1 |
On Dienstag 09 Dezember 2008, Sami Näätänen wrote: |
2 |
> So hi from a amd64 newbie. Not so newbie with Gentoo though. :) |
3 |
> |
4 |
> My system is an Intel quad core core2 with a 2.4 GHz clock speed coupled |
5 |
> with a 4GB of memory. No overclocking etc. Want this to be stable. :) |
6 |
> |
7 |
> I'm just curious what people use as their stable CFLAGS in amd64 Gentoo? |
8 |
> (Sorry if this has been up lately, but I just switched to 64bit env so...) |
9 |
> |
10 |
> |
11 |
> Here is mine and some explanation of why (And I use ~arch system with gcc |
12 |
> 4.3) |
13 |
> |
14 |
> The flags are in order they are used in my CFLAGS and CXXFLAGS. |
15 |
> |
16 |
> Gives stable base |
17 |
> -O2 |
18 |
|
19 |
yes |
20 |
|
21 |
> |
22 |
> Want to optimize for my system, but don't want "native" |
23 |
> -march=core2 |
24 |
|
25 |
ok |
26 |
|
27 |
> |
28 |
> If some ebuilds filter march this will still cache optimize etc for my |
29 |
> system -mtune=core2 |
30 |
|
31 |
I would scrap that. |
32 |
|
33 |
> |
34 |
> Faster floating point math and better chance of vectorization |
35 |
> -mfpmath=sse |
36 |
|
37 |
superfluos. March with amd64 sse is used by default. |
38 |
|
39 |
> |
40 |
> These because of the march might get filtered |
41 |
> -mmmx -msse -msse2 -msse3 -mssse3 |
42 |
|
43 |
if march get filtered, these might one of the reasons, I would remove them. |
44 |
> |
45 |
> For loop vectorization |
46 |
> -ftree-vectorize |
47 |
|
48 |
scrap that. |
49 |
|
50 |
|
51 |
> -pipe |
52 |
> |
53 |
once upon a time I used this flags: |
54 |
|
55 |
#CFLAGS="-march=k8 -O2 -pipe -fweb -ftracer -fpeel-loops -msse3" |
56 |
and even |
57 |
#CFLAGS="-march=k8 -O2 -fweb -ftracer -fpeel-loops -ftree-vectorize -frename- |
58 |
registers -floop-optimize2 -msse3 -pipe" |
59 |
|
60 |
to hunt down a java bug, I recompiled the whole system with: |
61 |
|
62 |
CFLAGS="-march=k8 -O2 -msse3 -pipe" |
63 |
|
64 |
and surprise - it was as fast as before - and compiling was faster too! |