[gem5-users] Got 'keyError: 'SWIG' error message

Hi, Is there anyone who can help me to solve below problem? I ran 'scons' command shown as: >scons build/ALPHA_FS/gem5.opt PROTOCOL=MOESI_CMP_direct RUBY=True And get below message (keyError: 'SWIG') First time I install and run splash on gem5 was around April 2012. That time I wasn

[gem5-users] Understanding numCycles, idleCycles, quiesceCycles statistics in ARM SMP system

Hi, I'm having some trouble understanding the following statistics in an ARM SMP full system linux simulation (arm_detailed, n=2, from gem5-stable) numCycles : The test program is single threaded, with most activity on CPU0. At the end of the test the stats.txt shows a different number for switch_

Re: [gem5-users] Got 'keyError: 'SWIG' error message

It seems like SWIG is not installed on the machine. Can you confirm? -- Nilay On Tue, August 7, 2012 2:39 am, Haera Chung wrote: > Hi, > > > > Is there anyone who can help me to solve below problem? > > I ran 'scons' command shown as: > >>scons build/ALPHA_FS/gem5.opt PROTOCOL=MOESI_CMP_direct RU

Re: [gem5-users] Understanding numCycles, idleCycles, quiesceCycles statistics in ARM SMP system

See Inline Hi, > I'm having some trouble understanding the following statistics in an > ARM SMP full system linux simulation (arm_detailed, n=2, from > gem5-stable) > Best thing to do is grep around to see where these stats are used. > > numCycles : The test program is single threaded, with mos

Re: [gem5-users] Got 'keyError: 'SWIG' error message

This does seem like a bug in the SConstruct though in that we use main['SWIG'] on line 351 but don't check to see if it's valid and warn about not having swig installed until line 577. Anyone have any idea why it's that way, and why we don't move the check up earlier? Steve On Tue, Aug 7, 2012 a

Re: [gem5-users] Got 'keyError: 'SWIG' error message

Hi Steve, It is all legacy. The line was even hardcoded to 'swig' a few months ago before I made it the user env SWIG. Once I clear my jungle of patches I'll fix it up :) Andreas From: Steve Reinhardt mailto:ste...@gmail.com>> Reply-To: gem5 users mailing list mailto:gem5-users@gem5.org>> Date

Re: [gem5-users] L2_latency and system panic

There is some issue with the o3 cpu not re-executing this load before commit (because it's uncacheable). You'll need to track the sequence number (sn) through execution in the O3 cpu and see why it wasn't re-executed and debug it. Thanks, Ali On 06.08.2012 07:55, Ali chaker wrote: > Hi,

[gem5-users] Ports in L1 Cache

Hi all, I am wondering if there is any quick way to increase the number of ports of a O3 CPU to the ICache and DCache (or mimic a similar behavior). Did anyone look at it yet? Thanks, -Andrea ___ gem5-users mailing list gem5-users@gem5.org http://m5sim.o

[gem5-users] Ruby Message.clone() -- multicast

Is it generally safe to send multiple copies of the same MsgPointer(ref-counted) around? That is, if a message has multiple destinations and it arrives at one, will that destination modify the underlying Message in a way which will affect other destinations? Garnet doesn't support multi/broadcasti

Re: [gem5-users] Ruby Message.clone() -- multicast

Hi Mark, No sending the same MsgPointer around can cause problems because the NI that receives it earlier will send it up to the cache/dir controller which will delete it after consuming it. You could perhaps add some extra bcast_id in the message at the source and identify it based on the {sou

[gem5-users] multi-programmed simulation on X86_FS

To whom it may concern, I tried to run 2 spec benchmarks on a 2-core CMP (on X86_FS mode). I tried to use /sbin/m5 pin 0 $bench0 & /sbin/m5 pin 1 $bench1 in my .rcS script file. However it shown the error information as : m5: setaffinity: Invalid argument I also tried to use taskset 0x

Re: [gem5-users] multi-programmed simulation on X86_FS

You could try using taskset (I'm not sure if it's on the disk image), but it does the same thing as m5 pin. taskset 0x1 $bench0 & taskset 0x2 $bench1 & taskset 0x4 $bench2 & Ali On 07.08.2012 19:27, Cookie wrote: > To whom it may concern, > I tried to run 2 spec benchmarks on a 2-co

Re: [gem5-users] multi-programmed simulation on X86_FS

Hi Ali, Thank you for your quick reply. But I did try taskset (as the way you shown) and it printed out the same error. 1/ Is that the problem related to disk image? Because when I check the previous FAQs, I noticed your reply at ( http://comments.gmane.org/gmane.comp.emulators.m5.users/3939). I

Re: [gem5-users] multi-programmed simulation on X86_FS

My next guess is that perhaps the kernel you're using doesn't support process affinity? I'm not sure if that is possible, but it's a guess. As for why cpu1 stats are 0, either you haven't switched cpu models yet or nothing has run on the second core (It's been idle). This is likely given that