Hello,
Had a similar problem. What I did was running "hg log `find -name HMC.py`" to
see which updates has changed HMC.py file. This gave:
changeset: 11551:d24ad08b22b0
user:Abdul Mutaal Ahmad
date:Fri Jul 01 09:45:21 2016 -0500
summary: mem: different HMC configuration
...
X86ISA::Walker::WalkerState::recvPacket(PacketPtr): Assertion
`!delayedResponse' failed.
Program aborted at tick 11
--- BEGIN LIBC BACKTRACE ---
...
Basically I am stuck at this point. Could anyone point me out my mistakes/how
to solve this problem?
The link to the configur
gem5-users-boun...@gem5.org>> on behalf of
Serhat Gesoglu
mailto:serhat.geso...@manchester.ac.uk>>
Reply-To: gem5 users mailing list
mailto:gem5-users@gem5.org>>
Date: Wednesday, 25 January 2017 at 19:55
To: "gem5-users@gem5.org<mailto:gem5-users@gem5.org>"
g.ini file under system.realview.vram or
system.realview.nvmem (type=SimpleMemory). SimpleMemory latency is defined in
src/mem/SimpleMemory.py
Hope these helps.
Thanks and kind regards
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on
Hello,
Have you tried changing the path in configs/common/SysPath.py ?
Serhat
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Wang, Chenxu
[wa...@rose-hulman.edu]
Sent: 10 February 2017 09:10
To: gem5-users@gem5.org
Subject: [gem5-users] Errors
Hello Muzamil,
I, as well, had the same error/similar errors and believe that there is a bug
in the HMC model .
For more information, simulating the HMC model is only possible with an atomic
CPU but without caches. The following situations (for an ARM system) also
failed for me:
- atomic CPU wi
Hello Muzamil,
I believe LiveProcess() was changed to Process(). simple.py you are using was
probably downloaded from learning.gem5.org, that file is not up-to-date. You
may want to check configs/learning_gem5/part/simple.py for an updated version.
This should be the changeset: http://repo.gem5.
Hello,
L3 cache is not implemented in gem5 but you can manually implement it (and add
a command line option such as --l3caches), unless you are using ruby (as far as
I know due to not having a 3-level coherence protocol).
You may want to check this tutorial for more information about adding cach
Hello,
I believe, you can use "m5_reset_stats" in SE mode, in your program. You may
want to check util/m5/m5op.h and other related files in util/m5 directory.
Cheers
Serhat
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Summer Deng
[csummer.
Hello,
Packet objects (MemReq), holds all the information you need. In order to have
the information, you should create a memory object sitting between between l1
and l2 caches. This page explains how to do that in detail:
http://learning.gem5.org/book/part2/memoryobject.html.
Hope this helps
Hello,
I am not sure about the second bug, sorry, but the warnings in your first
output would not affect your simulations, unless you are planning to something
using those.
"Mount failed for selinuxfs on /sys/fs/selinux: No such file or directory"
selinux in Ubuntu has some problems: https://wik
Hello,
You can use "--ignore-style" command line option to disable style checking
hooks.
Here is the source: http://gem5.org/Build_System#Command_line_options
Cheers
Serhat
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of
maitysancha...@gmail
Hello,
It is an automatically created file, after building a system you can find this
file in gem5_dir/build/[arch]/config/
Hope this helps.
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Nidhi Kamath
[nidhikamat
Hello,
You can create ARM dtb files following the instructions here:
http://www.gem5.org/ARM_Kernel
The command you are looking for is: make -C system/arm/dt
Hope this helps
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of
/questions/41930/kernel-panic-not-syncing-vfs-unable-to-mount-root-fs-on-unknown-block0-0
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Francesco Mazzei
[mazzeifr...@gmail.com]
Sent: 09 August 2017 16:25
To: gem5 users mailing list
Hello,
The file should be created by scons. I just did a clean clone and build, and
the aforementioned file was created without any problems. Are you using the
latest version of gem5? Can you try rebuilding again?
