SWDIV_NOCHK(X,Y)

Purpose

Provides software floating-point division algorithms when targeting and running on POWER5 processors. Checking for invalid arguments is not performed.

This function returns the result of a floating-point division and can increase performance over the normal divide operator or the SWDIV built-in function where your application performs division repeatedly within a loop, and arguments are within the permitted range.

Class

Elemental function

Argument type and attributes

X
can be of type REAL(4) or REAL(8).

For a REAL(4) argument, you must not specify the following:

  • |numerator| equal to infinity
  • |denominator| equal to infinity
  • |denominator|< 2**(-1022)
  • |numerator/denominator| equal to infinity

For correct operation, REAL(8) arguments must satisfy the following conditions:

  • 2**(-970) < |numerator| < Inf
  • 2**(-1022) <= |denominator| < 2**1021
  • 2**(-1021) < |numerator/denominator| < 2**1023
Y
must be of the same type and kind type parameter as X.

Result type and attributes

Same as X and Y.

Result value

The result has a value equal to X/Y.

For REAL(4) arguments, the the result is bitwise identical to IEEE division.

For REAL(8) arguments with -qstrict in effect, the result is bitwise identical to IEEE division.

For REAL(8) arguments with -qnostrict in effect, the result can differ slightly from the IEEE result.