op-4.h

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

/* Software floating-point emulation.
   Basic four-word fraction declaration and manipulation.
   Copyright (C) 1997,1998,1999 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Richard Henderson ([e-mail]),
		  Jakub Jelinek ([e-mail]),
		  David S. Miller ([e-mail]) and
		  Peter Maydell ([e-mail]).

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Library General Public License as
   published by the Free Software Foundation; either version 2 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
   Library General Public License for more details.

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

#ifndef __MATH_EMU_OP_4_H__
#define __MATH_EMU_OP_4_H__

#define _FP_FRAC_DECL_4(X)	_FP_W_TYPE X##_f[4]
#define _FP_FRAC_COPY_4(D,S)			\
  (D##_f[0] = S##_f[0], D##_f[1] = S##_f[1],	\
   D##_f[2] = S##_f[2], D##_f[3] = S##_f[3])
#define _FP_FRAC_SET_4(X,I)	__FP_FRAC_SET_4(X, I)
#define _FP_FRAC_HIGH_4(X)	(X##_f[3])
#define _FP_FRAC_LOW_4(X)	(X##_f[0])
#define _FP_FRAC_WORD_4(X,w)	(X##_f[w])

#define _FP_FRAC_SLL_4(X,N)						\
  do {									\
    _FP_I_TYPE _up, _down, _skip, _i;					\
    _skip = (N) / _FP_W_TYPE_SIZE;					\
    _up = (N) % _FP_W_TYPE_SIZE;					\
    _down = _FP_W_TYPE_SIZE - _up;					\
    if (!_up)								\
      for (_i = 3; _i >= _skip; --_i)					\
	X##_f[_i] = X##_f[_i-_skip];					\
    else								\
      {									\
	for (_i = 3; _i > _skip; --_i)					\
	  X##_f[_i] = X##_f[_i-_skip] << _up				\
		      | X##_f[_i-_skip-1] >> _down;			\
	X##_f[_i--] = X##_f[0] << _up; 					\
      }									\
    for (; _i >= 0; --_i)						\
      X##_f[_i] = 0;							\
  } while (0)

/* This one was broken too */
#define _FP_FRAC_SRL_4(X,N)						\
  do {									\
    _FP_I_TYPE _up, _down, _skip, _i;					\
    _skip = (N) / _FP_W_TYPE_SIZE;					\
    _down = (N) % _FP_W_TYPE_SIZE;					\
    _up = _FP_W_TYPE_SIZE - _down;					\
    if (!_down)								\
      for (_i = 0; _i <= 3-_skip; ++_i)					\
	X##_f[_i] = X##_f[_i+_skip];					\
    else								\
      {									\
	for (_i = 0; _i < 3-_skip; ++_i)				\
	  X##_f[_i] = X##_f[_i+_skip] >> _down				\
		      | X##_f[_i+_skip+1] << _up;			\
	X##_f[_i++] = X##_f[3] >> _down;				\
      }									\
    for (; _i < 4; ++_i)						\
      X##_f[_i] = 0;							\
  } while (0)


/* Right shift with sticky-lsb. 
 * What this actually means is that we do a standard right-shift,
 * but that if any of the bits that fall off the right hand side
 * were one then we always set the LSbit.
 */
#define _FP_FRAC_SRS_4(X,N,size)					\
  do {									\
    _FP_I_TYPE _up, _down, _skip, _i;					\
    _FP_W_TYPE _s;							\
    _skip = (N) / _FP_W_TYPE_SIZE;					\
    _down = (N) % _FP_W_TYPE_SIZE;					\
    _up = _FP_W_TYPE_SIZE - _down;					\
    for (_s = _i = 0; _i < _skip; ++_i)					\
      _s |= X##_f[_i];							\
    _s |= X##_f[_i] << _up;						\
/* s is now != 0 if we want to set the LSbit */				\
    if (!_down)								\
      for (_i = 0; _i <= 3-_skip; ++_i)					\
	X##_f[_i] = X##_f[_i+_skip];					\
    else								\
      {									\
	for (_i = 0; _i < 3-_skip; ++_i)				\
	  X##_f[_i] = X##_f[_i+_skip] >> _down				\
		      | X##_f[_i+_skip+1] << _up;			\
	X##_f[_i++] = X##_f[3] >> _down;				\
      }									\
    for (; _i < 4; ++_i)						\
      X##_f[_i] = 0;							\
    /* don't fix the LSB until the very end when we're sure f[0] is stable */	\
    X##_f[0] |= (_s != 0);						\
  } while (0)

#define _FP_FRAC_ADD_4(R,X,Y)						\
  __FP_FRAC_ADD_4(R##_f[3], R##_f[2], R##_f[1], R##_f[0],		\
		  X##_f[3], X##_f[2], X##_f[1], X##_f[0],		\
		  Y##_f[3], Y##_f[2], Y##_f[1], Y##_f[0])

