[gem5-users] miss latency cycles is larger than the total CPU cycles
Hi, In my stat.txt file, I see that the miss latency given in cycles is almost 15 times greater than the total execution cycles of my gem5 run. system.switch_cpus.numCycles 31316822936# number of cpu cycles simulated system.l2.demand_miss_latency::switch_cpus.dtb.walker 476626107789 # number of demand (read+write) miss cycles These results are from simulating with TimingSimpleCPU. However, O3 CPU also gives similar results. Can someone please explain why the miss latencies are larger than the number of execution cycles? Thanks in advance, Regards Sethu ___ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
Re: [gem5-users] Migration of gem5-dev and gem5-users to Google Groups
Dear all, Unbeknownst to me, it seems like Google Groups has some limits on the number of "external users" (those without a *@gem5.org email address --- i.e., everyone) that can be added in a single day (there are also other limits, which may be problematic in the future: https://support.google.com/a/answer/166852) . As such I'm postponing the migration until I can find a decent solution to this problem. We shall continue to use Mailman for the time being. Some of you may have already received notification of being added to the Google Groups (though most of you will have not). This is nothing to worry about. No action is required. I apologize for the short Mailing-list downtime. Kind regards, Bobby -- Dr. Bobby R. Bruce Room 2235, Kemper Hall, UC Davis Davis, CA, 95616 web: https://www.bobbybruce.net On Wed, Feb 19, 2020 at 2:23 PM Bobby Bruce wrote: > Dear all, > > Over the next few hours, I shall be migrating the gem5 mailing lists > (gem5-dev and gem5-users) from our old Mailman server to Google Groups. I'm > hoping this should be a relatively easy and quick transfer. All of you will > receive an email inviting you to the new Google Groups, which you should > accept (assuming you want to remain part of the mailing list/lists). The > only potential avenue for problems is the short time you will not receive > emails prior to accepting your Google Groups invitation (so please do this > ASAP). Once this migration is complete, the functionality should be > identical (same email addresses, etc). You will also have the new option of > posting via the Google Groups web interface if you prefer. > > If in a couple of hours of this mail you have yet to receive an > invitation, then please join directly: > > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-dev/join > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-users/join > > If anyone encounters any issues, then please don't hesitate to let me know > at bbr...@ucdavis.edu > > Kind regards, > Bobby Bruce > > -- > Dr. Bobby R. Bruce > Room 2235, > Kemper Hall, UC Davis > Davis, > CA, 95616 > > web: https://www.bobbybruce.net > ___ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
Re: [gem5-users] Migration of gem5-dev and gem5-users to Google Groups
Dear all, Over the next few hours, I shall be migrating the gem5 mailing lists (gem5-dev and gem5-users) from our old Mailman server to Google Groups. I'm hoping this should be a relatively easy and quick transfer. All of you will receive an email inviting you to the new Google Groups, which you should accept (assuming you want to remain part of the mailing list/lists). The only potential avenue for problems is the short time you will not receive emails prior to accepting your Google Groups invitation (so please do this ASAP). Once this migration is complete, the functionality should be identical (same email addresses, etc). You will also have the new option of posting via the Google Groups web interface if you prefer. If in a couple of hours of this mail you have yet to receive an invitation, then please join directly: https://groups.google.com/a/gem5.org/forum/#!forum/gem5-dev/join https://groups.google.com/a/gem5.org/forum/#!forum/gem5-users/join If anyone encounters any issues, then please don't hesitate to let me know at bbr...@ucdavis.edu Kind regards, Bobby Bruce -- Dr. Bobby R. Bruce Room 2235, Kemper Hall, UC Davis Davis, CA, 95616 web: https://www.bobbybruce.net On Wed, Feb 19, 2020 at 2:23 PM Bobby Bruce wrote: > Dear all, > > Over the next few hours, I shall be migrating the gem5 mailing lists > (gem5-dev and gem5-users) from our old Mailman server to Google Groups. I'm > hoping this should be a relatively easy and quick transfer. All of you will > receive an email inviting you to the new Google Groups, which you should > accept (assuming you want to remain part of the mailing list/lists). The > only potential avenue for problems is the short time you will not receive > emails prior to accepting your Google Groups invitation (so please do this > ASAP). Once this migration is complete, the functionality should be > identical (same email addresses, etc). You will also have the new option of > posting via the Google Groups web interface if you prefer. > > If in a couple of hours of this mail you have yet to receive an > invitation, then please join directly: > > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-dev/join > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-users/join > > If anyone encounters any issues, then please don't hesitate to let me know > at bbr...@ucdavis.edu > > Kind regards, > Bobby Bruce > > -- > Dr. Bobby R. Bruce > Room 2235, > Kemper Hall, UC Davis > Davis, > CA, 95616 > > web: https://www.bobbybruce.net > ___ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
