
    <para>
        These all operate component-wise. 
        The description is per-component.
      The generic type name <type>gentype</type> is used to indicate that the function can
      take <type>float</type>, <type>float2</type>, <type>float3</type>, <type>float4</type>,
      <type>float8</type>, <type>float16</type>, <type>double</type>, <type>double2</type>,
      <type>double3</type>, <type>double4</type>, <type>double8</type>, or <type>double16</type>
      as the type for the arguments.
    </para>

    <para>
      The generic type name <type>gentypef</type> is used to indicate that the function can
      take <type>float</type>, <type>float2</type>, <type>float3</type>, <type>float4</type>,
      <type>float8</type>, or <type>float16</type> as the type for the arguments.
    </para>

    <para>
      The generic type name <type>gentyped</type> is used to indicate that the function can take
      <type>double</type>, <type>double2</type>, <type>double3</type>, <type>double4</type>,
      <type>double8</type>, or <type>double16</type> as the type for the arguments.
    </para>

    <para>
      The built-in common functions are implemented using the round to nearest even rounding mode.
    </para>

<!-- don't mention the half option here because it doesn't apply to all the files that include
this file.  Instead, mention it in each individual .xml file where it applies. -->

<!-- 29-May-2013 -->