(count, x) \
  do {									\
    UWtype __xr = (x);							\
    UWtype __a; 							\
									\
    if (W_TYPE_SIZE <= 32)						\
      { 								\
	__a = __xr < ((UWtype) 1 << 2*__BITS4)				\
	  ? (__xr < ((UWtype) 1 << __BITS4) ? 0 : __BITS4)		\
	  : (__xr < ((UWtype) 1 << 3*__BITS4) ?  2*__BITS4 : 3*__BITS4);\
      } 								\
    else								\
      { 								\
	for (__a = W_TYPE_SIZE - 8; __a > 0; __a -= 8)			\
	  if (((__xr >> __a) & 0xff) != 0)				\
	    break;							\
      } 								\
									\
    (count) = W_TYPE_SIZE - (__clz_tab[__xr >> __a] + __a);		\
  } while (0)
/* This version gives a well-defined value for zero. */
#define COUNT_LEADING_ZEROS_0 W_TYPE_SIZE
#endif

#if !defined (count_trailing_zeros)
/* Define count_trailing_zeros using count_leading_zeros.  The latter might be
   defined in asm, but if it is not, the C version above is good enough.  */
#define count_trailing_zeros(count, x) \
  do {									\
    UWtype __ctz_x = (x);						\
    UWtype __ctz_c;							\
    count_leading_zeros (__ctz_c, __ctz_x & -__ctz_x);			\
    (count) = W_TYPE_SIZE - 1 - __ctz_c;				\
  } while (0)
#endif

#ifndef UDIV_NEEDS_NORMALIZATION
#define UDIV_NEEDS_NORMALIZATION 0
#endif