Next: Vectorization of loops, Previous: Inlining of Subprograms, Up: Performance Considerations [Contents][Index]

On almost all targets, GNAT maps Float and Long_Float to the 32-bit and 64-bit standard IEEE floating-point representations, and operations will use standard IEEE arithmetic as provided by the processor. On most, but not all, architectures, the attribute Machine_Overflows is False for these types, meaning that the semantics of overflow is implementation-defined. In the case of GNAT, these semantics correspond to the normal IEEE treatment of infinities and NaN (not a number) values. For example, 1.0 / 0.0 yields plus infinitiy and 0.0 / 0.0 yields a NaN. By avoiding explicit overflow checks, the performance is greatly improved on many targets. However, if required, floating-point overflow can be enabled by the use of the pragma Check_Float_Overflow.

Another consideration that applies specifically to x86 32-bit architectures is which form of floating-point arithmetic is used. By default the operations use the old style x86 floating-point, which implements an 80-bit extended precision form (on these architectures the type Long_Long_Float corresponds to that form). In addition, generation of efficient code in this mode means that the extended precision form will be used for intermediate results. This may be helpful in improving the final precision of a complex expression. However it means that the results obtained on the x86 will be different from those on other architectures, and for some algorithms, the extra intermediate precision can be detrimental.

In addition to this old-style floating-point, all modern x86 chips implement an alternative floating-point operation model referred to as SSE2. In this model there is no extended form, and furthermore execution performance is significantly enhanced. To force GNAT to use this more modern form, use both of the switches:

-msse2 -mfpmath=sse

A unit compiled with these switches will automatically use the more efficient SSE2 instruction set for Float and Long_Float operations. Note that the ABI has the same form for both floating-point models, so it is permissible to mix units compiled with and without these switches.