parisc/math-emu/fmpyfadd.c

15  *	Double Floating-point Multiply Fused Add
16  *	Double Floating-point Multiply Negate Fused Add
17  *	Single Floating-point Multiply Fused Add
18  *	Single Floating-point Multiply Negate Fused Add
41  *  Double Floating-point Multiply Fused Add
68 	 * set sign bit of result of multiply  in dbl_fmpyfadd()
75 	 * Generate multiply exponent   in dbl_fmpyfadd()
100 				 *  sign opposite of the multiply result  in dbl_fmpyfadd()
178 					 * invalid since multiply operands are  in dbl_fmpyfadd()
191 				 *  sign opposite of the multiply result  in dbl_fmpyfadd()
277 	 * Generate multiply mantissa  in dbl_fmpyfadd()
364 	/* Multiply the first two source mantissas together */  in dbl_fmpyfadd()
375 	 * simple shift and add multiply algorithm is used.   in dbl_fmpyfadd()
411 	 * No rounding is required, since the result of the multiply  in dbl_fmpyfadd()
419 	 * multiply result might not fit into the exponent field.  We  in dbl_fmpyfadd()
512 		 * multiply overflowed.  A borrow can occur out of the hidden  in dbl_fmpyfadd()
703  *  Double Floating-point Multiply Negate Fused Add
727 	 * set sign bit of result of multiply
735 	 * Generate multiply exponent
760 				 *  sign opposite of the multiply result
838 					 * invalid since multiply operands are
851 				 *  sign opposite of the multiply result
937 	 * Generate multiply mantissa
1024 	/* Multiply the first two source mantissas together */
1035 	 * simple shift and add multiply algorithm is used.
1071 	 * No rounding is required, since the result of the multiply
1079 	 * multiply result might not fit into the exponent field.  We
1172 		 * multiply overflowed.  A borrow can occur out of the hidden
1361  *  Single Floating-point Multiply Fused Add
1385 	 * set sign bit of result of multiply
1392 	 * Generate multiply exponent
1416 				 *  sign opposite of the multiply result
1494 					 * invalid since multiply operands are
1507 				 *  sign opposite of the multiply result
1593 	 * Generate multiply mantissa
1680 	/* Multiply the first two source mantissas together */
1691 	 * simple shift and add multiply algorithm is used.
1725 	 * No rounding is required, since the result of the multiply
1733 	 * multiply result might not fit into the exponent field.  We
1823 		 * multiply overflowed.  A borrow can occur out of the hidden
2002  *  Single Floating-point Multiply Negate Fused Add
2026 	 * set sign bit of result of multiply
2034 	 * Generate multiply exponent
2058 				 *  sign opposite of the multiply result
2136 					 * invalid since multiply operands are
2149 				 *  sign opposite of the multiply result
2235 	 * Generate multiply mantissa
2322 	/* Multiply the first two source mantissas together */
2333 	 * simple shift and add multiply algorithm is used.
2367 	 * No rounding is required, since the result of the multiply
2375 	 * multiply result might not fit into the exponent field.  We
2465 		 * multiply overflowed.  A borrow can occur out of the hidden