Hi Sue,
I merely want to highlight that clang seems to use far less memory than gcc
during both compilation and linking. If you have the possibility, using clang
might mitigate the issue until the decoder is split.
Andreas
From: gem5-users-boun...@gem5.org [mailto:gem5-users-boun...@gem5.org]
Hi all,
I just ran splash benchmark..but getting this error...
$ build/ALPHA/m5.debug configs/splash2/run.py -n 2 -b FMM
gem5 Simulator System. http://gem5.org
gem5 is copyrighted software; use the --copyright option for details.
gem5 compiled Jul 23 2012 12:03:50
gem5 started Jul 25 2012 09:5
Hi all,
I have a question about the "--clock=CLOCK" parameter in the command line.
Under fs.py, ruby_fs.py and ruby_random_test.py, they all have this clock
parameter. I wonder when I set --clock=0.5GHz under ruby_fs.py, is that the
frequency of core part or it is the frequency of Gems( including
Hi Ali and GEM5 Users
I have tried again and could boot both ALPHA and X86, as follows:
> Time to shell prompt at ALPHA: 0m38.826s (running on [Intel i7
Extreme]@[3.33GHz+16GB RAM])
$ cd /home/user/gem5; export M5_PATH=/home/user/gem5; time
./build/ALPHA/gem5.opt --outdir=/tmp/output ./configs/e
Hello,
I am searching for benchmarks for running gem5 with X86 SE.
I read the workloads section at http://www.m5sim.org/Documentation.
but i noticed that SPEC is used for ALPHA and there is no information about
using SPLASH and SPEC for X86 and there is no guide for link to get these
benchmarks.
Found the problem.
It was an issu with pagePtr not being initialized in system.cc -
http://www.mail-archive.com/gem5-dev@gem5.org/msg02833.html
Thanks again for your help guys!
-Andrea
On Tue, Jul 24, 2012 at 3:55 PM, Andrea Pellegrini <
andrea.pellegr...@gmail.com> wrote:
> Ali, Korey, thanks f
Hi Ali
I am a very new user and after your answer I tried the following
simulations:
1) I have tried to simulate X86 boot in FS mode using --cpu-type=atomic all
the time, and running only a "hello program", for 1165m59.515s with no
success or any error message.
2) I have also tried to simulate A
Hi Nilay
I am a very new user and after your answer I found this:
(from FAQ at
http://www.m5sim.org/Frequently_Asked_Questions#How_many_CPUs_can_M5_run.3F)
How many CPUs can M5 run?
- There is no inherent limit in M5 (other than simulation speed). In SE
mode there are no obstacles to simu
Thanks for the heads up. I see in the mailing list archives where others
have run into this... I don't know what's unique about Red Hat that causes
these problems.
As I mentioned before, I did spend some time looking into how we could
split up the x86 decoder.cc into chunks, and it's very feasibl
Thank you for the suggestion. We'll give it a try later this week or next.
Sue
-Original Message-
From: gem5-users-boun...@gem5.org [mailto:gem5-users-boun...@gem5.org] On
Behalf Of Nilay Vaish
Sent: Monday, July 23, 2012 11:15 AM
To: gem5 users mailing list
Subject: [EXTERNAL] Re: [gem5-
Ali, Korey, thanks for your suggestions.
It happens right away, as soon as "process.cc" start initiating the memory
space for the program. Valgrind does not detect any issue on my laptop, and
unfortunately I cannot run it on the cluster.
Nobody else is using the cluster, so it's the perfect time
/mc/compose?to=gem5-users@gem5.org>
> > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
> >
>
>
>
> --
>
> *thanks®ards
> *
> *BISWABANDAN*
> *Any intelligent fool can make things bigger, more complex, and more
> violent.
> It takes a touch of genius - and a lo
Also, how much memory are yuou asking for? Is this a early error or
after simulation for awhile?
If you are running on a cluster, you need to be cognizant that other
users can have processes that request a lot of memory so maybe figure
out how you can reserve the necessary amount for you simulatio
Could you give it a run through valgrind and see if it shows
anything?
Thanks,
Ali
On 24.07.2012 13:55, Andrea Pellegrini
wrote:
> Hi all,
> I am facing a bizarre issue w/ X86, SE, O3.
> On
my laptop the simulator works fine, but when I run gem5 on our
simulation pool I almost always g
sers
> >
>
>
>
> --
>
> *thanks®ards
> *
> *BISWABANDAN*
> *Any intelligent fool can make things bigger, more complex, and more
> violent.
> It takes a touch of genius - and a lot of courage - to move in the opposite
> direction.*
> -- next part -
Hi all,
I am facing a bizarre issue w/ X86, SE, O3.
On my laptop the simulator works fine, but when I run gem5 on our
simulation pool I almost always get "fatal: Out of memory, please increase
size of physical memory".
Of course I recompile everything from scratch when I run gem5 on our
servers.
