1 |
On 08/14/2013 07:18:41 AM, Pandu Poluan wrote: |
2 |
> Hello list! |
3 |
> |
4 |
> My company has 2 HP DL585 G5 servers and 5 Dell R... something |
5 |
> servers. All |
6 |
> using AMD processors. They currently are acting as XenServer hosts. |
7 |
> |
8 |
> How do I determine the 'least common denominator' for Gentoo VMs |
9 |
> (running |
10 |
> as XenServer guests), especially for gcc flags? |
11 |
> |
12 |
> I know that the (theoretical) best performance is to use |
13 |
> -march=native , |
14 |
> but since the processors of the HP servers are not exactly the same |
15 |
> as the |
16 |
> Dell's, I'm concerned that compiling with -march=native will render |
17 |
> the VMs |
18 |
> unable to migrate between the different hosts. |
19 |
> |
20 |
> Note: Yes I know the HP servers are much older than the Dell ones, |
21 |
> but if I |
22 |
> go -march=native then perform an emerge when the guest is on the Dell |
23 |
> host, |
24 |
> the guest VM might not be able to migrate to the older HPs. |
25 |
> |
26 |
> Rgds, |
27 |
> -- |
28 |
|
29 |
Why not compute it yourself? |
30 |
|
31 |
Do cat /proc/cpuinfo on all machines and compute the intersection of |
32 |
all "flags" |
33 |
Then enter something like the following into /etc/portage/make.conf |
34 |
|
35 |
CFLAGS="-O3 -pipe -msse -msse2 -msse3 -msse4a -m3dnow" |
36 |
|
37 |
Helmut |