Hi Jason and Yuan, Is this also valid to multithreaded applications (using pthreads library) in SE mode? If so, the results that gem5 simulator generates, in SE mode for multithreaded applications, is not reliable.
thanks in advance. ---------------------------------------------------------------------------------------------------------------------------------------------- Francisco Carlos Silva Junior PhD Student at University of Brasilia ________________________________ De: gem5-users <gem5-users-boun...@gem5.org> em nome de Jason Lowe-Power <ja...@lowepower.com> Enviado: terça-feira, 24 de setembro de 2019 11:47 Para: gem5 users mailing list <gem5-users@gem5.org> Assunto: Re: [gem5-users] Question about multi-program simulation using spec2006 Hi Yuan, Generally, it is difficult to get multiprogrammed workloads running in SE mode. It may be possible, but it probably isn't very realistic anyway. I suggest using FS mode. Cheers, Jason On Mon, Sep 23, 2019 at 5:24 PM yuan <syu...@ncsu.edu<mailto:syu...@ncsu.edu>> wrote: Hi, All, I am trying multi program simulation using spec2006 benchmarks. When I configure a multicore system and assign each core a different benchmark, I find that eventually there are only part of the cores are working. That means eventually there are only 1 or 2 cores has statistics, but the others have no statistics. I tried to dump out the instruction counter of each core but find that not all cores can dump out this info. Does anyone has any hints about this? Thanks all. Best regards. Yuan Sent from Mail<https://go.microsoft.com/fwlink/?LinkId=550986> for Windows 10 _______________________________________________ gem5-users mailing list gem5-users@gem5.org<mailto:gem5-users@gem5.org> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
_______________________________________________ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