#define _FP_FRAC_SUB_4(R,X,Y)						\
  __FP_FRAC_SUB_4(R##_f[3], R##_f[2], R##_f[1], R##_f[0],		\
		  X##_f[3], X##_f[2], X##_f[1], X##_f[0],		\
		  Y##_f[3], Y##_f[2], Y##_f[1], Y##_f[0])

#define _FP_FRAC_DEC_4(X,Y)						\
  __FP_FRAC_DEC_4(X##_f[3], X##_f[2], X##_f[1], X##_f[0],		\
		  Y##_f[3], Y##_f[2], Y##_f[1], Y##_f[0])

#define _FP_FRAC_ADDI_4(X,I)						\
  __FP_FRAC_ADDI_4(X##_f[3], X##_f[2], X##_f[1], X##_f[0], I)

#define _FP_ZEROFRAC_4  0,0,0,0
#define _FP_MINFRAC_4   0,0,0,1
#define _FP_MAXFRAC_4	(~(_FP_WS_TYPE)0), (~(_FP_WS_TYPE)0), (~(_FP_WS_TYPE)0), (~(_FP_WS_TYPE)0)

#define _FP_FRAC_ZEROP_4(X)     ((X##_f[0] | X##_f[1] | X##_f[2] | X##_f[3]) == 0)
#define _FP_FRAC_NEGP_4(X)      ((_FP_WS_TYPE)X##_f[3] < 0)
#define _FP_FRAC_OVERP_4(fs,X)  (_FP_FRAC_HIGH_##fs(X) & _FP_OVERFLOW_##fs)

#define _FP_FRAC_EQ_4(X,Y)				\
 (X##_f[0] == Y##_f[0] && X##_f[1] == Y##_f[1]		\
  && X##_f[2] == Y##_f[2] && X##_f[3] == Y##_f[3])

#define _FP_FRAC_GT_4(X,Y)				\
 (X##_f[3] > Y##_f[3] ||				\
  (X##_f[3] == Y##_f[3] && (X##_f[2] > Y##_f[2] ||	\
   (X##_f[2] == Y##_f[2] && (X##_f[1] > Y##_f[1] ||	\
    (X##_f[1] == Y##_f[1] && X##_f[0] > Y##_f[0])	\
   ))							\
  ))							\
 )

#define _FP_FRAC_GE_4(X,Y)				\
 (X##_f[3] > Y##_f[3] ||				\
  (X##_f[3] == Y##_f[3] && (X##_f[2] > Y##_f[2] ||	\
   (X##_f[2] == Y##_f[2] && (X##_f[1] > Y##_f[1] ||	\
    (X##_f[1] == Y##_f[1] && X##_f[0] >= Y##_f[0])	\
   ))							\
  ))							\
 )


#define _FP_FRAC_CLZ_4(R,X)		\
  do {					\
    if (X##_f[3])			\
    {					\
	__FP_CLZ(R,X##_f[3]);		\
    }					\
    else if (X##_f[2])			\
    {					\
	__FP_CLZ(R,X##_f[2]);		\
	R += _FP_W_TYPE_SIZE;		\
    }					\
    else if (X##_f[1])			\
    {					\
	__FP_CLZ(R,X##_f[2]);		\
	R += _FP_W_TYPE_SIZE*2;		\
    }					\
    else				\
    {					\
	__FP_CLZ(R,X##_f[0]);		\
	R += _FP_W_TYPE_SIZE*3;		\
    }					\
  } while(0)


#define _FP_UNPACK_RAW_4(fs, X, val)				\
  do {								\
    union _FP_UNION_##fs _flo; _flo.flt = (val);		\
    X##_f[0] = _flo.bits.frac0;					\
    X##_f[1] = _flo.bits.frac1;					\
    X##_f[2] = _flo.bits.frac2;					\
    X##_f[3] = _flo.bits.frac3;					\
    X##_e  = _flo.bits.exp;					\
    X##_s  = _flo.bits.sign;					\
  } while (0)

#define _FP_UNPACK_RAW_4_P(fs, X, val)				\
  do {								\
    union _FP_UNION_##fs *_flo =				\
      (union _FP_UNION_##fs *)(val);				\
								\
    X##_f[0] = _flo->bits.frac0;				\
    X##_f[1] = _flo->bits.frac1;				\
    X##_f[2] = _flo->bits.frac2;				\
    X##_f[3] = _flo->bits.frac3;				\
    X##_e  = _flo->bits.exp;					\
    X##_s  = _flo->bits.sign;					\
  } while (0)

