[gem5-users] Number of ROI instructions for Parsec with simlarge input

2015-02-28 Thread Fulya via gem5-users
Hi, I would like to know the number of ROI instructions for Parsec with simlarge input. In order to find that out, I ran simulations using the timing simple CPU from the beginning to the end. I am wondering if the number of ROI instructions would be the same or close to each other when running w

[gem5-users] Bad page error continues even with Ruby model

2014-09-30 Thread Fulya via gem5-users
Hi all, I am posting as a follow up of this thread (http://www.mail-archive.com/gem5-users%40gem5.org/msg10489.html). I was having a bad page error when running X86 FS with more than one O3 cpu. I switched to Ruby memory model (with MOESI_hammer protocol), successfully created a checkpoint and

[gem5-users] restore_with_cpu option

2014-09-24 Thread Fulya via gem5-users
Hi all, I figured out myself that I should use both of the options. Thus, I successfully restored with timing simple cpu and shortly after switched to detailed cpu using the following options together: —restore-with-cpu=timing —cpu-type=detailed Issue is resolved. Best, Fulya

[gem5-users] sys-voltage option

2014-09-23 Thread Fulya via gem5-users
Hi all, I was wondering what the "sys-voltage” option is used for. I will be running gem5 simulations and generate power traces in McPat using the performance statistics. Does the sys-voltage option have any impact on the resulting performance statistics, or is it only functional when using Garn

[gem5-users] restore_with_cpu option

2014-09-23 Thread Fulya via gem5-users
Hi all, I am running Parsec with multicore using X86 FS with Ruby memory model and the latest stable gem5 version. I successfully took a checkpoint using the “timing simple cpu” and then restored from the checkpoint using “—restore_with_cpu=detailed” option. My first question is what is the diff

[gem5-users] Restoring from a checkpoint using ruby

2014-09-20 Thread Fulya via gem5-users
Hi all, I am trying to run Parsec on X86 FS multicore, using ruby memory model. My gem5 version is the latest stable version from May31, 2014. I successfully take a checkpoint at the beginning of ROI using "timing simple cpu”. When i try to restore from it using the detailed cpu, I get the follo

Re: [gem5-users] System Hangs

2014-09-18 Thread Fulya via gem5-users
Hi Ivan, I am having the same problem with running X86 FS with PARSEC, multicore, detailed cpu and classic memory model. I have been using the same linux-2.6.22 kernel (which i configured to run with up to 64 CPUs). I have been getting “bad page” errors after switching to detailed cpu posted bel

[gem5-users] Kernel version vs Gem5 version

2014-08-26 Thread Fulya via gem5-users
Hi all, It seems like using the kernel version x86_64-vmlinux-2.6.22.9.smp may have solved my problem that was posted in this thread: http://www.mail-archive.com/gem5-users@gem5.org/msg10387.html However, I am using the latest gem5 version gem5-stable-aaf017eaad7d and I only tested the atomic cpu

[gem5-users] scheduling issue for Parsec X68 FS mode

2014-08-25 Thread Fulya via gem5-users
Hi all, I have been running Parsec benchmarks with x86 FS mode. I am running 4 cpus, 4 threads and using simlarge input set. My gem5 version is the latest stable version (gem5-stable-aaf017eaad7d). I am using the x86_64-vmlinux-2.6.28.4-smp kernel and the parsec image provided on the UT Austin w