Cheers
Serhat Gesoglu
From: gem5-users
efine USE_KVM 0".
https://gem5.googlesource.com/public/gem5/+/master/SConstruct#1295
https://gem5.googlesource.com/public/gem5/+/master/src/SConscript#361
Cheers
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Nidhi Kamath
[nid
nd build/X86/configs/have_protobuf.hh
has the line "#define HAVE_PROTOBUF 1".
I searched for a solution in this mailing list but could not find a solution
(or the solutions suggested did not work). Anyone has any idea what might be
the problem?
Thanks and kind regards.
Serhat Geso
.
Thanks and kind regards.
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Serhat Gesoglu
[serhat.geso...@manchester.ac.uk]
Sent: 21 November 2017 16:19
To: gem5-users@gem5.org
Subject: [gem5-users] 'MemTraceProbe' is n
Hello,
Which scons version are you using? I had a similar problem, solution to this
was using scons version 2.5.1.
Hope this helps
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Samon Shivastar
[rulethek...@gmail.com]
Sent
Hello,
I believe you do not need to change anything on CommMonitor.py. Did you follow
the instructions here and attach a probe to the monitor you are using:
http://gem5.org/General_Memory_System#Traffic_analysis_and_memory_trace_capture
?
Cheers
Serhat Gesoglu
itor.trace = MemTraceProbe(trace_file="l1trace.trc.gz")
self.dcache_port = self.monitor.slave
self.monitor.master = dc.cpu_side
..
Cheers
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Saivarun R
[rsvar
Hello,
I am glad I could be of help.
Not exactly sure what was the problem with your versions. Making sure that only
the files you edited are different from the branch you use might help
(something like git diff | grep "diff --git").
Cheers
Serhat
From
://gem5.org/TraceCPU
- "Exploring System Performance using Elastic Traces: Fast, Accurate and
Portable" Radhika Jagtap, Stephan Diestelhorst, Andreas Hansson, Matthias Jung
and Norbert Wehn SAMOS 2016 https://doi.org/10.1109/SAMOS.2016.7818336
Cheers
Serh
"isInstFetch()" (pkt->req->isInstFetch()).
Hope this helps.
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Muhammad Ali Akhtar
[muhammadali...@gmail.com]
Sent: 13 February 2018 18:09
To: gem5-users@gem5.org
Subject: [ge
Hello,
It seems you have typos for both tries. For the first one cpu type should be
"DerivO3CPU" not "Deriv03CPU" (With the letter O not the number 0).
The second error is occuring due to missing a dash symbol for l2_size, there
must be 2 dashes (--l2_size not -l2_siz
first. It creates a checkpoint
and stops. The second time (when restored from a checkpoint), you use your own
script.
Kind regards
Serhat Gesoglu
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of Yunxia Zhu
[emilia...@gmail.com]
Sent: 21 August
..@gmail.com]
Sent: 28 August 2018 10:28
To: gem5 users mailing list
Subject: Re: [gem5-users] Create Checkpoint
Hello Serhat Gesoglu,
I used m5 commands but I still failed to create checkpoint.
Here it is details:
Create checkpoint:
gem5 $ build/X86/gem5.opt configs/example/fs.py
--script=co
-users [gem5-users-boun...@gem5.org] on behalf of Yunxia Zhu
[emilia...@gmail.com]
Sent: 28 August 2018 12:44
To: gem5 users mailing list
Subject: Re: [gem5-users] Create Checkpoint
Hello Serhat Gesoglu,
I didn't get any error and I didn't get "checkpoint simulation" either. M
Hello,
I am not really sure if it is normal for it to run that long. Are you using
custom image/kernel files or the ones dowloaded from gem5 website?
Could you also check your m5out/system.terminal to see if there is anything
useful?
Kind regards
Serhat Gesoglu
artup.
[ OK ] Started Update UTMP about System Runlevel Changes.
