Hi All,

i have made m5thread X86 compile splash2 benchmark.

and running radix with simsmall input
gem5x86.opt ../../configs/example/se.py --l2cache --l1d_size=32kB
--l1d_assoc=4 --l1i_size=32Kb --l1i_assoc=4 --l2_size=256kB
--l2_assoc=8 --cacheline_size=64 --num-cpus=4
--cmd=/opt/m5thread_X86/splash2/radix/radix --options="-p4-t -r1024
-n262144 -m524288" --cpu-type=timing

my benchmark is running for now more than 24 hours. I am just
wondering if things are working correct. or just i am doing some thing
wrong. if any of you have gone through this experience pl. share.

or if i am not doing something correct pl. guide.

A.K.T

On Thu, Mar 6, 2014 at 1:17 PM, Amrish Tewar <[email protected]> wrote:
> hi All,
>
> I tried to read the http://www.m5sim.org/Splash_benchmarks link but i
> am not very familiar with the technical issue discussing by the
> author.
>
> if some one make things easy for understanding i would really appreciate.
>
> I am still worrying the exe i am created is good to run splash2
> benchmark on SE mode.. or i am missing some thing from the link.
>
> If any person has experience. pl. share.
>
> Amrish K. Tewar
>
>
> On Thu, Mar 6, 2014 at 12:32 PM, Lluc Alvarez Marti <[email protected]> 
> wrote:
>> Hi,
>>
>> The inclusion of the pthread.o object file looks OK, assuming
>> "../../pthread.o" is a correct path. This should be enough to compile your
>> benchmarks with the m5threads library.
>>
>> Other issues you may find running the splash2 benchmarks on gem5 are
>> explained here: http://www.m5sim.org/Splash_benchmarks. I'm not familiar
>> with the splash2 at all, so I don't know what's the current state of all
>> this.
>>
>> Lluc
>>
>>
>> On Thu, 6 Mar 2014 11:34:22 -0600, Amrish Tewar wrote:
>>>
>>> Lluc Alvarez Marti, Aditya and All,
>>>
>>> as per guided by Lluc Alvarez Marti,
>>>
>>> i am using following command for making compatible with splash2
>>> benchmark with m5thread. I am asking if anyone agree or denies whether
>>> this is correct of not.
>>>
>>> sample for splash2/apps/lu_cb
>>>
>>> m4 ../../null_macros/c.m4.null.pthread lu.C > lu.c
>>> gcc -c -O2 -w -lm -o lu.o lu.c
>>> gcc -o lu lu.o -static ../../pthread.o -lm
>>>
>>> pl. guide.
>>>
>>> I am trying to compile all other benchmark of spalsh2 on same
>>> fundamental. if any one can correct me i am wrong or correct that will
>>> be help ful
>>>
>>> On Tue, Mar 4, 2014 at 10:11 AM, Lluc Alvarez Marti
>>> <[email protected]> wrote:
>>>>
>>>> Hi!
>>>>
>>>> You can simply compile the m5threads library separately to generate the
>>>> object file, pthread.o, and then just import the pthread.o in the
>>>> compilation of the binaries of your benchmarks. I've done so with the NAS
>>>> benchmarks and works perfectly, and I only had to add one line of code in
>>>> the makefiles to include the pthread.o of m5threads. It should be also
>>>> very
>>>> simple to do with the Parsecs.
>>>>
>>>> Regarding Aditya's question on changing the number of cpus, there's an
>>>> option in the configuration scripts to do so. More info here:
>>>> http://www.m5sim.org/Running_gem5.
>>>>
>>>> Lluc
>>>>
>>>>
>>>> On Tue, 4 Mar 2014 09:05:52 -0600, Amrish Tewar wrote:
>>>>>
>>>>>
>>>>> hey Aditya,
>>>>>
>>>>> I think you need to compile the splash benchmark with X86. i am
>>>>> solving the same problem.... trying to recompile the splash bench mark
>>>>> with m5 thread.
>>>>>
>>>>> if you look m5thread_X86 make file you will see some make file and how
>>>>> to compile.
>>>>>
>>>>> if you see make file in splash benchmark you will see how to compile
>>>>> the benchmark.
>>>>>
>>>>> now you need to write new make file which will be collobrative of this
>>>>> two.
>>>>>
>>>>> I got one or two benchmark compiled but will be compiling other in
>>>>> coming time.
>>>>>
>>>>> if you get some success let me update how you do it.
>>>>>
>>>>> if i got some success i will let you know.
>>>>>
>>>>> AKT
>>>>>
>>>>>
>>>>> On Mon, Mar 3, 2014 at 7:38 PM, Aditya Deshpande
>>>>> <[email protected]> wrote:
>>>>>>
>>>>>>
>>>>>> Hi All,
>>>>>>
>>>>>> I want to run multi-threaded benchmark/code in X86 SE mode. Do I need
>>>>>> to
>>>>>> compile the openmp or pthread code any differently to run in X86 SE
>>>>>> mode
>>>>>> or
>>>>>> just static compilation of code would suffice.
>>>>>>
>>>>>> Also, how to specify the run to use multiple threads/cores in the
>>>>>> execution
>>>>>> command of gem5.
>>>>>>
>>>>>> Regards,
>>>>>> Aditya
>>>>>>
>>>>>> _______________________________________________
>>>>>> gem5-users mailing list
>>>>>> [email protected]
>>>>>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>>>>>
>>>>>
>>>>> _______________________________________________
>>>>> gem5-users mailing list
>>>>> [email protected]
>>>>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>>>>
>>>>
>>>>
>>>>
>>>> WARNING / LEGAL TEXT: This message is intended only for the use of the
>>>> individual or entity to which it is addressed and may contain
>>>> information which is privileged, confidential, proprietary, or exempt
>>>> from disclosure under applicable law. If you are not the intended
>>>> recipient or the person responsible for delivering the message to the
>>>> intended recipient, you are strictly prohibited from disclosing,
>>>> distributing, copying, or in any way using this message. If you have
>>>> received this communication in error, please notify the sender and
>>>> destroy and delete any copies you may have received.
>>>>
>>>> http://www.bsc.es/disclaimer
>>>>
>>>> _______________________________________________
>>>> gem5-users mailing list
>>>> [email protected]
>>>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>>>
>>> _______________________________________________
>>> gem5-users mailing list
>>> [email protected]
>>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>>
>>
>>
>> WARNING / LEGAL TEXT: This message is intended only for the use of the
>> individual or entity to which it is addressed and may contain
>> information which is privileged, confidential, proprietary, or exempt
>> from disclosure under applicable law. If you are not the intended
>> recipient or the person responsible for delivering the message to the
>> intended recipient, you are strictly prohibited from disclosing,
>> distributing, copying, or in any way using this message. If you have
>> received this communication in error, please notify the sender and
>> destroy and delete any copies you may have received.
>>
>> http://www.bsc.es/disclaimer
>> _______________________________________________
>> gem5-users mailing list
>> [email protected]
>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to