#define _FP_PACK_RAW_4(fs, val, X)				\
  do {								\
    union _FP_UNION_##fs _flo;					\
    _flo.bits.frac0 = X##_f[0];					\
    _flo.bits.frac1 = X##_f[1];					\
    _flo.bits.frac2 = X##_f[2];					\
    _flo.bits.frac3 = X##_f[3];					\
    _flo.bits.exp   = X##_e;					\
    _flo.bits.sign  = X##_s;					\
    (val) = _flo.flt;				   		\
  } while (0)

#define _FP_PACK_RAW_4_P(fs, val, X)				\
  do {								\
    union _FP_UNION_##fs *_flo =				\
      (union _FP_UNION_##fs *)(val);				\
								\
    _flo->bits.frac0 = X##_f[0];				\
    _flo->bits.frac1 = X##_f[1];				\
    _flo->bits.frac2 = X##_f[2];				\
    _flo->bits.frac3 = X##_f[3];				\
    _flo->bits.exp   = X##_e;					\
    _flo->bits.sign  = X##_s;					\
  } while (0)

/*
 * Multiplication algorithms:
 */

/* Given a 1W * 1W => 2W primitive, do the extended multiplication.  */

#define _FP_MUL_MEAT_4_wide(wfracbits, R, X, Y, doit)			    \
  do {									    \
    _FP_FRAC_DECL_8(_z); _FP_FRAC_DECL_2(_b); _FP_FRAC_DECL_2(_c);	    \
    _FP_FRAC_DECL_2(_d); _FP_FRAC_DECL_2(_e); _FP_FRAC_DECL_2(_f);	    \
									    \
    doit(_FP_FRAC_WORD_8(_z,1), _FP_FRAC_WORD_8(_z,0), X##_f[0], Y##_f[0]); \
    doit(_b_f1, _b_f0, X##_f[0], Y##_f[1]);				    \
    doit(_c_f1, _c_f0, X##_f[1], Y##_f[0]);				    \
    doit(_d_f1, _d_f0, X##_f[1], Y##_f[1]);				    \
    doit(_e_f1, _e_f0, X##_f[0], Y##_f[2]);				    \
    doit(_f_f1, _f_f0, X##_f[2], Y##_f[0]);				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,3),_FP_FRAC_WORD_8(_z,2),	    \
		    _FP_FRAC_WORD_8(_z,1), 0,_b_f1,_b_f0,		    \
		    0,0,_FP_FRAC_WORD_8(_z,1));				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,3),_FP_FRAC_WORD_8(_z,2),	    \
		    _FP_FRAC_WORD_8(_z,1), 0,_c_f1,_c_f0,		    \
		    _FP_FRAC_WORD_8(_z,3),_FP_FRAC_WORD_8(_z,2),	    \
		    _FP_FRAC_WORD_8(_z,1));				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,4),_FP_FRAC_WORD_8(_z,3),	    \
		    _FP_FRAC_WORD_8(_z,2), 0,_d_f1,_d_f0,		    \
		    0,_FP_FRAC_WORD_8(_z,3),_FP_FRAC_WORD_8(_z,2));	    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,4),_FP_FRAC_WORD_8(_z,3),	    \
		    _FP_FRAC_WORD_8(_z,2), 0,_e_f1,_e_f0,		    \
		    _FP_FRAC_WORD_8(_z,4),_FP_FRAC_WORD_8(_z,3),	    \
		    _FP_FRAC_WORD_8(_z,2));				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,4),_FP_FRAC_WORD_8(_z,3),	    \
		    _FP_FRAC_WORD_8(_z,2), 0,_f_f1,_f_f0,		    \
		    _FP_FRAC_WORD_8(_z,4),_FP_FRAC_WORD_8(_z,3),	    \
		    _FP_FRAC_WORD_8(_z,2));				    \
    doit(_b_f1, _b_f0, X##_f[0], Y##_f[3]);				    \
    doit(_c_f1, _c_f0, X##_f[3], Y##_f[0]);				    \
    doit(_d_f1, _d_f0, X##_f[1], Y##_f[2]);				    \
    doit(_e_f1, _e_f0, X##_f[2], Y##_f[1]);				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,5),_FP_FRAC_WORD_8(_z,4),	    \
		    _FP_FRAC_WORD_8(_z,3), 0,_b_f1,_b_f0,		    \
		    0,_FP_FRAC_WORD_8(_z,4),_FP_FRAC_WORD_8(_z,3));	    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,5),_FP_FRAC_WORD_8(_z,4),	    \
		    _FP_FRAC_WORD_8(_z,3), 0,_c_f1,_c_f0,		    \
