Re: [gem5-users] ARM bootloader

[Ciro Santilli]

On Thu, Oct 18, 2018 at 5:45 PM Thawra Kadeed  wrote:
>
> Hello,
>
> I have, please, a small question about how GEM5 deals with the
> ARM-specific bootloader.
>
> In GEM5 there are two bootloaders belong to ARM
> (http://www.gem5.org/ARM_Implementation). Let's talk about the simple
> bootloader which starts Cpu0 from the start address of the kernel, and
> puts other cores in a spin-loop until they are started by the kernel.
>
> My main question is:
> How GEM5 uses the ARM-specific bootloader? e.g. GEM5 loads it to the
> simulated memory and then who executes it at the start-up of the system?
>

Well, gem5 sets the PC to the start of the bootloader that was loaded
in memory, and then it just runs like any other code, there is nothing
more than that to
it.

Use gem5.opt --debug-flags=Exec and see the trace.

>
> Thanks in advance.
> Thawra
> ___
> gem5-users mailing list
> gem5-users@gem5.org
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

[gem5-users] ARM bootloader

[Thawra Kadeed]

Hello,

I have, please, a small question about how GEM5 deals with the 
ARM-specific bootloader.


In GEM5 there are two bootloaders belong to ARM 
(http://www.gem5.org/ARM_Implementation). Let's talk about the simple 
bootloader which starts Cpu0 from the start address of the kernel, and 
puts other cores in a spin-loop until they are started by the kernel.


My main question is:
How GEM5 uses the ARM-specific bootloader? e.g. GEM5 loads it to the 
simulated memory and then who executes it at the start-up of the system?



Thanks in advance.
Thawra
___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] "gem5 has encountered a segmentation fault

[Samon Shivastar]

Thanks Boris, Gabe for your reply.

I am using:
x86 architecture
gcc (Ubuntu 7.3.0-27ubuntu1~18.04)  7.3.0
ldd (Ubuntu GLIBC 2.27-3ubuntu1) 2.27

But my benchmarks were compiled on slightly older version of gcc (around
5.2 something). Do I need to re-compile benchmarks again? If so, what
optimization should I use? (i used -O2 -static before).

Thanks in advance for your help :)

Sam

> The message about increasing the stack size is normal. In SE mode the
 > stack grows on demand, and that's just letting you know it added a
new page.
>
> Gabe

> On Wed, Oct 17, 2018 at 10:57 AM Boris Shingarov >
>wrote:

> Which ISA?  What version of the compiler, and what version of libc?
> On PowerPC and MIPS, syscall support in GEM5 has lagged so far behind that
> GEM5 will crash on SE workloads linked to any reasonably-recent glibc.
>
> -"gem5-users"  wrote: -
> To: gem5-users@gem5.org
> From: Samon Shivastar
> Sent by: "gem5-users"
> Date: 10/17/2018 12:57PM
> Subject: [gem5-users] "gem5 has encountered a segmentation fault"
>
> Hello everyone,
>
> I am trying to run different SPECCPU 2006 benchmarks on gem5 is SE mode
> but for some of the benchmarks, the simulation prints the following line:
>
> "info: Increasing stack size by one page."
>
> a bunch of times and then aborts prematurely citing the reason:
>
> "gem5 has encountered a segmentation fault!"
>
> I have two questions:
> 1. What does the line "info: Increasing stack size by one page." exactly
> mean?
> 2. How to fix segmentation fault issue?
>
> I've tried increasing memory size in se.py (--mem-size) but of no use.
> Is there any place where I can increase the stack size to try to fix this
> problem?
>
> Any help would be greatly appreciated :)
>
> Thanks
> Sam
___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

[gem5-users] Accessing the Process ID

[Tassneem Helal]

Hello,

I'm trying to access the processes' IDs for each core instead of accessing
only the instructions (requests), but I'm a little bit lost on where to
find such a thing in the code.
I would really appreciate your help with that

Sincerely,

Tassneem Helal
___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] Gem5 and McPAT error

[Andreas Brokalakis]

Dear Weizheng,

you can find the templates here:
https://github.com/H2020-COSSIM/cMcPAT/tree/master/mcpat/ProcessorDescriptionFiles

Here you can find the conversion script:
https://github.com/H2020-COSSIM/cMcPAT/tree/master/Scripts (note that it
has changes compared to the one you are using)

Lastly, you can find in the repository a newer version of McPAT, which is a
modified 1.3 version.