Re: [gem5-users] Migration of gem5-dev and gem5-users to Google Groups
Dear all, Unbeknownst to me, it seems like Google Groups has some limits on the number of "external users" (those without a *@gem5.org email address --- i.e., everyone) that can be added in a single day (there are also other limits, which may be problematic in the future: https://support.google.com/a/answer/166852) . As such I'm postponing the migration until I can find a decent solution to this problem. We shall continue to use Mailman for the time being. Some of you may have already received notification of being added to the Google Groups (though most of you will have not). This is nothing to worry about. No action is required. I apologize for the short Mailing-list downtime. Kind regards, Bobby -- Dr. Bobby R. Bruce Room 2235, Kemper Hall, UC Davis Davis, CA, 95616 web: https://www.bobbybruce.net On Wed, Feb 19, 2020 at 2:23 PM Bobby Bruce wrote: > > Dear all, > > Over the next few hours, I shall be migrating the gem5 mailing lists (gem5-dev and gem5-users) from our old Mailman server to Google Groups. I'm hoping this should be a relatively easy and quick transfer. All of you will receive an email inviting you to the new Google Groups, which you should accept (assuming you want to remain part of the mailing list/lists). The only potential avenue for problems is the short time you will not receive emails prior to accepting your Google Groups invitation (so please do this ASAP). Once this migration is complete, the functionality should be identical (same email addresses, etc). You will also have the new option of posting via the Google Groups web interface if you prefer. > > If in a couple of hours of this mail you have yet to receive an invitation, then please join directly: > > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-dev/join > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-users/join > > If anyone encounters any issues, then please don't hesitate to let me know at bbr...@ucdavis.edu > > Kind regards, > Bobby Bruce > > -- > Dr. Bobby R. Bruce > Room 2235, > Kemper Hall, UC Davis > Davis, > CA, 95616 > > web: https://www.bobbybruce.net ___ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
Re: [gem5-users] Migration of gem5-dev and gem5-users to Google Groups
Dear all, Unbeknownst to me, it seems like Google Groups has some limits on the number of "external users" (those without a *@gem5.org email address --- i.e., everyone) that can be added in a single day (there are also other limits, which may be problematic in the future: https://support.google.com/a/answer/166852) . As such I'm postponing the migration until I can find a decent solution to this problem. We shall continue to use Mailman for the time being. Some of you may have already received notification of being added to the Google Groups (though most of you will have not). This is nothing to worry about. No action is required. I apologize for the short Mailing-list downtime. Kind regards, Bobby -- Dr. Bobby R. Bruce Room 2235, Kemper Hall, UC Davis Davis, CA, 95616 web: https://www.bobbybruce.net On Wed, Feb 19, 2020 at 2:23 PM Bobby Bruce wrote: > Dear all, > > Over the next few hours, I shall be migrating the gem5 mailing lists > (gem5-dev and gem5-users) from our old Mailman server to Google Groups. I'm > hoping this should be a relatively easy and quick transfer. All of you will > receive an email inviting you to the new Google Groups, which you should > accept (assuming you want to remain part of the mailing list/lists). The > only potential avenue for problems is the short time you will not receive > emails prior to accepting your Google Groups invitation (so please do this > ASAP). Once this migration is complete, the functionality should be > identical (same email addresses, etc). You will also have the new option of > posting via the Google Groups web interface if you prefer. > > If in a couple of hours of this mail you have yet to receive an > invitation, then please join directly: > > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-dev/join > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-users/join > > If anyone encounters any issues, then please don't hesitate to let me know > at bbr...@ucdavis.edu > > Kind regards, > Bobby Bruce > > -- > Dr. Bobby R. Bruce > Room 2235, > Kemper Hall, UC Davis > Davis, > CA, 95616 > > web: https://www.bobbybruce.net > ___ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