		    _FP_FRAC_WORD_8(_z,5),_FP_FRAC_WORD_8(_z,4),	    \
		    _FP_FRAC_WORD_8(_z,3));				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,5),_FP_FRAC_WORD_8(_z,4),	    \
		    _FP_FRAC_WORD_8(_z,3), 0,_d_f1,_d_f0,		    \
		    _FP_FRAC_WORD_8(_z,5),_FP_FRAC_WORD_8(_z,4),	    \
		    _FP_FRAC_WORD_8(_z,3));				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,5),_FP_FRAC_WORD_8(_z,4),	    \
		    _FP_FRAC_WORD_8(_z,3), 0,_e_f1,_e_f0,		    \
		    _FP_FRAC_WORD_8(_z,5),_FP_FRAC_WORD_8(_z,4),	    \
		    _FP_FRAC_WORD_8(_z,3));				    \
    doit(_b_f1, _b_f0, X##_f[2], Y##_f[2]);				    \
    doit(_c_f1, _c_f0, X##_f[1], Y##_f[3]);				    \
    doit(_d_f1, _d_f0, X##_f[3], Y##_f[1]);				    \
    doit(_e_f1, _e_f0, X##_f[2], Y##_f[3]);				    \
    doit(_f_f1, _f_f0, X##_f[3], Y##_f[2]);				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,6),_FP_FRAC_WORD_8(_z,5),	    \
		    _FP_FRAC_WORD_8(_z,4), 0,_b_f1,_b_f0,		    \
		    0,_FP_FRAC_WORD_8(_z,5),_FP_FRAC_WORD_8(_z,4));	    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,6),_FP_FRAC_WORD_8(_z,5),	    \
		    _FP_FRAC_WORD_8(_z,4), 0,_c_f1,_c_f0,		    \
		    _FP_FRAC_WORD_8(_z,6),_FP_FRAC_WORD_8(_z,5),	    \
		    _FP_FRAC_WORD_8(_z,4));				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,6),_FP_FRAC_WORD_8(_z,5),	    \
		    _FP_FRAC_WORD_8(_z,4), 0,_d_f1,_d_f0,		    \
		    _FP_FRAC_WORD_8(_z,6),_FP_FRAC_WORD_8(_z,5),	    \
		    _FP_FRAC_WORD_8(_z,4));				    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,7),_FP_FRAC_WORD_8(_z,6),	    \
		    _FP_FRAC_WORD_8(_z,5), 0,_e_f1,_e_f0,		    \
		    0,_FP_FRAC_WORD_8(_z,6),_FP_FRAC_WORD_8(_z,5));	    \
    __FP_FRAC_ADD_3(_FP_FRAC_WORD_8(_z,7),_FP_FRAC_WORD_8(_z,6),	    \
		    _FP_FRAC_WORD_8(_z,5), 0,_f_f1,_f_f0,		    \
		    _FP_FRAC_WORD_8(_z,7),_FP_FRAC_WORD_8(_z,6),	    \
		    _FP_FRAC_WORD_8(_z,5));				    \
    doit(_b_f1, _b_f0, X##_f[3], Y##_f[3]);				    \
    __FP_FRAC_ADD_2(_FP_FRAC_WORD_8(_z,7),_FP_FRAC_WORD_8(_z,6),	    \
		    _b_f1,_b_f0,					    \
		    _FP_FRAC_WORD_8(_z,7),_FP_FRAC_WORD_8(_z,6));	    \
									    \
    /* Normalize since we know where the msb of the multiplicands	    \
       were (bit B), we know that the msb of the of the product is	    \
       at either 2B or 2B-1.  */					    \
    _FP_FRAC_SRS_8(_z, wfracbits-1, 2*wfracbits);			    \
    __FP_FRAC_SET_4(R, _FP_FRAC_WORD_8(_z,3), _FP_FRAC_WORD_8(_z,2),	    \
		    _FP_FRAC_WORD_8(_z,1), _FP_FRAC_WORD_8(_z,0));	    \
  } while (0)

#define _FP_MUL_MEAT_4_gmp(wfracbits, R, X, Y)				    \
  do {									    \
    _FP_FRAC_DECL_8(_z);						    \
									    \
    mpn_mul_n(_z_f, _x_f, _y_f, 4);					    \
									    \
    /* Normalize since we know where the msb of the multiplicands	    \
       were (bit B), we know that the msb of the of the product is	    \
       at either 2B or 2B-1.  */					    \
    _FP_FRAC_SRS_8(_z, wfracbits-1, 2*wfracbits);	 		    \
    __FP_FRAC_SET_4(R, _FP_FRAC_WORD_8(_z,3), _FP_FRAC_WORD_8(_z,2),	    \
		    _FP_FRAC_WORD_8(_z,1), _FP_FRAC_WORD_8(_z,0));	    \