no. could we solve this problem now? 4 byte alignment on pentiums is EVIL
EVIL EVIL. its worse than either zero or 16. Its a total waste of space.
On ppro and p-ii, alignment is a different issue. A fixed alignment there is,
again, waste of space as improvements through alignment are seldom, and
dependent on the number of fill bytes required (egcs is able to selectively
add alignment).
For the ppro & p-ii, an alignment of either 0 (for compact code) or 16
is best.
> Why aren't those flags used for 486 kernels? On my system a 2.1.106 kernel
The 486 usually incurs a 2-3% speed penalty when not using 16 byte alignments
(which are default with -m486), although its usually a different issue with
the kernel.
-----==- |
----==-- _ |
---==---(_)__ __ ____ __ Marc Lehmann +--
--==---/ / _ \/ // /\ \/ / pcg@goof.com |e|
-=====/_/_//_/\_,_/ /_/\_\ --+
The choice of a GNU generation |
|
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu