1 |
On Tuesday 02 Aug 2016 00:33:57 waltdnes@××××××××.org wrote: |
2 |
> On Tue, Aug 02, 2016 at 01:11:24AM +0200, Jeremi Piotrowski wrote |
3 |
> |
4 |
> > Does it make sense to compile your own versions of these packages |
5 |
> > and then binary merge, when portage already contains binary ebuilds |
6 |
> > for these packages? (firefox-bin/libreoffice-bin/google-chrome) |
7 |
> |
8 |
> I've got an underpowered netbook that needs all the help it can get. |
9 |
> I build in the VM with... |
10 |
> |
11 |
> -O2 -march=bonnell -mfpmath=sse -pipe -fomit-frame-pointer |
12 |
> -fno-unwind-tables -fno-asynchronous-unwind-tables |
13 |
> |
14 |
> Even older desktops benefit. One case in point is my former Dell |
15 |
> D530 Core2 Duo. When Gentoo had been installed, it could not keep up |
16 |
> with the slowest stream of NHL Gamecenter Live. Everything was generic |
17 |
> x86 with SSE2 thrown in, from the stage3. After re-emerging system and |
18 |
> world optimized for the machine's cpu, it could keep up with not only |
19 |
> the lowest quality stream, but a medium-quality stream. So yes, it |
20 |
> helps. |
21 |
> |
22 |
> From http://gentoo-en.vfose.ru/wiki/Safe_Cflags#-march.3Dnative to |
23 |
> find out exactly what your cpu is, run the following command on the |
24 |
> *TARGET* machine... |
25 |
> |
26 |
> gcc -march=native -E -v - </dev/null 2>&1 | grep cc1 |
27 |
> |
28 |
> Ignore the flag output, which may be over-optimistic. Just look at |
29 |
> what it says for "-march=". |
30 |
|
31 |
Yes, I've had similar experiences here with own built binaries being faster |
32 |
than generic *-bin packages offered by portage. The 32bit box in question is |
33 |
running a single core Pentium4 ... I could bet it feels slower than my |
34 |
AppleTV1 with its 1.00GHz Pentium-M. :-) |
35 |
-- |
36 |
Regards, |
37 |
Mick |