| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | #define _FP_DECL(wc, X)			\ | 
 | 2 |   _FP_I_TYPE X##_c, X##_s, X##_e;	\ | 
 | 3 |   _FP_FRAC_DECL_##wc(X) | 
 | 4 |  | 
 | 5 | /* | 
 | 6 |  * Finish truely unpacking a native fp value by classifying the kind | 
 | 7 |  * of fp value and normalizing both the exponent and the fraction. | 
 | 8 |  */ | 
 | 9 |  | 
 | 10 | #define _FP_UNPACK_CANONICAL(fs, wc, X)					\ | 
 | 11 | do {									\ | 
 | 12 |   switch (X##_e)							\ | 
 | 13 |   {									\ | 
 | 14 |   default:								\ | 
 | 15 |     _FP_FRAC_HIGH_##wc(X) |= _FP_IMPLBIT_##fs;				\ | 
 | 16 |     _FP_FRAC_SLL_##wc(X, _FP_WORKBITS);					\ | 
 | 17 |     X##_e -= _FP_EXPBIAS_##fs;						\ | 
 | 18 |     X##_c = FP_CLS_NORMAL;						\ | 
 | 19 |     break;								\ | 
 | 20 | 									\ | 
 | 21 |   case 0:								\ | 
 | 22 |     if (_FP_FRAC_ZEROP_##wc(X))						\ | 
 | 23 |       X##_c = FP_CLS_ZERO;						\ | 
 | 24 |     else								\ | 
 | 25 |       {									\ | 
 | 26 | 	/* a denormalized number */					\ | 
 | 27 | 	_FP_I_TYPE _shift;						\ | 
 | 28 | 	_FP_FRAC_CLZ_##wc(_shift, X);					\ | 
 | 29 | 	_shift -= _FP_FRACXBITS_##fs;					\ | 
 | 30 | 	_FP_FRAC_SLL_##wc(X, (_shift+_FP_WORKBITS));			\ | 
 | 31 | 	X##_e -= _FP_EXPBIAS_##fs - 1 + _shift;				\ | 
 | 32 | 	X##_c = FP_CLS_NORMAL;						\ | 
 | 33 |       }									\ | 
 | 34 |     break;								\ | 
 | 35 | 									\ | 
 | 36 |   case _FP_EXPMAX_##fs:							\ | 
 | 37 |     if (_FP_FRAC_ZEROP_##wc(X))						\ | 
 | 38 |       X##_c = FP_CLS_INF;						\ | 
 | 39 |     else								\ | 
 | 40 |       /* we don't differentiate between signaling and quiet nans */	\ | 
 | 41 |       X##_c = FP_CLS_NAN;						\ | 
 | 42 |     break;								\ | 
 | 43 |   }									\ | 
 | 44 | } while (0) | 
 | 45 |  | 
 | 46 |  | 
 | 47 | /* | 
 | 48 |  * Before packing the bits back into the native fp result, take care | 
 | 49 |  * of such mundane things as rounding and overflow.  Also, for some | 
 | 50 |  * kinds of fp values, the original parts may not have been fully | 
 | 51 |  * extracted -- but that is ok, we can regenerate them now. | 
 | 52 |  */ | 
 | 53 |  | 
 | 54 | #define _FP_PACK_CANONICAL(fs, wc, X)				\ | 
 | 55 | ({int __ret = 0;						\ | 
 | 56 |   switch (X##_c)						\ | 
 | 57 |   {								\ | 
 | 58 |   case FP_CLS_NORMAL:						\ | 
 | 59 |     X##_e += _FP_EXPBIAS_##fs;					\ | 
 | 60 |     if (X##_e > 0)						\ | 
 | 61 |       {								\ | 
 | 62 | 	__ret |= _FP_ROUND(wc, X);				\ | 
 | 63 | 	if (_FP_FRAC_OVERP_##wc(fs, X))				\ | 
 | 64 | 	  {							\ | 
 | 65 | 	    _FP_FRAC_SRL_##wc(X, (_FP_WORKBITS+1));		\ | 
 | 66 | 	    X##_e++;						\ | 
 | 67 | 	  }							\ | 
 | 68 | 	else							\ | 
 | 69 | 	  _FP_FRAC_SRL_##wc(X, _FP_WORKBITS);			\ | 
 | 70 | 	if (X##_e >= _FP_EXPMAX_##fs)				\ | 
 | 71 | 	  {							\ | 
 | 72 | 	    /* overflow to infinity */				\ | 
 | 73 | 	    X##_e = _FP_EXPMAX_##fs;				\ | 
 | 74 | 	    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);		\ | 
 | 75 |             __ret |= EFLAG_OVERFLOW;				\ | 
 | 76 | 	  }							\ | 
 | 77 |       }								\ | 
 | 78 |     else							\ | 
 | 79 |       {								\ | 
 | 80 | 	/* we've got a denormalized number */			\ | 
 | 81 | 	X##_e = -X##_e + 1;					\ | 
 | 82 | 	if (X##_e <= _FP_WFRACBITS_##fs)			\ | 
 | 83 | 	  {							\ | 
 | 84 | 	    _FP_FRAC_SRS_##wc(X, X##_e, _FP_WFRACBITS_##fs);	\ | 
 | 85 | 	    _FP_FRAC_SLL_##wc(X, 1);				\ | 
 | 86 | 	    if (_FP_FRAC_OVERP_##wc(fs, X))			\ | 
 | 87 | 	      {							\ | 
 | 88 | 	        X##_e = 1;					\ | 
 | 89 | 	        _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);	\ | 
 | 90 | 	      }							\ | 