In any case, it is kinda hard to understand why you have this problem if
you do not share your stats (as well as config.json file), the template and
the output file. Also keep in mind that while a conversion may be legit,
McPAT does not support all possible combinations of systems that gem5 may
support. For example, we modified McPAT because the atomic simple CPU
models that gem5 could support, where not acceptable for McPAT (for example
McPAT will always assume that you have a certain uarch structures). In some
cases we also found that the conversion tool that you have used, didn't
work properly with newer versions of gem5 and under certain circumstances
it would replace a value with a 'nan' number. Of course this caused
problems similar to the ones you are reporting. I would suggest looking
thoroughly to the output.xml file and check that all values that you are
trying to convert using stats.txt and config.json data are properly
converted and there is no problem there.

Best,
Andreas

On Wed, Oct 17, 2018 at 1:16 AM Weizheng Xu <
weizhengxu2...@u.northwestern.edu> wrote:

> Dear all,
>
> I have add the template I used for McPAT as the attachment. But I still
> have the same problem here. I have check the repository of the person who
> help me before https://github.com/H2020-COSSIM/cMcPAT, but I did not find
> the template in his files. I am not sure how can I change the template
> because when I change the value of number of cores and others, they have
> the same problem.
>
> Any help appreciate.
>
> Best wishes,
> weizheng
>
>
>
>
> 在 Sep 25, 2018，7:10 AM，Andreas Brokalakis  写道：
>
> Dear Weizheng,
>
> you are using a quite old version of McPAT. Current version is 1.3. It
> would be better if you used that one.
>
> Now concerning your issues. You need to make sure that the system that you
> are trying to simulate in gem5 matches with the template that you are
> trying to use in McPAT. It is assumed that you need to make changes in the
> template xml file to match it with the gem5 system. Check the proper
> instructions on how to do that.
>
> You can also check the modified McPAT and conversion scripts in my
> repository here: https://github.com/H2020-COSSIM/cMcPAT
>
> Best regards,
> Andreas
>
> On Mon, Sep 24, 2018 at 11:10 PM Weizheng Xu <
> weizhengxu2...@u.northwestern.edu> wrote:
>
>> Dear all,
>>
>> I use gem5 get the full system simulation results and want to use McPAT
>> to get the power model.  I use the Gem5ToMcpat.py and template_xeon.xml
>> gotten from website to translate the stats.txt to the output.xml, which can
>> be read as input by McPAT. But when I use this output.xml as a input for
>> McPAT  (I use command ./mcpat -infile
>> /home//Desktop/test/gem5/ext/mcpat/out.xml in the terminal to run the
>> McPAT), I got the error shown as following:
>> "McPAT (version 0.8 of Aug, 2010) is computing the target processor...
>>
>> some value(s) of
>> number_of_cores/number_of_L2s/number_of_L3s/number_of_NoCs is/are not
>> correct!”
>>
>> I tried to change these values in the template_xeon.xml but still failed
>> with this problem.
>>
>> I really don’t know how to solve this problem.
>>
>> PS: I use ubuntu16.04 LTS and gem5. I use the McPAT provided in the
>> gem5/ext file and with version of 0.8
>>
>> Any help appreciated,
>> thanks
>>
>> Weizheng
>> ___
>> gem5-users mailing list
>> gem5-users@gem5.org
>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>
> ___
> gem5-users mailing list
> gem5-users@gem5.org
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>
>
> ___
> gem5-users mailing list
> gem5-users@gem5.org
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] [EXT] Re: Look into my running simulation

[nocua]

Hi Vitorio,

Based on your command line, I notice that you are configuring a system 
with L2/L3 caches, however, in order to collect the traces using the 
Elastic Traces probe the system should have only L1 caches (as explain 
in the cache configuration file).


