For most programs, using options to improve floating-point (FP) precision adversely affects performance. In general, to achieve greater performance, it may be necessary to sacrifice some degree of floating-point accuracy.
If you are not sure whether your application needs the compiler supported options, try compiling and running your program both with and without the options to evaluate the effects on performance versus precision.
While there are several floating-point related options, the recommended method to control the semantics of floating-point calculations is to use the -fp-model (Linux*) or /fp (Windows*) option. See the following topic for detailed descriptions of the different models and examples:
-fp-model compiler option