1 |
Walter Dnes wrote: |
2 |
> On Fri, Feb 24, 2012 at 03:13:07AM +0200, Nikos Chantziaras wrote |
3 |
> |
4 |
>> The speed gains of building for specific submodels of CPUs might |
5 |
>> be there, but they're minimal. Benchmarks have shown (can't find |
6 |
>> the article, it was on Phoronix) that after -march=i686 you get |
7 |
>> diminishing returns. |
8 |
> |
9 |
> In that case, the benchmarks are useless. From my personal |
10 |
> experience... a fresh i686 install on a 4 and 1/2 year old Dell with |
11 |
> onboard Intel GPU was not able to keep up with the slowest available |
12 |
> speed on NHL Gamecenter Live. Ditto for 1080i TV from my HDHomerun |
13 |
> tuner box. After rebuilding system+world+kernel with "march=native", |
14 |
> it works just fine for the above tasks. I'm not the only one to see |
15 |
> this. See thread... |
16 |
> "Slow not in sync movie playing with mplayer2, ffmpeg, x264 with intel core i5" |
17 |
> starting Sun, 12 Feb 2012 on this list. |
18 |
> |
19 |
> As I mentioned in that thread |
20 |
>> Optimizing one library may seem very minor, but it all adds up when |
21 |
>> you optimize every library on your system. |
22 |
> |
23 |
> To get the full benefit of optimization, you need to optimize your |
24 |
> entire system. The i686 code used for the install CD has to be generic |
25 |
> lowest-common-denominator i686 code, in order to run on every 6-year-old |
26 |
> i686 cpu out there. The tradeoff is that you lose the benefits of |
27 |
> optimisation. |
28 |
> |
29 |
|
30 |
|
31 |
It's odd that I was thinking about your video problem when I posted my |
32 |
reply earlier. |
33 |
|
34 |
If using those makes no difference, why even have the option? |
35 |
|
36 |
Dale |
37 |
|
38 |
:-) :-) |
39 |
|
40 |
-- |
41 |
I am only responsible for what I said ... Not for what you understood or |
42 |
how you interpreted my words! |
43 |
|
44 |
Miss the compile output? Hint: |
45 |
EMERGE_DEFAULT_OPTS="--quiet-build=n" |