1 |
A while back I ran a large number of tests on optimisations across an |
2 |
athlon t-bird 1.4g, pentium4M (dell laptop) and a cyrix 200 (for fun!). |
3 |
The applications were scientific, some home scripts and gimp |
4 |
manipulations. |
5 |
|
6 |
I was mainly interested in routines that run for many hours/days as this |
7 |
was what was causing me the most grief at the time. Basicly, ~10% gains |
8 |
can be be seen between -Os (s must be for for slowest!) and -O2 (-O3 is |
9 |
almost always slower than -O2) |
10 |
|
11 |
Of course, results were highly variable, and application dependent. |
12 |
|
13 |
I came to the conclusion that for me, compiling the system with |
14 |
"-march=athlon-xp -O2 -pipe -fomit-frame-pointer -falign-functions=4" |
15 |
gave the best general gain. My next step was to be to compile all the |
16 |
gui stuff with -Os to speed up startup - but I never got around to it. |
17 |
|
18 |
Per package optimisations would be nice, but I can imagine it getting |
19 |
into a far greater mess than USE flags are at the moment - getting |
20 |
unusable. |
21 |
|
22 |
BillK |
23 |
|
24 |
On Thu, 2004-07-22 at 19:06, Jerry McBride wrote: |
25 |
> On Thursday 22 July 2004 02:35 pm, Bart Alewijnse wrote: |
26 |
> > I'm curious as to how many of you have considered and tried using -Os |
27 |
|
28 |
|
29 |
|
30 |
-- |
31 |
gentoo-performance@g.o mailing list |