 | 91 | 	    else						\ | 
 | 92 | 	      {							\ | 
 | 93 | 		X##_e = 0;					\ | 
 | 94 | 		_FP_FRAC_SRL_##wc(X, _FP_WORKBITS+1);		\ | 
 | 95 |                 __ret |= EFLAG_UNDERFLOW;			\ | 
 | 96 | 	      }							\ | 
 | 97 | 	  }							\ | 
 | 98 | 	else							\ | 
 | 99 | 	  {							\ | 
 | 100 | 	    /* underflow to zero */				\ | 
 | 101 | 	    X##_e = 0;						\ | 
 | 102 | 	    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);		\ | 
 | 103 |             __ret |= EFLAG_UNDERFLOW;				\ | 
 | 104 | 	  }							\ | 
 | 105 |       }								\ | 
 | 106 |     break;							\ | 
 | 107 | 								\ | 
 | 108 |   case FP_CLS_ZERO:						\ | 
 | 109 |     X##_e = 0;							\ | 
 | 110 |     _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);			\ | 
 | 111 |     break;							\ | 
 | 112 | 								\ | 
 | 113 |   case FP_CLS_INF:						\ | 
 | 114 |     X##_e = _FP_EXPMAX_##fs;					\ | 
 | 115 |     _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);			\ | 
 | 116 |     break;							\ | 
 | 117 | 								\ | 
 | 118 |   case FP_CLS_NAN:						\ | 
 | 119 |     X##_e = _FP_EXPMAX_##fs;					\ | 
 | 120 |     if (!_FP_KEEPNANFRACP)					\ | 
 | 121 |       {								\ | 
 | 122 | 	_FP_FRAC_SET_##wc(X, _FP_NANFRAC_##fs);			\ | 
 | 123 | 	X##_s = 0;						\ | 
 | 124 |       }								\ | 
 | 125 |     else							\ | 
 | 126 |       _FP_FRAC_HIGH_##wc(X) |= _FP_QNANBIT_##fs;		\ | 
 | 127 |     break;							\ | 
 | 128 |   }								\ | 
 | 129 |   __ret;							\ | 
 | 130 | }) | 
 | 131 |  | 
 | 132 |  | 
 | 133 | /* | 
 | 134 |  * Main addition routine.  The input values should be cooked. | 
 | 135 |  */ | 
 | 136 |  | 
 | 137 | #define _FP_ADD(fs, wc, R, X, Y)					     \ | 
 | 138 | do {									     \ | 
 | 139 |   switch (_FP_CLS_COMBINE(X##_c, Y##_c))				     \ | 
 | 140 |   {									     \ | 
 | 141 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NORMAL):			     \ | 
 | 142 |     {									     \ | 
 | 143 |       /* shift the smaller number so that its exponent matches the larger */ \ | 
 | 144 |       _FP_I_TYPE diff = X##_e - Y##_e;					     \ | 
 | 145 | 									     \ | 
 | 146 |       if (diff < 0)							     \ | 
 | 147 | 	{								     \ | 
 | 148 | 	  diff = -diff;							     \ | 
 | 149 | 	  if (diff <= _FP_WFRACBITS_##fs)				     \ | 
 | 150 | 	    _FP_FRAC_SRS_##wc(X, diff, _FP_WFRACBITS_##fs);		     \ | 
 | 151 | 	  else if (!_FP_FRAC_ZEROP_##wc(X))				     \ | 
 | 152 | 	    _FP_FRAC_SET_##wc(X, _FP_MINFRAC_##wc);			     \ | 
 | 153 | 	  else								     \ | 
 | 154 | 	    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);			     \ | 
 | 155 | 	  R##_e = Y##_e;						     \ | 
 | 156 | 	}								     \ | 
 | 157 |       else								     \ | 
 | 158 | 	{								     \ | 
 | 159 | 	  if (diff > 0)							     \ | 
 | 160 | 	    {								     \ | 
 | 161 | 	      if (diff <= _FP_WFRACBITS_##fs)				     \ | 
 | 162 | 	        _FP_FRAC_SRS_##wc(Y, diff, _FP_WFRACBITS_##fs);		     \ | 
 | 163 | 	      else if (!_FP_FRAC_ZEROP_##wc(Y))				     \ | 
 | 164 | 	        _FP_FRAC_SET_##wc(Y, _FP_MINFRAC_##wc);			     \ | 
 | 165 | 	      else							     \ | 
 | 166 | 	        _FP_FRAC_SET_##wc(Y, _FP_ZEROFRAC_##wc);		     \ | 
 | 167 | 	    }								     \ | 
 | 168 | 	  R##_e = X##_e;						     \ | 
 | 169 | 	}								     \ | 
 | 170 | 									     \ | 
 | 171 |       R##_c = FP_CLS_NORMAL;						     \ | 
 | 172 | 									     \ | 
 | 173 |       if (X##_s == Y##_s)						     \ | 
 | 174 | 	{								     \ | 
 | 175 | 	  R##_s = X##_s;						     \ | 
 | 176 | 	  _FP_FRAC_ADD_##wc(R, X, Y);					     \ | 
 | 177 | 	  if (_FP_FRAC_OVERP_##wc(fs, R))				     \ | 
 | 178 | 	    {								     \ | 
