ColdFire soft-float optimizations

[Mike Stump]

On Thursday, June 3, 2004, at 09:42 AM, Peter Barada wrote:
> I'm thinking about a set of optimizations for single precision
> floating point(SPFP) on ColdFire cores that don't have an FPU.  These
> optimizations make the assumption that the domain of the FP numbers do
> not include NaN in any of its forms,

-ffinite-math-only as documented in the manual?

>  and don't have to set errno.

-fno-math-errno as documented in the manual?

> I'm wondering what combination of -ffast-math

This flag turns the above two on, as documented in the manual?

> and -funsafe-math-optimizations should to be turned on to enable these
> optimizations.

I am not sure that you need this flag, as I am unsure what 
optimizations you want to do exactly.  Maybe someone else can guess, 
failing that, you'll have to describe each one and then we can chime 
in.  For the optimizations you listed, it didn't sound like you needed 
to check this flag, but I am not an FP person.