[gem5-users] ERROR Checkpointing in ALPHA full system

[Fengkai Yuan]

Hi all

     Now, I can boot up a 16-core ALPHA ruby_fs system successfully, with
MESI_CMP_directory protocol.  When I used the "m5 checkpoint" command in
the sell, the simulation aborted with the following information:

Runtime Error at MESI_CMP_directory-L1cache.sm:221, Ruby Time: 23014921238:
Invalid RubyRequestType, PID...

     I check the .sm file above and I found the function below:

  Event mandatory_request_type_to_event(RubyRequestType type) {
    if (type == RubyRequestType:LD) {
      return Event:Load;
    } else if (type == RubyRequestType:IFETCH) {
      return Event:Ifetch;
    } else if ((type == RubyRequestType:ST) || (type ==
RubyRequestType:ATOMIC)) {
      return Event:Store;
    } else {
      error("Invalid RubyRequestType");   *****    HERE is the LINE 221
 ********
    }
  }


      I guess this is because CPU send a wrong type of  RubyRequest message
to a L1 cache and I want to know how to fix this problem.

      Thank you very much for your help!

_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users