| 1 |
Pandu. |
| 2 |
|
| 3 |
I don't have the link handy. But there is a list of safe CFLAGS. Pick the one for the older CPU. |
| 4 |
That should be safe. |
| 5 |
|
| 6 |
-- |
| 7 |
Joost |
| 8 |
|
| 9 |
Pandu Poluan <pandu@××××××.info> wrote: |
| 10 |
>Hello list! |
| 11 |
> |
| 12 |
>My company has 2 HP DL585 G5 servers and 5 Dell R... something servers. |
| 13 |
>All |
| 14 |
>using AMD processors. They currently are acting as XenServer hosts. |
| 15 |
> |
| 16 |
>How do I determine the 'least common denominator' for Gentoo VMs |
| 17 |
>(running |
| 18 |
>as XenServer guests), especially for gcc flags? |
| 19 |
> |
| 20 |
>I know that the (theoretical) best performance is to use -march=native |
| 21 |
>, |
| 22 |
>but since the processors of the HP servers are not exactly the same as |
| 23 |
>the |
| 24 |
>Dell's, I'm concerned that compiling with -march=native will render the |
| 25 |
>VMs |
| 26 |
>unable to migrate between the different hosts. |
| 27 |
> |
| 28 |
>Note: Yes I know the HP servers are much older than the Dell ones, but |
| 29 |
>if I |
| 30 |
>go -march=native then perform an emerge when the guest is on the Dell |
| 31 |
>host, |
| 32 |
>the guest VM might not be able to migrate to the older HPs. |
| 33 |
> |
| 34 |
>Rgds, |
| 35 |
>-- |
| 36 |
|
| 37 |
-- |
| 38 |
Sent from my Android phone with K-9 Mail. Please excuse my brevity. |
Archives