Hi Yingying, None of them works. I found a previous bug report ( > http://flyspray.gem5.org/index.php?do=details&task_id=7) and I felt the > problem was similar to this one. However Joel Hestness told me that it had > been solved in the version I used. >
Actually, this bug has not yet been resolved as far as I know. The bug fix that I was referring to in our previous email solved the issue of x86 interrupts getting dropped due to priority inversion (Nilay's changeset 9624:43bd6562745e). Per our prior email thread, it sounded like you were running into an issue in which the CPU cores stopped executing instructions (using --debug-flags=Exec). The Flyspray report linked above has the CPU cores falling into an idle loop, which now sounds like a more likely problem given the IPC numbers you're seeing. It would be most helpful if you could pin down the specifics of how the simulation is hanging (as opposed to looking at statistics). The debug flags, Exec and LocalApic, should be most useful for this. Joel -- Joel Hestness PhD Student, Computer Architecture Dept. of Computer Science, University of Wisconsin - Madison http://pages.cs.wisc.edu/~hestness/
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