./configs/common/CacheConfig.py

# If elastic trace generation is enabled, make sure the memory 
system is
# minimal so that compute delays do not include memory access 
latencies.

# Configure the compulsory L1 caches for the O3CPU, do not configure
# any more caches.
if options.l2cache and options.elastic_trace_en:
fatal("When elastic trace is enabled, do not configure L2 
caches.")


If you want to avoid connecting to a terminal but rather directly run 
the application, you could add the --script option followed by the path 
where to find the rcS. For instance, 
--script=/home/folder/folder/spec_benchmark.rcS.


If the simulation is working properly, you will notice on your m5out 
folder the traces that you created (inst.proto.gz/data.prot.gz) and they 
should increase over time.


You can check as well some info about how to collect/replay Elastic 
Traces in [1].


I hope this helps.

Kind Regards,
Alejandro NOCUA
CNRS Postdoctoral Researcher
LIRMM
161 Rue Ada
34000

[1] http://gem5.org/TraceCPU



Le 2018-10-18 02:41, Vitorio Cargnini (lcargnini) a écrit :

Hi,

I still trying to boot, my gut-feeling, it seems to me that if I
enable the elastic traces all goes south.

My parameters:
gem5.opt --smt --caches --cpu-type=DerivO3CPU --cpu-clock=3GHz
--mem-type=SimpleMemory --mem-channels=2 --mem-ranks=4 --mem-size=16GB
--l1d_size=32kB --l1i_size=64kB --l2_size=8MB --l3_size=22MB
--elastic-trace-en --inst-trace-file=inst.proto.gz
--data-trace-file=data.prot.gz
--disk-image=$M5_PATH/disks/ubuntu-14.04-amd64.img
--kernel=$M5_PATH/binaries/vmlinux-4.8.13-1_amd64

So far it was booting and working without the traces enabled.

What should I do to make it work, I want to trace a benchmark run on
my gem5 and later only feed my system with the traces.

Regards,
Vitorio.


From: Ciro Santilli [mailto:ciro.santi...@gmail.com]
Sent: Wednesday, October 17, 2018 12:05 AM
To: gem5 users mailing list ; Vitorio Cargnini
(lcargnini) 
Subject: [EXT] Re: [gem5-users] Look into my running simulation


On Wed, Oct 17, 2018 at 2:24 AM Gabe Black 
 wrote:

Hi Vitorio. It looks like the kernel panicked and never finished
booting. You can exit m5term by typing ~. (tilda and then period),

OMG, this is amazing!
 
or you can use whatever telnet client/terminal emulator you're 
comfortable with.



Beware however that telnet has some quirks, e.g. arrows stop working,
better stick to m5term.
 
Gabe
On Tue, Oct 16, 2018, 3:41 PM Vitorio Cargnini (lcargnini)
 wrote:
Hello,
 
I set a running simulation, with a SPEC benchmark. However this it is
running for some days already. So I want to check if everything it is
fine with the simulated system, if it is really running.
 
The reason it is:
I have my installation in /home/folder/folder. However I’m running
from a different folder like
/somewhere/folder/folder/folder_where_i_want_the_m5out_folder
 
Looking inside this target location, stats.txt it is empty so far,
there is also a file system.pc.com_1.terminal, and when I look in it I
see in the end:
…
Mountpoint-cache hash table entries: 32768 (order: 6, 262144 bytes)
CPU: CPU feature monitor disabled, no CPUID level 0x5
CPU: CPU feature xsave disabled, no CPUID level 0xd
mce: CPU supports 4 MCE banks
mce: unknown CPU type - not enabling MCE support
Last level iTLB entries: 4KB 0, 2MB 0, 4MB 0
Last level dTLB entries: 4KB 0, 2MB 0, 4MB 0, 1GB 0
Freeing SMP alternatives memory: 24K (8198e000 - 
81994000)

