vrs4_powxf: Four-valued single precision power function with constant y

• C Prototype:
  • __m128 __vrs4_powxf(__m128 x,float y);
  • Inputs:
    • __m128 x - the single precision input base values.
      float y - the common single precision input exponent value.
  • Outputs:
    • __m128 z - the single precision results of each x raised to the y power, returned in xmm0.
• Notes:
  • __vrs4_powxf() computes the single precision x raised to the y power for four input x arguments and a constant y input value. This routine accepts four single precision input values passed as an __m128 value. The y value is passed as one single precision value. The result is the x raised to the y power for all four input values, returned as a __m128 value.
    This is a relaxed version of powxf, 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 0.5 ulp over the valid input range.
• Special case return values:

  • Input x	Input y	Output
    +/- 0	y<0, odd integer	+/- infinity
    +/- 0	y<0, not odd integer	+infinity
    +/- 0	y>0, odd integer	+/- 0
    +/- 0	y>0, not odd integer	+0
    -1	+infinity	1
    +1	y (incl. NaN)	1
    x (incl. Nan)	+/- 0	1
    x<0	y, not integer	QNaN
    |x|<1	-infinity	+infinity
    |x|>1	-infinity	+0
    |x|<1	+infinity	+0
    |x|>1	+infinity	+infinity
    -infinity	y<0, odd integer	-0
    -infinity	y<0, not odd integer	+0
    -infinity	y>0, odd integer	-infinity
    -infinity	y>0, not odd integer	+infinity
    +infinity	y<0,	+0
    +infinity	y>0,	+infinity
    NaN	y nonzero,	NaN
    x<>1	NaN,	NaN

• Performance:
  • 372 cycles for most valid inputs (93 cycles per value).