Many thanks for your hints!
On 05/14/2017 07:13:05 AM, Walter Dnes wrote:
Why aren't you running "-march=native"? You're probably missing
quite
a few features of your cpu. BTW, "-march=native" implies
"-mtune=native"
and "-msse3" (if the cpu supports it). Out of sheer curiousity, what
does gcc report as your native cpu when you run...
gcc -c -Q -march=native --help=target | grep march=
-march=amdfam10
> and quite a e few
> CFLAGS="-O3 -mtune=native -pipe -msse -msse2 -msse3 -msse4a -m3dnow"
> (for my aged AMD64 Phenom II machine)
>
> in /etc/portage/env/...
"-O3"... yikes! Not really recommended. If you want speedup, use
"-march=native" instead.
I didn't have any problems with that. I only use these setting non
compute intensive packages which
are not system critical.
In make.conf, I have...
CFLAGS="-O2 -march=native -mfpmath=sse -fomit-frame-pointer -pipe
-fno-unwind-tables -fno-asynchronous-unwind-tables"
The 2 "unwind_tables" flags reduce code bloat. See
http://comments.gmane.org/gmane.linux.busybox/36695 for details. The
guys at busybox do what they can to reduce code bloat. Knocking 15%
off
the size of an executable or library helps. This results in faster
loading at startup (less to load), and less stuff in ram cuts down on
swapping.
Many thanks, again
Helmut
