Hi Giang,
I would recommend using the mercurial linux repository and the patch
queue provided. If you can't do that then you should apply all the
patches in the order that they're listed in the series file. The
comment after the patch describes what version of the kernel that
patch is for.
Additionally, you'll need to compile the PAL code with the big tsunami
options. Without those changes the kernel will be unable to sent
interrupts to > 4 processors.
Ali
On Apr 10, 2008, at 1:54 PM, Giang Hoang wrote:
Hello,
I am currently able to run m5 in full system mode with 4
processors. However, I cannot yet get it run with 8 processors. I
have looked through previous threads and found some suggestions on
how to fix this problem. However, there are things that are not
clear to me. So I hope someone would clarify these.
First, I found recommendations that I should compile the kernel
2.6.13 downloaded from m5 web site rather than the stock kernel.
But I cannot find a link to this kernel source from m5 website?
I tried compiling with the kernel 2.6.13 that I downloaded from
kernel.org instead. I found patches to allow more than 4 processors
from m5 web site, however, I am not sure which one I should apply?
Is it necessary to set up a mercurial repository in order to apply
these patches? If I apply all of them using the patch command, the
kernel fails to compile. I could compile the kernel when I applied
only the patches bigtsunami_2.6.13.diff, bigtsunami.diff,
defaultconfig_2.6.13.diff and a few other patches. However, m5 does
not fully boot. Here are the last few output I had before the
program stalled:
Using epoch = 1900
Console: colour dummy device 80x25
Dentry cache hash table entries: 32768 (order: 5, 262144 bytes)
Inode-cache hash table entries: 16384 (order: 4, 131072 bytes)
Memory: 118496k/131072k available (3424k kernel code, 9112k
reserved, 998k data, 224k init)
Mount-cache hash table entries: 512
SMP starting up secondaries.
Slave CPU 1 console command START
SlaveCmd: restart FFFFFC0000310020 FFFFFC0000310020 vptb
FFFFFFFE00000000 my_rpb FFFFFC0000018400 my_rpb_phys 18400
Slave CPU 2 console command START
SlaveCmd: restart FFFFFC0000310020 FFFFFC0000310020 vptb
FFFFFFFE00000000 my_rpb FFFFFC0000018680 my_rpb_phys 18680
Slave CPU 3 console command START
SlaveCmd: restart FFFFFC0000310020 FFFFFC0000310020 vptb
FFFFFFFE00000000 my_rpb FFFFFC0000018900 my_rpb_phys 18900
Slave CPU 4 console command START
SlaveCmd: restart FFFFFC0000310020 FFFFFC0000310020 vptb
FFFFFFFE00000000 my_rpb FFFFFC0000018B80 my_rpb_phys 18B80
Slave CPU 5 console command START
SlaveCmd: restart FFFFFC0000310020 FFFFFC0000310020 vptb
FFFFFFFE00000000 my_rpb FFFFFC0000018E00 my_rpb_phys 18E00
Please give some suggestions on how to fix this problem
Thank you very much.
Giang Hoang
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