 | 179 | 	      _FP_FRAC_SRS_##wc(R, 1, _FP_WFRACBITS_##fs);		     \ | 
 | 180 | 	      R##_e++;							     \ | 
 | 181 | 	    }								     \ | 
 | 182 | 	}								     \ | 
 | 183 |       else								     \ | 
 | 184 | 	{								     \ | 
 | 185 | 	  R##_s = X##_s;						     \ | 
 | 186 | 	  _FP_FRAC_SUB_##wc(R, X, Y);					     \ | 
 | 187 | 	  if (_FP_FRAC_ZEROP_##wc(R))					     \ | 
 | 188 | 	    {								     \ | 
 | 189 | 	      /* return an exact zero */				     \ | 
 | 190 | 	      if (FP_ROUNDMODE == FP_RND_MINF)				     \ | 
 | 191 | 		R##_s |= Y##_s;						     \ | 
 | 192 | 	      else							     \ | 
 | 193 | 		R##_s &= Y##_s;						     \ | 
 | 194 | 	      R##_c = FP_CLS_ZERO;					     \ | 
 | 195 | 	    }								     \ | 
 | 196 | 	  else								     \ | 
 | 197 | 	    {								     \ | 
 | 198 | 	      if (_FP_FRAC_NEGP_##wc(R))				     \ | 
 | 199 | 		{							     \ | 
 | 200 | 		  _FP_FRAC_SUB_##wc(R, Y, X);				     \ | 
 | 201 | 		  R##_s = Y##_s;					     \ | 
 | 202 | 		}							     \ | 
 | 203 | 									     \ | 
 | 204 | 	      /* renormalize after subtraction */			     \ | 
 | 205 | 	      _FP_FRAC_CLZ_##wc(diff, R);				     \ | 
 | 206 | 	      diff -= _FP_WFRACXBITS_##fs;				     \ | 
 | 207 | 	      if (diff)							     \ | 
 | 208 | 		{							     \ | 
 | 209 | 		  R##_e -= diff;					     \ | 
 | 210 | 		  _FP_FRAC_SLL_##wc(R, diff);				     \ | 
 | 211 | 		}							     \ | 
 | 212 | 	    }								     \ | 
 | 213 | 	}								     \ | 
 | 214 |       break;								     \ | 
 | 215 |     }									     \ | 
 | 216 | 									     \ | 
 | 217 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NAN):				     \ | 
 | 218 |     _FP_CHOOSENAN(fs, wc, R, X, Y);					     \ | 
 | 219 |     break;								     \ | 
 | 220 | 									     \ | 
 | 221 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):			     \ | 
 | 222 |     R##_e = X##_e;							     \ | 
 | 223 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL):			     \ | 
 | 224 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF):				     \ | 
 | 225 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO):				     \ | 
 | 226 |     _FP_FRAC_COPY_##wc(R, X);						     \ | 
 | 227 |     R##_s = X##_s;							     \ | 
 | 228 |     R##_c = X##_c;							     \ | 
 | 229 |     break;								     \ | 
 | 230 | 									     \ | 
 | 231 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL):			     \ | 
 | 232 |     R##_e = Y##_e;							     \ | 
 | 233 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN):			     \ | 
 | 234 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN):				     \ | 
 | 235 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN):				     \ | 
 | 236 |     _FP_FRAC_COPY_##wc(R, Y);						     \ | 
 | 237 |     R##_s = Y##_s;							     \ | 
 | 238 |     R##_c = Y##_c;							     \ | 
 | 239 |     break;								     \ | 
 | 240 | 									     \ | 
 | 241 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF):				     \ | 
 | 242 |     if (X##_s != Y##_s)							     \ | 
 | 243 |       {									     \ | 
 | 244 | 	/* +INF + -INF => NAN */					     \ | 
 | 245 | 	_FP_FRAC_SET_##wc(R, _FP_NANFRAC_##fs);				     \ | 
 | 246 | 	R##_s = X##_s ^ Y##_s;						     \ | 
 | 247 | 	R##_c = FP_CLS_NAN;						     \ | 
 | 248 | 	break;								     \ | 
 | 249 |       }									     \ | 
 | 250 |     /* FALLTHRU */							     \ | 
 | 251 | 									     \ | 
 | 252 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL):			     \ | 
 | 253 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO):				     \ | 
 | 254 |     R##_s = X##_s;							     \ | 
 | 255 |     R##_c = FP_CLS_INF;							     \ | 
 | 256 |     break;								     \ | 
