The latency is set to "warn: interval=18294713441". This is for the apache quadcore benchmark.
-Rick nathan binkert wrote: > What was the latency set at? I believe that it was a problem and the > change should be committed, I'd just like to understand it. > > Nate > > >> That was the cause the assertion error in the quadcore experiments. >> >> -Rick >> >> nathan binkert wrote: >> >>> I'm not saying that you're wrong, but can't this only be a problem if >>> you specify a latency that's greater than 2 billion ticks (2us)? Were >>> you running with this kind of super high latency? >>> >>> Nate >>> >>> >>> >>>> I believe in src/cpu/base.hh::121, class ProfileEvent : public Event that: >>>> >>>> int interval; >>>> >>>> should be: >>>> >>>> Tick interval; >>>> >>>> src/cpu/base.hh::128 >>>> ProfileEvent(BaseCPU *cpu, int interval); >>>> >>>> should be: >>>> ProfileEvent(BaseCPU *cpu, Tick interval); >>>> >>>> and also in src/cpu/base.cc:360, >>>> >>>> BaseCPU::ProfileEvent::ProfileEvent(BaseCPU *_cpu, int _interval) >>>> >>>> should be >>>> >>>> BaseCPU::ProfileEvent::ProfileEvent(BaseCPU *_cpu, Tick _interval) >>>> >>>> Otherwise, this can cause problems because src/cpu/BaseCPU.py specifies >>>> the value as a latency. This was causing an assertion to fail in the >>>> eventq.hh:schedule() being called from src/cpu/base.cc:: >>>> BaseCPU::ProfileEvent::process() >>>> >>>> -Rick >>>> _______________________________________________ >>>> m5-dev mailing list >>>> m5-dev@m5sim.org >>>> http://m5sim.org/mailman/listinfo/m5-dev >>>> >>>> >>>> >>>> >>> _______________________________________________ >>> m5-dev mailing list >>> m5-dev@m5sim.org >>> http://m5sim.org/mailman/listinfo/m5-dev >>> >>> >>> >> _______________________________________________ >> m5-dev mailing list >> m5-dev@m5sim.org >> http://m5sim.org/mailman/listinfo/m5-dev >> >> >> > _______________________________________________ > m5-dev mailing list > m5-dev@m5sim.org > http://m5sim.org/mailman/listinfo/m5-dev > _______________________________________________ m5-dev mailing list m5-dev@m5sim.org http://m5sim.org/mailman/listinfo/m5-dev