NAME
    intBitsToFloat - returns the float value corresponding to a given bit
    represention.of a scalar int value or vector of int values

SYNPOSIS
      float  intBitsToFloat(int  x);
      float1 intBitsToFloat(int1 x);
      float2 intBitsToFloat(int2 x);
      float3 intBitsToFloat(int3 x);
      float4 intBitsToFloat(int4 x);
 
PARAMETERS
    x       Integer vector or scalar to raw cast to a scalar float or vector
            of floats

DESCRIPTION
    Returns the IEEE 754 float scalar value or vector values corresponding
    to a given 32-bit integer bit represention for a scalar int value or
    vector of int values.

    This function is based on Java's jave.lang.Float method of the same
    name. See:

      http://java.sun.com/j2se/1.4.2/docs/api/java/lang/Float.html

    The Cg compiler can typically optimize intBitsToFloat so it has no
    instruction cost.

REFERENCE IMPLEMENTATION
    intBitsToFloat operates consistent with the following ANSI C code:

      float floatToRawIntBits(int x)
      {
        union {
          float f;  // assuming 32-bit IEEE 754 single-precision
          int i;    // assuming 32-bit 2's complement int
        } u;

        u.i = x;
        return u.f;
      }

PROFILE SUPPORT
    intBitsToFloat is supported by the the gp4vp manpage, the gp4gp manpage,
    and the gp4vp manpage profiles.

    intBitsToFloat is *not* supported by pre-G80 profiles.

SEE ALSO
    the ceil manpage, *floatToIntBits*, the floatToRawIntBits manpage, the
    floor manpage, the round manpage, the trunc manpage

