vrd2_exp: Two-valued double precision exponential function

• C Prototype:
  • __m128d __vrd2_exp(__m128d x);
  • Inputs:
    • __m128d x - the double precision input value pair.
  • Outputs:
    • e raised to the power x (exponential of x).
    • __m128d y - the double precision exponent result pair, returned in xmm0.
• Notes:
  • __vrd2_exp computes the exponential function of two input arguments.
    
    This routine accepts a pair of double precision input values passed as a __m128d value. The result is the double precision exponent of both values, returned as a __m128d value. This is a relaxed version of exp, suitable for use with fastmath compiler flags or applications not requiring full error handling. Denormal inputs may produce unpredictable results. Special case inputs produce C99 return values. The routine is accurate to better than 1 ulp over the valid input range.
• Special case return values:

  • Input	Output
    QNaN	same QNaN
    SNaN	same NaN converted to QNaN
    < -708.5	0
    > 709.8	+infinity

• Performance:
  • 80 cycles for most valid inputs (40 cycles per value).