Hi Kypros,
The hierarchy is something like this:
src/cpu/testers/networktest.cc (~CPU, issues reads and writes) -->
NetworkTest protocol (~cache coherence protocol which creates cache/dir
controllers) --> garnet/fixed-pipeline/NetworkInterface_d (receives msgs
from cache controller and converts
t;
>
> --
>
> *thanks®ards
> *
> *BISWABANDAN*
> *Any intelligent fool can make things bigger, more complex, and more
> violent.
> It takes a touch of genius - and a lot of courage - to move in the opposite
> direction.*
> -- next part --
>
iolent.
It takes a touch of genius - and a lot of courage - to move in the opposite
direction.*
-- next part --
An HTML attachment was scrubbed...
URL:
<http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20120724/d94ef3e0/attachment-0001.html>
Can you try and run this on a x86_64 system? That file system is ~2GB
which will overflow a standard int on your 32-bit setup and would
explain the whacky behavior.
Or we have to set _FILE_OFFSET_BITS=64 for the M5 compile to use
uint64's for file operations to avoid this. (not sure how to do thi
Could you try and run with opt instead of fast? You should only run
fast if you've successfully run a simulation before or run something
very similar to it. Having asserts and additional debugging is helpful
in these situations. Clearly something has gone wrong because Linux
thinks the device is
Hi Tony,
Thanks for trying that.
I'm using the vmlinux.arm.smp.fb.2.6.38.8 kernel which I downloaded
with the ubuntu-natty image from the new full systems package linked
to on the downloads page
(http://www.gem5.org/dist/current/arm/arm-system-2011-08.tar.bz2) .
I have also tried with the VExpr
Hi Tushar,
Thank you for the quick reply.
What I want to do, is change injRate
from PACKETS per node per cycle to FLITS per node per cycle.
To do this I need to divide the success possibility by the number of flits in
the packet, but the sizes of the buffers are stored in the attributes of the
After you updated the patch, the old combination of cpu-type=timing and
restore-with-cpu =timing works.
But cpu-type=detailed and restore-with-cpu=timing fails with the same
assertion
command line:
/home/anusha/gem5_9123/build/ALPHA_MOESI_CMP_directory/9123moesi.opt
--debug-flags=ProtocolTrace -
Hi Kypro,
NetworkTest is simply the dummy coherence protocol that you can run to simulate
network-only traffic.
GarnetNetwork_d is the actual network.
The messages to/from the NetworkInterface_d come from/to the cache/dir
controllers in NetworkTest.
Could you give me more details about what is it
I am unable to replicate the error using the latest stable repo with the
ubuntu-natty image and your command line verbatim. Are you sure you're
using the correct kernel?
-Tony
On Tue, Jul 24, 2012 at 11:04 AM, Stuart Ryan wrote:
> Hi,
>
> I'm using gem5-stable (9073:f75ee4849c40) and having som
On Tue, 24 Jul 2012, Anusha wrote:
The value of _status at that point is
Breakpoint 1, TimingSimpleCPU::switchOut (this=0x2391180)
at build/ALPHA_MOESI_CMP_directory/cpu/simple/timing.cc:154
154 {
(gdb) p _status
$3 = BaseSimpleCPU::IcacheWaitResponse
Hence the assertion fails.
Earli
On Tue, 24 Jul 2012, huangyongbing wrote:
Hi all,
I want to simulate many-cores on gem5. So I want to know the
maximum cores that gem5 can support for x86 architecture.
gem5 does not impose any upper bound on the number of CPUs instantiated in
a simulation.
--
Nilay
Hi,
I'm using gem5-stable (9073:f75ee4849c40) and having some trouble
getting a FS ARM platform to boot with the
arm-ubuntu-natty-headless.img (or indeed with a self made image
following the instructions on the wiki - with the same error) . I have
not had any problems with the busybox image (linu
Hi all,
I want to simulate many-cores on gem5. So I want to know the
maximum cores that gem5 can support for x86 architecture.
Thanks.
Best regards,
Yongbing Huang
___
gem5-users mailing list
gem5-users@gem5.org
http:
The value of _status at that point is
Breakpoint 1, TimingSimpleCPU::switchOut (this=0x2391180)
at build/ALPHA_MOESI_CMP_directory/cpu/simple/timing.cc:154
154 {
(gdb) p _status
$3 = BaseSimpleCPU::IcacheWaitResponse
Hence the assertion fails.
Earlier when cpu-type was timing and resto
Hello,
I need to pass the buffer sizes from GarnetNetwork_d
to NetworkTest. Is there any connection between the two?
E.g. is there any pointer accessible from NetworkTest that
points to the GarnetNetwork_d, or a router?
Thank you,
Kypros Chrysanthou
Hello,
I need to pass the buffer sizes from GarnetNetwork_d
to NetworkTest. Is there any connection between the two?
E.g. is there any pointer accessible from NetworkTest that
points to the GarnetNetwork, or a router?
Thank you,
Kypros Chrysanthou
__
33 matches
Mail list logo