 | 257 | 									     \ | 
 | 258 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF):			     \ | 
 | 259 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_INF):				     \ | 
 | 260 |     R##_s = Y##_s;							     \ | 
 | 261 |     R##_c = FP_CLS_INF;							     \ | 
 | 262 |     break;								     \ | 
 | 263 | 									     \ | 
 | 264 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_ZERO):			     \ | 
 | 265 |     /* make sure the sign is correct */					     \ | 
 | 266 |     if (FP_ROUNDMODE == FP_RND_MINF)					     \ | 
 | 267 |       R##_s = X##_s | Y##_s;						     \ | 
 | 268 |     else								     \ | 
 | 269 |       R##_s = X##_s & Y##_s;						     \ | 
 | 270 |     R##_c = FP_CLS_ZERO;						     \ | 
 | 271 |     break;								     \ | 
 | 272 | 									     \ | 
 | 273 |   default:								     \ | 
 | 274 |     abort();								     \ | 
 | 275 |   }									     \ | 
 | 276 | } while (0) | 
 | 277 |  | 
 | 278 |  | 
 | 279 | /* | 
 | 280 |  * Main negation routine.  FIXME -- when we care about setting exception | 
 | 281 |  * bits reliably, this will not do.  We should examine all of the fp classes. | 
 | 282 |  */ | 
 | 283 |  | 
 | 284 | #define _FP_NEG(fs, wc, R, X)		\ | 
 | 285 |   do {					\ | 
 | 286 |     _FP_FRAC_COPY_##wc(R, X);		\ | 
 | 287 |     R##_c = X##_c;			\ | 
 | 288 |     R##_e = X##_e;			\ | 
 | 289 |     R##_s = 1 ^ X##_s;			\ | 
 | 290 |   } while (0) | 
 | 291 |  | 
 | 292 |  | 
 | 293 | /* | 
 | 294 |  * Main multiplication routine.  The input values should be cooked. | 
 | 295 |  */ | 
 | 296 |  | 
 | 297 | #define _FP_MUL(fs, wc, R, X, Y)			\ | 
 | 298 | do {							\ | 
 | 299 |   R##_s = X##_s ^ Y##_s;				\ | 
 | 300 |   switch (_FP_CLS_COMBINE(X##_c, Y##_c))		\ | 
 | 301 |   {							\ | 
 | 302 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NORMAL):	\ | 
 | 303 |     R##_c = FP_CLS_NORMAL;				\ | 
 | 304 |     R##_e = X##_e + Y##_e + 1;				\ | 
 | 305 | 							\ | 
 | 306 |     _FP_MUL_MEAT_##fs(R,X,Y);				\ | 
 | 307 | 							\ | 
 | 308 |     if (_FP_FRAC_OVERP_##wc(fs, R))			\ | 
 | 309 |       _FP_FRAC_SRS_##wc(R, 1, _FP_WFRACBITS_##fs);	\ | 
 | 310 |     else						\ | 
 | 311 |       R##_e--;						\ | 
 | 312 |     break;						\ | 
 | 313 | 							\ | 
 | 314 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NAN):		\ | 
 | 315 |     _FP_CHOOSENAN(fs, wc, R, X, Y);			\ | 
 | 316 |     break;						\ | 
 | 317 | 							\ | 
 | 318 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL):	\ | 
 | 319 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF):		\ | 
 | 320 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO):		\ | 
 | 321 |     R##_s = X##_s;					\ | 
 | 322 | 							\ | 
 | 323 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF):		\ | 
 | 324 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL):	\ | 
 | 325 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL):	\ | 
 | 326 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_ZERO):	\ | 
 | 327 |     _FP_FRAC_COPY_##wc(R, X);				\ | 
 | 328 |     R##_c = X##_c;					\ | 
 | 329 |     break;						\ | 
 | 330 | 							\ | 
 | 331 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN):	\ | 
 | 332 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN):		\ | 
 | 333 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN):		\ | 
 | 334 |     R##_s = Y##_s;					\ | 
 | 335 | 							\ | 
 | 336 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF):	\ | 
 | 337 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):	\ | 
 | 338 |     _FP_FRAC_COPY_##wc(R, Y);				\ | 
 | 339 |     R##_c = Y##_c;					\ | 
 | 340 |     break;						\ | 
 | 341 | 							\ | 
