Light on PPC interrupt management requested

[jzamora at avellano.datsi.fi.upm.es (Juan Zamorano Flores)]

> 
> Benefits : if you sitch from one thread that use the FPU to another that
> do not, you do not need to save the FPU registers. If the threads takes
> that own the FPU register is shdeuled again, you will just reenable the FPU
> with no need of restoring the FPU registers...
> 
   Hello,

   I am sorry for the intrusion but I think we can't forget that RTEMS
means Real Time Ex...
   
   The above is not a benefit for a real time OS: Real time computing is not
fast computing but predictable computing (J. Stankovic Missconceptions
about Real-Time computing).

   In order to avoid context switching overload that approach will overload
the estimate computation time of the task which uses the FPU. I think that
approach raises the indeterminist of the OS services.

   I think that the true feature of a RT OS is that the OS services have
an upper bounded computation time. 

   So I think that the simple approach (to save FPU register in context
switch for a FP task) will produce better RT behaviour.

   Just my 2 cents (of euro)

   Juan