Re: [gem5-users] Migration of gem5-dev and gem5-users to Google Groups
Dear all, Unbeknownst to me, it seems like Google Groups has some limits on the number of "external users" (those without a *@gem5.org email address --- i.e., everyone) that can be added in a single day (there are also other limits, which may be problematic in the future: https://support.google.com/a/answer/166852) . As such I'm postponing the migration until I can find a decent solution to this problem. We shall continue to use Mailman for the time being. Some of you may have already received notification of being added to the Google Groups (though most of you will have not). This is nothing to worry about. No action is required. I apologize for the short Mailing-list downtime. Kind regards, Bobby -- Dr. Bobby R. Bruce Room 2235, Kemper Hall, UC Davis Davis, CA, 95616 web: https://www.bobbybruce.net On Wed, Feb 19, 2020 at 2:23 PM Bobby Bruce wrote: > Dear all, > > Over the next few hours, I shall be migrating the gem5 mailing lists > (gem5-dev and gem5-users) from our old Mailman server to Google Groups. I'm > hoping this should be a relatively easy and quick transfer. All of you will > receive an email inviting you to the new Google Groups, which you should > accept (assuming you want to remain part of the mailing list/lists). The > only potential avenue for problems is the short time you will not receive > emails prior to accepting your Google Groups invitation (so please do this > ASAP). Once this migration is complete, the functionality should be > identical (same email addresses, etc). You will also have the new option of > posting via the Google Groups web interface if you prefer. > > If in a couple of hours of this mail you have yet to receive an > invitation, then please join directly: > > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-dev/join > https://groups.google.com/a/gem5.org/forum/#!forum/gem5-users/join > > If anyone encounters any issues, then please don't hesitate to let me know > at bbr...@ucdavis.edu > > Kind regards, > Bobby Bruce > > -- > Dr. Bobby R. Bruce > Room 2235, > Kemper Hall, UC Davis > Davis, > CA, 95616 > > web: https://www.bobbybruce.net > ___ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
[gem5-users] Migration of gem5-dev and gem5-users to Google Groups
Dear all, Over the next few hours, I shall be migrating the gem5 mailing lists (gem5-dev and gem5-users) from our old Mailman server to Google Groups. I'm hoping this should be a relatively easy and quick transfer. All of you will receive an email inviting you to the new Google Groups, which you should accept (assuming you want to remain part of the mailing list/lists). The only potential avenue for problems is the short time you will not receive emails prior to accepting your Google Groups invitation (so please do this ASAP). Once this migration is complete, the functionality should be identical (same email addresses, etc). You will also have the new option of posting via the Google Groups web interface if you prefer. If in a couple of hours of this mail you have yet to receive an invitation, then please join directly: https://groups.google.com/a/gem5.org/forum/#!forum/gem5-dev/join https://groups.google.com/a/gem5.org/forum/#!forum/gem5-users/join If anyone encounters any issues, then please don't hesitate to let me know at bbr...@ucdavis.edu Kind regards, Bobby Bruce -- Dr. Bobby R. Bruce Room 2235, Kemper Hall, UC Davis Davis, CA, 95616 web: https://www.bobbybruce.net ___ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
Re: [gem5-users] Incorrect Result When Switching to Detailed CPU
I checked out to d40f0bc579fb8b10da7181
Fetch from https://github.com/darchr/gem5
and cherry picked 6450aaa7ca9e3040fb9eecf69c51a01884ac370c and
3403665994b55f664f4edfc9074650aaa7ddcd2c
ISA is x86.
Config files are almost the same with
https://gem5art.readthedocs.io/en/latest/tutorials/npb-tutorial.html
Abhishek Singh , 19 Şub 2020 Çar, 20:51
tarihinde şunu yazdı:
> Hey,
> Can you post details on commit number and ISA, so that we can reproduce
> the output and see
>
> On Wed, Feb 19, 2020 at 12:35 PM Muhammet Abdullah Soytürk <
> muhammetabdullahsoyt...@gmail.com> wrote:
>
>> Hi all,
>>
>> I am trying to simulate PageRank in full system simulation. The
>> application generates a kronecker graph at the beginning (e.g. ./pr -g 10
>> generates a kronecker graph witih 1024 nodes). The problem is that when I
>> try to simulate the whole application with KVM, I get the correct result
>> but when I switch to a detailed cpu (atomic, o3 or timing) just before the
>> application starts, it cannot generate the graph properly.