 | 342 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO):		\ | 
 | 343 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_INF):		\ | 
 | 344 |     R##_c = FP_CLS_NAN;					\ | 
 | 345 |     _FP_FRAC_SET_##wc(R, _FP_NANFRAC_##fs);		\ | 
 | 346 |     break;						\ | 
 | 347 | 							\ | 
 | 348 |   default:						\ | 
 | 349 |     abort();						\ | 
 | 350 |   }							\ | 
 | 351 | } while (0) | 
 | 352 |  | 
 | 353 |  | 
 | 354 | /* | 
 | 355 |  * Main division routine.  The input values should be cooked. | 
 | 356 |  */ | 
 | 357 |  | 
 | 358 | #define _FP_DIV(fs, wc, R, X, Y)			\ | 
 | 359 | do {							\ | 
 | 360 |   R##_s = X##_s ^ Y##_s;				\ | 
 | 361 |   switch (_FP_CLS_COMBINE(X##_c, Y##_c))		\ | 
 | 362 |   {							\ | 
 | 363 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NORMAL):	\ | 
 | 364 |     R##_c = FP_CLS_NORMAL;				\ | 
 | 365 |     R##_e = X##_e - Y##_e;				\ | 
 | 366 | 							\ | 
 | 367 |     _FP_DIV_MEAT_##fs(R,X,Y);				\ | 
 | 368 |     break;						\ | 
 | 369 | 							\ | 
 | 370 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NAN):		\ | 
 | 371 |     _FP_CHOOSENAN(fs, wc, R, X, Y);			\ | 
 | 372 |     break;						\ | 
 | 373 | 							\ | 
 | 374 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL):	\ | 
 | 375 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF):		\ | 
 | 376 |   case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO):		\ | 
 | 377 |     R##_s = X##_s;					\ | 
 | 378 |     _FP_FRAC_COPY_##wc(R, X);				\ | 
 | 379 |     R##_c = X##_c;					\ | 
 | 380 |     break;						\ | 
 | 381 | 							\ | 
 | 382 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN):	\ | 
 | 383 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN):		\ | 
 | 384 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN):		\ | 
 | 385 |     R##_s = Y##_s;					\ | 
 | 386 |     _FP_FRAC_COPY_##wc(R, Y);				\ | 
 | 387 |     R##_c = Y##_c;					\ | 
 | 388 |     break;						\ | 
 | 389 | 							\ | 
 | 390 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF):	\ | 
 | 391 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_INF):		\ | 
 | 392 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL):	\ | 
 | 393 |     R##_c = FP_CLS_ZERO;				\ | 
 | 394 |     break;						\ | 
 | 395 | 							\ | 
 | 396 |   case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO):	\ | 
 | 397 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO):		\ | 
 | 398 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL):	\ | 
 | 399 |     R##_c = FP_CLS_INF;					\ | 
 | 400 |     break;						\ | 
 | 401 | 							\ | 
 | 402 |   case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF):		\ | 
 | 403 |   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_ZERO):	\ | 
 | 404 |     R##_c = FP_CLS_NAN;					\ | 
 | 405 |     _FP_FRAC_SET_##wc(R, _FP_NANFRAC_##fs);		\ | 
 | 406 |     break;						\ | 
 | 407 | 							\ | 
 | 408 |   default:						\ | 
 | 409 |     abort();						\ | 
 | 410 |   }							\ | 
 | 411 | } while (0) | 
 | 412 |  | 
 | 413 |  | 
 | 414 | /* | 
 | 415 |  * Main differential comparison routine.  The inputs should be raw not | 
 | 416 |  * cooked.  The return is -1,0,1 for normal values, 2 otherwise. | 
 | 417 |  */ | 
 | 418 |  | 
 | 419 | #define _FP_CMP(fs, wc, ret, X, Y, un)					\ | 
 | 420 |   do {									\ | 
 | 421 |     /* NANs are unordered */						\ | 
 | 422 |     if ((X##_e == _FP_EXPMAX_##fs && !_FP_FRAC_ZEROP_##wc(X))		\ | 
 | 423 | 	|| (Y##_e == _FP_EXPMAX_##fs && !_FP_FRAC_ZEROP_##wc(Y)))	\ | 
 | 424 |       {									\ | 
 | 425 | 	ret = un;							\ | 
 | 426 |       }									\ | 
 | 427 |     else								\ | 
 | 428 |       {									\ | 