Ubuntu 16.04.1 LTS zhu ttyS0
with best regards
yunxia zhu
On Wed, 29 Aug 2018 at 16:27, Serhat Gesoglu
mailto:serhat.geso...@manchester.ac.uk>> wrote:
Hello,
I am not really sure if it is normal for it to run that long.
Hello,
Are there spaces after the equal signs in the command you are trying to run or
are they there due to the email formatting? If it's the former, you should
remove them and try running the command again.
i.e.
$ ./build/ALPHA/gem5.opt ./configs/example/fs.py
--disk-image=/media/shukla/Window
Hi,
> i m getting the output as clock = 1 1 3 4 i can't understand what it means?
Those numbers represent "ticks". Ticks are the smallest time unit gem5
understands and 1 tick is equal to 1 picosecond [1].
As I understand from this config, you have 4 different clocks in your setup
which are 1000
Hello,
fsck and its variations can be used on a partition, not on an entire image
file/disk.
Since you are using an image file, you need to create a loop device to run
e2fsck.
After increasing the disk size with:
$ dd if=/dev/zero bs=1M count=400 >> linux-x86.img
Expand the first partition:
Hello,
"chroot" is what you are looking for to install the packages you want.
$ mount -o loop,offset /mnt
$ cd /mnt
$ mount --bind /proc /mnt/proc
$ mount --bind /sys /mnt/sys
$ mount --bind /dev /mnt/dev
$ chroot .
After chroot you'll be in the image file's root directory and should be able to
Hello,
You can combine "--at-instruction" and "--take-checkpoint" /
"--checkpoint-restore" flags to take a checkpoint after 100M instructions and
restore from the same point.
Serhat
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of siva sankar
Hello,
Are you using the up-to-date gem5? Memory classes were renamed a while ago.
You can check the available classes using
$ ./build/ARM/gem5.opt configs/example/fs.py --list-mem-types
Serhat
From: gem5-users [gem5-users-boun...@gem5.org] on behalf of V
Hello,
"run.py" is a simple script to introduce the full system mode.
For creating/restoring checkpoints "configs/example/fs.py" might be a better
example.
I would also recommend taking a look at the run() function in
"configs/common/Simulation.py".
Serhat
_
Hello,
If you are using the recent versions of gem5, you should use:
***
from m5.objects.CommMonitor import *
from m5.objects.MemTraceProbe import *
***
instead of "from import *"
I just did a clean install / build and did not have any errors.
Kind regards
Serhat
___
mod.__dict__
File "/home/cc/gem5-prefetch-camat/src/cpu/BaseCPU.py", line 60:
from m5.objects.MemTraceProbe import *
***
I think this error was because of the absence of protobuf. However, I have
installed protobuf,
***
protoc --version
libprotoc 3.9.0
***
So is this a version
Hi,
Yes, you can trace the packets by using CommMonitor. You will need to add the
monitor between cache and cpu (gem5/src/cpu/BaseCPU.py).
Take a look at: gem5/src/mem/CommMonitor.py
and http://old.gem5.org/General_Memory_System.html (there is a traffic analysis
subsection which could be useful)
Hi,
You need to decode the trace file using gem5/util/decode_packet_trace.py.
This python file dumps the traces to ASCII.
More information on the fields can be found here:
https://www.gem5.org/documentation/general_docs/cpu_models/TraceCPU
Serhat
From: gem5-users
Hi,
I am sure there are much better ways to do this but so far there are not any
other suggestions.
One solution could be creating an event and scheduling it to monitor the number
of misses.
When the number reaches N, exitSimLoop exits the simulation with a cause, such
as "Encountered N misses"
Hi,
I am copying the instructions from my answer to another gem5 question to
increase your disk image size:
https://www.mail-archive.com/gem5-users@gem5.org/msg16495.html
fsck and its variations can be used on a partition, not on an entire image
file/disk.
Since you are using an image file, you
44 matches
Mail list logo