I was wondering if it's necessary to turn on FPU stuff for a realtime
kernel thread, if I do some basic floating point math but I don't care
about the state of floating point registers being saved across iterations
of a thread loop...?

It seems to me that even though I don't care about the persistence of
double or float variables across thread invocations, if the FPU isn't
configured correctly strange unwanted CPU exceptions can occur.  Is this
so?


:)

-Calin

-- [rtl] ---
To unsubscribe:
echo "unsubscribe rtl" | mail [EMAIL PROTECTED] OR
echo "unsubscribe rtl <Your_email>" | mail [EMAIL PROTECTED]
--
For more information on Real-Time Linux see:
http://www.rtlinux.org/

Reply via email to