 | 429 |         int __x_zero = (!X##_e && _FP_FRAC_ZEROP_##wc(X)) ? 1 : 0;	\ | 
 | 430 |         int __y_zero = (!Y##_e && _FP_FRAC_ZEROP_##wc(Y)) ? 1 : 0;	\ | 
 | 431 | 									\ | 
 | 432 | 	if (__x_zero && __y_zero)					\ | 
 | 433 | 	  ret = 0;							\ | 
 | 434 | 	else if (__x_zero)						\ | 
 | 435 | 	  ret = Y##_s ? 1 : -1;						\ | 
 | 436 | 	else if (__y_zero)						\ | 
 | 437 | 	  ret = X##_s ? -1 : 1;						\ | 
 | 438 | 	else if (X##_s != Y##_s)					\ | 
 | 439 | 	  ret = X##_s ? -1 : 1;						\ | 
 | 440 | 	else if (X##_e > Y##_e)						\ | 
 | 441 | 	  ret = X##_s ? -1 : 1;						\ | 
 | 442 | 	else if (X##_e < Y##_e)						\ | 
 | 443 | 	  ret = X##_s ? 1 : -1;						\ | 
 | 444 | 	else if (_FP_FRAC_GT_##wc(X, Y))				\ | 
 | 445 | 	  ret = X##_s ? -1 : 1;						\ | 
 | 446 | 	else if (_FP_FRAC_GT_##wc(Y, X))				\ | 
 | 447 | 	  ret = X##_s ? 1 : -1;						\ | 
 | 448 | 	else								\ | 
 | 449 | 	  ret = 0;							\ | 
 | 450 |       }									\ | 
 | 451 |   } while (0) | 
 | 452 |  | 
 | 453 |  | 
 | 454 | /* Simplification for strict equality.  */ | 
 | 455 |  | 
 | 456 | #define _FP_CMP_EQ(fs, wc, ret, X, Y)					  \ | 
 | 457 |   do {									  \ | 
 | 458 |     /* NANs are unordered */						  \ | 
 | 459 |     if ((X##_e == _FP_EXPMAX_##fs && !_FP_FRAC_ZEROP_##wc(X))		  \ | 
 | 460 | 	|| (Y##_e == _FP_EXPMAX_##fs && !_FP_FRAC_ZEROP_##wc(Y)))	  \ | 
 | 461 |       {									  \ | 
 | 462 | 	ret = 1;							  \ | 
 | 463 |       }									  \ | 
 | 464 |     else								  \ | 
 | 465 |       {									  \ | 
 | 466 | 	ret = !(X##_e == Y##_e						  \ | 
 | 467 | 		&& _FP_FRAC_EQ_##wc(X, Y)				  \ | 
 | 468 | 		&& (X##_s == Y##_s || !X##_e && _FP_FRAC_ZEROP_##wc(X))); \ | 
 | 469 |       }									  \ | 
 | 470 |   } while (0) | 
 | 471 |  | 
 | 472 | /* | 
 | 473 |  * Main square root routine.  The input value should be cooked. | 
 | 474 |  */ | 
 | 475 |  | 
 | 476 | #define _FP_SQRT(fs, wc, R, X)						\ | 
 | 477 | do {									\ | 
 | 478 |     _FP_FRAC_DECL_##wc(T); _FP_FRAC_DECL_##wc(S);			\ | 
 | 479 |     _FP_W_TYPE q;							\ | 
 | 480 |     switch (X##_c)							\ | 
 | 481 |     {									\ | 
 | 482 |     case FP_CLS_NAN:							\ | 
 | 483 |     	R##_s = 0;							\ | 
 | 484 |     	R##_c = FP_CLS_NAN;						\ | 
 | 485 |     	_FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);			\ | 
 | 486 |     	break;								\ | 
 | 487 |     case FP_CLS_INF:							\ | 
 | 488 |     	if (X##_s)							\ | 
 | 489 |     	  {								\ | 
 | 490 |     	    R##_s = 0;							\ | 
 | 491 | 	    R##_c = FP_CLS_NAN; /* sNAN */				\ | 
 | 492 |     	  }								\ | 
 | 493 |     	else								\ | 
 | 494 |     	  {								\ | 
 | 495 |     	    R##_s = 0;							\ | 
 | 496 |     	    R##_c = FP_CLS_INF; /* sqrt(+inf) = +inf */			\ | 
 | 497 |     	  }								\ | 
 | 498 |     	break;								\ | 
 | 499 |     case FP_CLS_ZERO:							\ | 
 | 500 | 	R##_s = X##_s;							\ | 
 | 501 |     	R##_c = FP_CLS_ZERO; /* sqrt(+-0) = +-0 */			\ | 
 | 502 | 	break;								\ | 
 | 503 |     case FP_CLS_NORMAL:							\ | 
 | 504 |     	R##_s = 0;							\ | 
 | 505 |         if (X##_s)							\ | 
 | 506 |           {								\ | 
 | 507 | 	    R##_c = FP_CLS_NAN; /* sNAN */				\ | 
 | 508 | 	    break;							\ | 
 | 509 |           }								\ | 
 | 510 |     	R##_c = FP_CLS_NORMAL;						\ | 
 | 511 |         if (X##_e & 1)							\ | 
 | 512 |           _FP_FRAC_SLL_##wc(X, 1);					\ | 
 | 513 |         R##_e = X##_e >> 1;						\ | 
 | 514 |         _FP_FRAC_SET_##wc(S, _FP_ZEROFRAC_##wc);			\ | 
 | 515 |         _FP_FRAC_SET_##wc(R, _FP_ZEROFRAC_##wc);			\ | 
 | 516 |         q = _FP_OVERFLOW_##fs;						\ | 
 | 517 |         _FP_FRAC_SLL_##wc(X, 1);					\ | 
