Christian Budde wrote:
> I'm not into FPC, but this looks like if the compiler doesn't put the
> variable(/branch address) on an address which is dividable by 16. On
> some Intel processors, that makes a huge difference, especially in case
> of branches.
So you are saying 'var i:double' has to be on an address dividable by 16 for
some Intel processors.
I found this:
Pentium-MMX 0% slowdown
PentiumII 222% slowdown
Pentium4 333% slowdown
Can somebody post an asm that more easily shows this problem?
Thanks!
--
Al
_________________________________________________________________
To unsubscribe: mail [EMAIL PROTECTED] with
"unsubscribe" as the Subject
archives at http://www.lazarus.freepascal.org/mailarchives
