Hello Fernando,
Thanks for your guidance.
Regards,
Shervin
---
Hello,
It would be interesting comparing the performance stats produced by gem5
for each core. If they are approximately the same, McPAT is taking into
account the physical distributio
Hello,
It would be interesting comparing the performance stats produced by gem5
for each core. If they are approximately the same, McPAT is taking into
account the physical distribution of the cores, distances, etc.
If your results aren't wrong, they are very interesting!
Regards,
--
Fernando A
Hi Fernando,
Yes, all cores execute same code (Canneal benchamark). For getting correct
power number for all cores, I am wondering whether the execution time
(sim_seconds/sim_ticks) should be above a certain value. If so, what is the
lower threshold of execution time?
Thanks,
Shervin
Hi,
Do the cores execute the same code?
--
Fernando A. Endo, PhD student and researcher
CEA Lab
and
Université de Grenoble, UJF
France
2012/11/4 shervin hajiamini
> Hi Ali,
>
>
> Thank you very much for further direction. I am able to have the stats
> dumped every period with respect to the
Hi Ali,
Thank you very much for further direction. I am able to have the stats dumped
every period with respect to the start and the end ticks.
I have inputted stats (for
a period) into McPat tool to get the power consumption for each core (out of 64
simulated cores). Based on the output of Mc
Runjie,
Thank you again for the further direction.
Regards,
Shervin
--- On Tue, 10/30/12, Runjie Zhang wrote:
From: Runjie Zhang
Subject: Re: [gem5-users] dumping periodic stats with checkpoints
To: "shervin hajiamini"
Cc: gem5-users@gem5.org
Date: Tuesday, October 30, 2012, 4:5
you could precisely let me
> know which command option(s) I need to use? could you please give me a
> numerical example?
>
> Thanks,
> Shervin
>
> --- On *Tue, 10/30/12, Runjie Zhang * wrote:
>
>
> From: Runjie Zhang
> Subject: Re: [gem5-users] dumping periodic sta
tick/cycle c_1 and ends
at tick/cycle c_2, I would appreciate if you could precisely let me know which
command option(s) I need to use? could you please give me a numerical example?
Thanks,
Shervin
--- On Tue, 10/30/12, Runjie Zhang wrote:
From: Runjie Zhang
Subject: Re: [gem5-users] dumping
Hi, Shervin
Have you tried the cmd line options of either fs.py or ruby_fs.py?
For example:
--take-checkpoints=TAKE_CHECKPOINTS
will take checkpoint at cycle M and every N
cycles thereafter
--max-checkpoints=MAX_CHECKPOINTS
the second simulate should be end_tick_ROI - start_tick_ROI. You pass a
relative time to the function, not an absolute time.
Thanks,
Ali
On Oct 27, 2012, at 11:29 PM, shervin hajiamini wrote:
> Hi Ali, Andreas,
>
>
>
> I have tested dumping periodic stats for only ROI by putting the followi
Hi Ali, Andreas,
I have tested dumping periodic stats for only ROI by putting
the following statements in simulation.py:
M5.simulate(start_tick_ROI)
statDump(40)
exit_event =
m5.simulate(end_tick_ROI)
The stats get dumped (every period) starting from start_tick_ROI, but
it does
Hi Ali,
Thank you very much for your direction. If I have understood it correctly,
"ticks_till_ROI" indicates the TICK when ROI starts? How can I specify when (at
which tick) ROI ends? Shall I specify that with m5.MaxTick?
Could you please tell me where exactly (in simulation.py) I should put t
Hi Shervin,
You can modify Simulation.py to run for however many ticks you need an then
return control to python:
m5.simulate(ticks_till_ROI)
statDump(10)
m5.simulate(m5.MaxTick)
Ali
On Oct 24, 2012, at 1:43 AM, shervin hajiamini wrote:
> Ali,
>
> Based on the stats I get for the ent
Ali,
Based on the stats I get for the entire ROI (non-periodic) of a benchmark, I
know approximately at which tick ROI starts and at which tick the ROI ends,
however I do not know how I can use this information for PERIODIC dumping of
stats for ROI only.
I am using statDump(period) which has
How do you know the simulator is in the ROI?
Provided you know when it will be in the ROI, you can can periodically dump the
stats at that point.
Ali
On Oct 24, 2012, at 1:07 AM, shervin hajiamini wrote:
>
> Hello Fernando,
>
> Thanks for the link.
>
> It seems that for getting the periodi
Hello Fernando,
Thanks for the link.
It seems that for getting the periodic stats of a benchmark I need to change
the source code of the benchmark, however I am wondering whether there is a way
to dump the stats ONLY for ROI periodically (w/o checkpoints) without modifying
the source code of
Hello,
What you're looking for is here: http://www.m5sim.org/M5ops
You need to include a header file on your code and call functions to
dump stats and/or reset them. You'll also need to include a .S file in
your makefile.
Hope it will help.
2012/10/23, shervin hajiamini :
>
>
> Hi all,
>
>
> For
17 matches
Mail list logo
