Hi, Thanks for your reply.
I did that and Linux was booted successfully. Then things go wrong when I try to modify pipeline stages of routers. To be more clear, I have two versions of GEM5. The first one implements MyTopology with generic GARNET routers and it works. The second one implements MyTopology with modified routers and this version is stuck at booting Linux. Terminal returns that the system has brought up 16 CPUs but stuck at here (shown below) Brought up 16 CPUs SMP: Total of 16 processors activated (63965.49 BogoMIPS). net_namespace: 552 bytes -- 陳冠廷 K.-T. Eric Chen 國立交通大學電子所 Institute of Electronics, National Chiao Tung University, Hsinchu, Taiwan E-mail：[email protected] / [email protected] On Thu, Sep 13, 2012 at 10:28 AM, Nilay Vaish <[email protected]> wrote: > On Thu, 13 Sep 2012, 陳冠廷 K.-T. Eric Chen wrote: > > Hi, >> >> I'm trying to build a new topology (MyTopology) with heterogeneous routers >> using RUBY. (Heterogeneous means routers with different pipeline stages) >> >> I've written a new python file for MyTopology and it works fine (both >> ALPHA_Network_test and ALPHA_MESI_CMP_directory) with homogeneous routers. >> But I got problem when I try to simulate with heterogeneous routers >> (flexible-network, different pipeline stages for routers). The >> ALPHA_Network_test was fine. But full-system simulation is stuck at some >> point when booting up Linux. It has executed for 2 days and didn't return >> any exceptions or errors. Does anyone have any ideas? >> >> > Why not first try out booting Linux with out any changes? > > -- > Nilay > _______________________________________________ > 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