>>
>> def writeBenchScript():
>> file_name = '/home/muhammet/Desktop/run_pr'
>> with open(file_name,"w") as bench_file:
>> bench_file.write('m5 exit\n')
>> bench_file.write('/home/gem5/gapbs/pr -g 4 \n')
>> bench_file.write('sleep 30 \n') # to print to console.
>>
>> return file_name
>>
>> The code above creates the script.I am using this
>>
>> runscript to send the file create above to the guest and my run config file
>> is like this:
>>
>> boot_linux()
>> m5.stats.reset()
>>
>> if not cpu_name == "kvm":
>> system.switchCpus(system.cpu, system.detailed_cpu)
>>
>> run_gap_benchmark()
>> m5.stats.dump()
>>
>> finish_the_rest
>>
>> What I normally should get is something like this:
>>
>> Generate Time: 0.00023
>> Build Time: 0.00016
>> Graph has 16 nodes and 67 undirected edges for degree: 4
>>
>> But I am getting:
>>
>> Generate Time: 0.0
>> Build Time: 0.0
>> Graph has 14 nodes and 0 undirected edges for degree: 0
>>
>> What is the problem that I am missing?
>>
>> Best,
>> Muhammet
>>
>> ___
>> 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] Incorrect Result When Switching to Detailed CPU
Hey,
Can you post details on commit number and ISA, so that we can reproduce the
output and see
On Wed, Feb 19, 2020 at 12:35 PM Muhammet Abdullah Soytürk <
muhammetabdullahsoyt...@gmail.com> wrote:
> Hi all,
>
> I am trying to simulate PageRank in full system simulation. The
> application generates a kronecker graph at the beginning (e.g. ./pr -g 10
> generates a kronecker graph witih 1024 nodes). The problem is that when I
> try to simulate the whole application with KVM, I get the correct result
> but when I switch to a detailed cpu (atomic, o3 or timing) just before the
> application starts, it cannot generate the graph properly.
>
> def writeBenchScript():
> file_name = '/home/muhammet/Desktop/run_pr'
> with open(file_name,"w") as bench_file:
> bench_file.write('m5 exit\n')
> bench_file.write('/home/gem5/gapbs/pr -g 4 \n')
> bench_file.write('sleep 30 \n') # to print to console.
>
> return file_name
>
> The code above creates the script.I am using this
>
> runscript to send the file create above to the guest and my run config file
> is like this:
>
> boot_linux()
> m5.stats.reset()
>
> if not cpu_name == "kvm":
> system.switchCpus(system.cpu, system.detailed_cpu)
>
> run_gap_benchmark()
> m5.stats.dump()
>
> finish_the_rest
>
> What I normally should get is something like this:
>
> Generate Time: 0.00023
> Build Time: 0.00016
> Graph has 16 nodes and 67 undirected edges for degree: 4
>
> But I am getting:
>
> Generate Time: 0.0
> Build Time: 0.0
> Graph has 14 nodes and 0 undirected edges for degree: 0
>
> What is the problem that I am missing?
>
> Best,
> Muhammet
>
> ___
> 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] Incorrect Result When Switching to Detailed CPU
Hi all,
I am trying to simulate PageRank in full system simulation. The application
generates a kronecker graph at the beginning (e.g. ./pr -g 10 generates a
kronecker graph witih 1024 nodes). The problem is that when I try to
simulate the whole application with KVM, I get the correct result but when
I switch to a detailed cpu (atomic, o3 or timing) just before the
application starts, it cannot generate the graph properly.
def writeBenchScript():
file_name = '/home/muhammet/Desktop/run_pr'
with open(file_name,"w") as bench_file:
bench_file.write('m5 exit\n')
bench_file.write('/home/gem5/gapbs/pr -g 4 \n')
bench_file.write('sleep 30 \n') # to print to console.
return file_name
The code above creates the script.I am using this
runscript to send the file create above to the guest and my run config file
is like this:
boot_linux()
m5.stats.reset()
if not cpu_name == "kvm":
system.switchCpus(system.cpu, system.detailed_cpu)
run_gap_benchmark()
m5.stats.dump()
finish_the_rest
What I normally should get is something like this:
Generate Time: 0.00023
Build Time: 0.00016
Graph has 16 nodes and 67 undirected edges for degree: 4
But I am getting:
Generate Time: 0.0
Build Time: 0.0
Graph has 14 nodes and 0 undirected edges for degree: 0
What is the problem that I am missing?
Best,
Muhammet
___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
