SE I suppose? It seems that the benchmark ends normally with an exit syscall, I would start by looking at --debug-flags SyscallBase to double check that.
Then if that is the case, the only explanation is that some value is getting corrupted somewhere due to a gem5 bug. So I would try to: 1) compare traces from an Atomic and O3 run 2) GDB into the GDB stub to see what leads to that exit being called. On Fri, Jul 10, 2020 at 5:15 PM Alex Freij via gem5-users <gem5-users@gem5.org> wrote: > > Hello all, > > I'm running a single core X86 o3 sim with SPEC2006 benchmarks, and have run > into a scenario where some of the benchmarks are terminating early. Using the > "DRAM" debug flag, I see this message upon termination: > > Exiting @ tick 67067500 because exiting with last active thread context > 67067500: system.mem_ctrls_0: Computing stats due to a dump callback > 67067500: system.mem_ctrls_1: Computing stats due to a dump callback > > Does anyone know of any way to properly debug the root cause of this issue? I > have also used the Exec and ExecAll flags, but not much more information was > provided. > > Thank you, > > - Alex > _______________________________________________ > gem5-users mailing list -- gem5-users@gem5.org > To unsubscribe send an email to gem5-users-le...@gem5.org > %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s On Fri, Jul 10, 2020 at 5:15 PM Alex Freij via gem5-users <gem5-users@gem5.org> wrote: > > Hello all, > > I'm running a single core X86 o3 sim with SPEC2006 benchmarks, and have run > into a scenario where some of the benchmarks are terminating early. Using the > "DRAM" debug flag, I see this message upon termination: > > Exiting @ tick 67067500 because exiting with last active thread context > 67067500: system.mem_ctrls_0: Computing stats due to a dump callback > 67067500: system.mem_ctrls_1: Computing stats due to a dump callback > > Does anyone know of any way to properly debug the root cause of this issue? I > have also used the Exec and ExecAll flags, but not much more information was > provided. > > Thank you, > > - Alex > _______________________________________________ > gem5-users mailing list -- gem5-users@gem5.org > To unsubscribe send an email to gem5-users-le...@gem5.org > %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s _______________________________________________ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s