Intel Behavior and Implementation

C

The hardware is 80386, 80486, and Pentium^TM microprocessors from Intel and compatible microprocessors from other manufacturers. While great effort went into compatibility with the SPARC platform, several differences exist.

On Intel:

• real*16 is not implemented in FORTRAN.

• The floating-point registers are 80-bits wide. Because intermediate results of arithmetic computations can be in extended precision, computation results can differ. The -fstore flag minimizes these discrepancies. However, using the -fstore flag introduces a penalty in performance.

• Each time a single or double precision floating-point number is loaded or stored, a conversion to or from double extended precision occurs. Thus loads and stores of floating-point numbers can cause exceptions.

• Gradual underflow is implemented entirely in hardware. There is no nonstandard mode.

• The fpversion utility is not provided.