warnings and panics are generally unrelated. warnings just let you know that M5 is doing something that you might want to know about. The fatal error is because your program is executing a system call that we don't support. It basically means that you need to implement the system call or set it up to be ignored.
Nate On Tue, Feb 16, 2010 at 5:25 PM, soumyaroop roy <[email protected]> wrote: > Hello there, > > I am getting a fatal due to usleep_thread syscall while simulating a > few multithreaded configuration for inorder in ALPHA_SE. And this > message seems to be preceded by a sequence of warnings like this: > warn: context 0: XXX consecutive store conditional failures > > It would be helpful to debug if I can have some comments on it. Are > the warning and the panic really related? Also, when might a > usleep_thread syscall get called? Couldn't find much info on google. > > The workloads comprise of spec 2k benchmarks and when run as a single > thread finish without any problems. > > Here are the contents of the simerr file for the one of the workloads: > > warn: Sockets disabled, not accepting gdb connections > For more information see: http://www.m5sim.org/warn/d946bea6 > warn: ignoring syscall sigprocmask(1073070158, 1, ...) > For more information see: http://www.m5sim.org/warn/5c5b547f > warn: ignoring syscall sigprocmask(1073070158, 1, ...) > For more information see: http://www.m5sim.org/warn/5c5b547f > warn: ignoring syscall sigprocmask(0, 3, ...) > For more information see: http://www.m5sim.org/warn/5c5b547f > warn: ignoring syscall sigprocmask(0, 3, ...) > For more information see: http://www.m5sim.org/warn/5c5b547f > hack: return a bogus context id > warn: context 0: 100000 consecutive store conditional failures > For more information see: http://www.m5sim.org/warn/b242bc93 > warn: context 0: 200000 consecutive store conditional failures > For more information see: http://www.m5sim.org/warn/b242bc93 > warn: context 0: 300000 consecutive store conditional failures > For more information see: http://www.m5sim.org/warn/b242bc93 > fatal: syscall usleep_thread (#251) unimplemented. > @ cycle 10657791500 > [unimplementedFunc:build/ALPHA_SE/sim/syscall_emul.cc, line 81] > Memory Usage: 1208176 KBytes > For more information see: http://www.m5sim.org/fatal/be2b42f > > regards, > Soumyaroop > > -- > Soumyaroop Roy > Ph.D. Candidate > Department of Computer Science and Engineering > University of South Florida, Tampa > http://www.csee.usf.edu/~sroy > _______________________________________________ > m5-dev mailing list > [email protected] > http://m5sim.org/mailman/listinfo/m5-dev > > _______________________________________________ m5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/m5-dev
