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
