William Kenworthy <[EMAIL PROTECTED]> writes:

> you might also look at -falign-functions=8/16/32 as well.  On an athlon
> tbird 1.4, 4 had zero gain, 8 and 16 were slower than 4, but 32 was
> consistantly a little better.  Possibly because its a 32 bit system

Uhm... no, that has nothing to do with it. -falign-functions=32 will
align on a 32 *byte*�boundary. It's the athlon's L1 cache which works
best if you have the data aligned to a 64 byte border.

Gru� Uli
-- 
"Or have we eaten on the insane root,
 that takes the reason prisoner?"  -- MacBeth I, 3


--
[EMAIL PROTECTED] mailing list

Reply via email to