BUG: unable to handle kernel paging request at cd82c740
IP: [] 0xcd82c771
PGD 1807067 PUD 1809067 PMD 0
Oops: 0010 [#1] SMP
Modules linked in:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.8.13 #1
Hardware name:  , BIOS  06/08/2008
task: 8180b500 task.stack: 8180
RIP: 0010:[]  [] 0xcd82c771
RSP: :81803e30  EFLAGS: 0028
RAX: 00020f76 RBX: 0805 RCX: 04000209
RDX: e7dbfbff RSI: 81803e59 RDI: 026c
RBP: 81803e52 R08: 810145f3 R09: 026c
R10: 81803e52 R11: 81803e52 R12: 819858bc
R13: 8192c2e0 R14: 81995000 R15: 00090200
FS:  () GS:88043fc0() 
knlGS:

CS:  0010 DS:  ES:  CR0: 80050033
CR2: cd82c740 CR3: 01806000 CR4: 06b0
DR0:  DR1:  DR2: 
DR3:  DR6: 0ff0 DR7: 
Stack:
810145fb 026c 8197b6a0 81014a35
66909d570006 9090 819dfbe2 004a
8106abcd 

Re: [gem5-users] Gem5 and McPAT error

[Georgios S. Bousdras]

Hi,

The template seems good.
Possibly the problem is after the parser.
The best way is to create your own parser. 
Share the output file in order to check what it is wrong.

Best Regards,
Georgios Bousdras
PhD Researcher — Embedded Systems


> On 17 Oct 2018, at 00:16, Weizheng Xu  
> wrote:
> 
> Dear all,
> 
> I have add the template I used for McPAT as the attachment. But I still have 
> the same problem here. I have check the repository of the person who help me 
> before https://github.com/H2020-COSSIM/cMcPAT 
> , but I did not find the template in 
> his files. I am not sure how can I change the template because when I change 
> the value of number of cores and others, they have the same problem. 
> 
> Any help appreciate.
> 
> Best wishes,
> weizheng
> 
> 
> 
> 
> 
>> 在 Sep 25, 2018，7:10 AM，Andreas Brokalakis > > 写道：
>> 
>> Dear Weizheng,
>> 
>> you are using a quite old version of McPAT. Current version is 1.3. It would 
>> be better if you used that one.
>> 
>> Now concerning your issues. You need to make sure that the system that you 
>> are trying to simulate in gem5 matches with the template that you are trying 
>> to use in McPAT. It is assumed that you need to make changes in the template 
>> xml file to match it with the gem5 system. Check the proper instructions on 
>> how to do that.
>> 
>> You can also check the modified McPAT and conversion scripts in my 
>> repository here: https://github.com/H2020-COSSIM/cMcPAT 
>> 
>> 
>> Best regards,
>> Andreas
>> 
>> On Mon, Sep 24, 2018 at 11:10 PM Weizheng Xu 
>> > > wrote:
>> Dear all,
>> 
>> I use gem5 get the full system simulation results and want to use McPAT to 
>> get the power model.  I use the Gem5ToMcpat.py and template_xeon.xml  gotten 
>> from website to translate the stats.txt to the output.xml, which can be read 
>> as input by McPAT. But when I use this output.xml as a input for McPAT  (I 
>> use command ./mcpat -infile /home//Desktop/test/gem5/ext/mcpat/out.xml in 
>> the terminal to run the McPAT), I got the error shown as following:
>> "McPAT (version 0.8 of Aug, 2010) is computing the target processor...
>> 
>> some value(s) of number_of_cores/number_of_L2s/number_of_L3s/number_of_NoCs 
>> is/are not correct!”
>> 
>> I tried to change these values in the template_xeon.xml but still failed 
>> with this problem.
>> 
>> I really don’t know how to solve this problem. 
>> 
>> PS: I use ubuntu16.04 LTS and gem5. I use the McPAT provided in the gem5/ext 
>> file and with version of 0.8
>> 
>> Any help appreciated,
>> thanks
>> 
>> Weizheng
>> ___
>> gem5-users mailing list
>> gem5-users@gem5.org 
>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users 
>> ___
>> gem5-users mailing list
>> gem5-users@gem5.org 
>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
> 
> ___
> gem5-users mailing list
> gem5-users@gem5.org
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users