 | 518 |         _FP_SQRT_MEAT_##wc(R, S, T, X, q);				\ | 
 | 519 |         _FP_FRAC_SRL_##wc(R, 1);					\ | 
 | 520 |     }									\ | 
 | 521 |   } while (0) | 
 | 522 |  | 
 | 523 | /* | 
 | 524 |  * Convert from FP to integer | 
 | 525 |  */ | 
 | 526 |  | 
 | 527 | /* "When a NaN, infinity, large positive argument >= 2147483648.0, or | 
 | 528 |  * large negative argument <= -2147483649.0 is converted to an integer, | 
 | 529 |  * the invalid_current bit...should be set and fp_exception_IEEE_754 should | 
 | 530 |  * be raised. If the floating point invalid trap is disabled, no trap occurs | 
 | 531 |  * and a numerical result is generated: if the sign bit of the operand | 
 | 532 |  * is 0, the result is 2147483647; if the sign bit of the operand is 1, | 
 | 533 |  * the result is -2147483648." | 
 | 534 |  * Similarly for conversion to extended ints, except that the boundaries | 
 | 535 |  * are >= 2^63, <= -(2^63 + 1), and the results are 2^63 + 1 for s=0 and | 
 | 536 |  * -2^63 for s=1. | 
 | 537 |  * -- SPARC Architecture Manual V9, Appendix B, which specifies how | 
 | 538 |  * SPARCs resolve implementation dependencies in the IEEE-754 spec. | 
 | 539 |  * I don't believe that the code below follows this. I'm not even sure | 
 | 540 |  * it's right! | 
 | 541 |  * It doesn't cope with needing to convert to an n bit integer when there | 
 | 542 |  * is no n bit integer type. Fortunately gcc provides long long so this | 
 | 543 |  * isn't a problem for sparc32. | 
 | 544 |  * I have, however, fixed its NaN handling to conform as above. | 
 | 545 |  *         -- PMM 02/1998 | 
 | 546 |  * NB: rsigned is not 'is r declared signed?' but 'should the value stored | 
 | 547 |  * in r be signed or unsigned?'. r is always(?) declared unsigned. | 
 | 548 |  * Comments below are mine, BTW -- PMM | 
 | 549 |  */ | 
 | 550 | #define _FP_TO_INT(fs, wc, r, X, rsize, rsigned)			\ | 
 | 551 |   do {									\ | 
 | 552 |     switch (X##_c)							\ | 
 | 553 |       {									\ | 
 | 554 |       case FP_CLS_NORMAL:						\ | 
 | 555 | 	if (X##_e < 0)							\ | 
 | 556 | 	  {								\ | 
 | 557 | 	  /* case FP_CLS_NAN: see above! */				\ | 
 | 558 | 	  case FP_CLS_ZERO:						\ | 
 | 559 | 	    r = 0;							\ | 
 | 560 | 	  }								\ | 
 | 561 | 	else if (X##_e >= rsize - (rsigned != 0))			\ | 
 | 562 | 	  {	/* overflow */						\ | 
 | 563 | 	  case FP_CLS_NAN:                                              \ | 
 | 564 |           case FP_CLS_INF:						\ | 
 | 565 | 	    if (rsigned)						\ | 
 | 566 | 	      {								\ | 
 | 567 | 		r = 1;							\ | 
 | 568 | 		r <<= rsize - 1;					\ | 
 | 569 | 		r -= 1 - X##_s;						\ | 
 | 570 | 	      }								\ | 
 | 571 | 	    else							\ | 
 | 572 | 	      {								\ | 
 | 573 | 		r = 0;							\ | 
 | 574 | 		if (!X##_s)						\ | 
 | 575 | 		  r = ~r;						\ | 
 | 576 | 	      }								\ | 
 | 577 | 	  }								\ | 
 | 578 | 	else								\ | 
 | 579 | 	  {								\ | 
 | 580 | 	    if (_FP_W_TYPE_SIZE*wc < rsize)				\ | 
 | 581 | 	      {								\ | 
 | 582 | 		_FP_FRAC_ASSEMBLE_##wc(r, X, rsize);			\ | 
 | 583 | 		r <<= X##_e - _FP_WFRACBITS_##fs;			\ | 
 | 584 | 	      }								\ | 
 | 585 | 	    else							\ | 
 | 586 | 	      {								\ | 
 | 587 | 		if (X##_e >= _FP_WFRACBITS_##fs)			\ | 
 | 588 | 		  _FP_FRAC_SLL_##wc(X, (X##_e - _FP_WFRACBITS_##fs + 1));\ | 
 | 589 | 		else							\ | 
 | 590 | 		  _FP_FRAC_SRL_##wc(X, (_FP_WFRACBITS_##fs - X##_e - 1));\ | 
 | 591 | 		_FP_FRAC_ASSEMBLE_##wc(r, X, rsize);			\ | 
 | 592 | 	      }								\ | 
 | 593 | 	    if (rsigned && X##_s)					\ | 
 | 594 | 	      r = -r;							\ | 
 | 595 | 	  }								\ | 
 | 596 | 	break;								\ | 
 | 597 |       }									\ | 
 | 598 |   } while (0) | 
 | 599 |  | 
 | 600 | #define _FP_FROM_INT(fs, wc, X, r, rsize, rtype)			\ | 
 | 601 |   do {									\ | 
 | 602 |     if (r)								\ | 
 | 603 |       {									\ | 
 | 604 | 	X##_c = FP_CLS_NORMAL;						\ | 
 | 605 | 									\ | 
 | 606 | 	if ((X##_s = (r < 0)))						\ | 
 | 607 | 	  r = -r;							\ | 
 | 608 | 	/* Note that `r' is now considered unsigned, so we don't have	\ | 
 | 609 | 	   to worry about the single signed overflow case.  */		\ | 
 | 610 | 									\ | 
 | 611 | 	if (rsize <= _FP_W_TYPE_SIZE)					\ | 
 | 612 | 	  __FP_CLZ(X##_e, r);						\ | 
 | 613 | 	else								\ | 
 | 614 | 	  __FP_CLZ_2(X##_e, (_FP_W_TYPE)(r >> _FP_W_TYPE_SIZE), 	\ | 
 | 615 | 		     (_FP_W_TYPE)r);					\ | 
 | 616 | 	if (rsize < _FP_W_TYPE_SIZE)					\ | 
 | 617 | 		X##_e -= (_FP_W_TYPE_SIZE - rsize);			\ | 
 | 618 | 	X##_e = rsize - X##_e - 1;					\ | 
 | 619 | 									\ | 
 | 620 | 	if (_FP_FRACBITS_##fs < rsize && _FP_WFRACBITS_##fs < X##_e)	\ | 
 | 621 | 	  __FP_FRAC_SRS_1(r, (X##_e - _FP_WFRACBITS_##fs), rsize);	\ | 
 | 622 | 	r &= ~((_FP_W_TYPE)1 << X##_e);					\ | 
 | 623 | 	_FP_FRAC_DISASSEMBLE_##wc(X, ((unsigned rtype)r), rsize);	\ | 
 | 624 | 	_FP_FRAC_SLL_##wc(X, (_FP_WFRACBITS_##fs - X##_e - 1));		\ | 
 | 625 |       }									\ | 
 | 626 |     else								\ | 
 | 627 |       {									\ | 
 | 628 | 	X##_c = FP_CLS_ZERO, X##_s = 0;					\ | 
 | 629 |       }									\ | 
 | 630 |   } while (0) | 
 | 631 |  | 
 | 632 |  | 
 | 633 | #define FP_CONV(dfs,sfs,dwc,swc,D,S)			\ | 
 | 634 |   do {							\ | 
 | 635 |     _FP_FRAC_CONV_##dwc##_##swc(dfs, sfs, D, S);	\ | 
 | 636 |     D##_e = S##_e;					\ | 
 | 637 |     D##_c = S##_c;					\ | 
 | 638 |     D##_s = S##_s;					\ | 
 | 639 |   } while (0) | 
 | 640 |  | 
 | 641 | /* | 
 | 642 |  * Helper primitives. | 
 | 643 |  */ | 
 | 644 |  | 
 | 645 | /* Count leading zeros in a word.  */ | 
 | 646 |  | 
 | 647 | #ifndef __FP_CLZ | 
 | 648 | #if _FP_W_TYPE_SIZE < 64 | 
 | 649 | /* this is just to shut the compiler up about shifts > word length -- PMM 02/1998 */ | 
 | 650 | #define __FP_CLZ(r, x)				\ | 
 | 651 |   do {						\ | 
 | 652 |     _FP_W_TYPE _t = (x);			\ | 
 | 653 |     r = _FP_W_TYPE_SIZE - 1;			\ | 
 | 654 |     if (_t > 0xffff) r -= 16;			\ | 
 | 655 |     if (_t > 0xffff) _t >>= 16;			\ | 
 | 656 |     if (_t > 0xff) r -= 8;			\ | 
 | 657 |     if (_t > 0xff) _t >>= 8;			\ | 
 | 658 |     if (_t & 0xf0) r -= 4;			\ | 
 | 659 |     if (_t & 0xf0) _t >>= 4;			\ | 
 | 660 |     if (_t & 0xc) r -= 2;			\ | 
 | 661 |     if (_t & 0xc) _t >>= 2;			\ | 
 | 662 |     if (_t & 0x2) r -= 1;			\ | 
 | 663 |   } while (0) | 
 | 664 | #else /* not _FP_W_TYPE_SIZE < 64 */ | 
 | 665 | #define __FP_CLZ(r, x)				\ | 
 | 666 |   do {						\ | 
 | 667 |     _FP_W_TYPE _t = (x);			\ | 
 | 668 |     r = _FP_W_TYPE_SIZE - 1;			\ | 
 | 669 |     if (_t > 0xffffffff) r -= 32;		\ | 
 | 670 |     if (_t > 0xffffffff) _t >>= 32;		\ | 
 | 671 |     if (_t > 0xffff) r -= 16;			\ | 
 | 672 |     if (_t > 0xffff) _t >>= 16;			\ | 
 | 673 |     if (_t > 0xff) r -= 8;			\ | 
 | 674 |     if (_t > 0xff) _t >>= 8;			\ | 
 | 675 |     if (_t & 0xf0) r -= 4;			\ | 
 | 676 |     if (_t & 0xf0) _t >>= 4;			\ | 
 | 677 |     if (_t & 0xc) r -= 2;			\ | 
 | 678 |     if (_t & 0xc) _t >>= 2;			\ | 
 | 679 |     if (_t & 0x2) r -= 1;			\ | 
 | 680 |   } while (0) | 
 | 681 | #endif /* not _FP_W_TYPE_SIZE < 64 */ | 
 | 682 | #endif /* ndef __FP_CLZ */ | 
 | 683 |  | 
 | 684 | #define _FP_DIV_HELP_imm(q, r, n, d)		\ | 
 | 685 |   do {						\ | 
 | 686 |     q = n / d, r = n % d;			\ | 
 | 687 |   } while (0) | 
 | 688 |  |