Thanks for the reply:
gdb shows that the segfault is happening in decode_cache.hh:
Program received signal SIGSEGV, Segmentation fault.
getPage (this=0x2ff4ee0) at build/X86/cpu/decode_cache.hh:86
86 if (recent[0] != pageMap.end()) {
Here is a backtrace:
(gdb) backtrace
#0 getPage (this=0x2ff4ee0) at build/X86/cpu/decode_cache.hh:86
#1 lookup (this=0x2ff4ee0) at build/X86/cpu/decode_cache.hh:122
#2 X86ISA::Decoder::doResetState (this=0x2ff4ee0)
at build/X86/arch/x86/decoder.cc:46
#3 0x000000000048de65 in X86ISA::Decoder::process (this=0x2ff4ee0)
at build/X86/arch/x86/decoder.cc:83
#4 0x0000000000e2d3fe in X86ISA::Decoder::moreBytes (this=0x2ff4ee0,
pc=...,
fetchPC=4763648, data=1784132751550744904)
at build/X86/arch/x86/decoder.hh:269
#5 0x0000000000f4c0f8 in BaseSimpleCPU::preExecute (this=0x2800900)
at build/X86/cpu/simple/base.cc:386
#6 0x0000000000f3a0f8 in AtomicSimpleCPU::tick (this=0x2800900)
at build/X86/cpu/simple/atomic.cc:517
#7 0x00000000010f02cc in EventQueue::serviceOne (this=<value optimized
out>)
at build/X86/sim/eventq.cc:207
#8 0x0000000001137943 in simulate (num_cycles=<value optimized out>)
at build/X86/sim/simulate.cc:72
#9 0x0000000000d3d00d in _wrap_simulate__SWIG_0 (self=<value optimized
out>,
args=0x30cfd50) at build/X86/python/swig/event_wrap.cc:4546
#10 _wrap_simulate (self=<value optimized out>, args=0x30cfd50)
at build/X86/python/swig/event_wrap.cc:4596
On Thu, Jan 10, 2013 at 11:21 AM, Nilay Vaish <[email protected]> wrote:
> On Thu, 10 Jan 2013, Yiding Han wrote:
>
> Hi,
>>
>> As a new user, I am running the latest version of gem5 on CentOS 6. I
>> want
>> to simulate the SPEC2k6 benchmarks with a X86 architecture. I compiled
>> ./build/X86/gem5.opt without any issue. The SPEC2k6 benchmarks are all
>> compiled with -static flags, which can run in SE mode successfully with my
>> scripts modified from this page:
>> http://www.m5sim.org/SPEC_**CPU2006_benchmarks<http://www.m5sim.org/SPEC_CPU2006_benchmarks>
>>
>> I generate the checkpoint with:
>> ./build/X86/gem5.opt configs/cmp.py -b perlbench
>> --take-checkpoint=500000000,**100000000 --max-checkpoint=1
>> --checkpoint-dir=./m5out/**checkpoint/400.perlbench/
>>
>> It seems to work since a checkpoint is written. Although gem5 seems to
>> have
>> issues exiting the simulation:
>>
>> Global frequency set at 1000000000000 ticks per second
>> 0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000
>> info: Entering event queue @ 0. Starting simulation...
>> warn: instruction 'fldcw_Mw' unimplemented
>> Writing checkpoint
>> Traceback (most recent call last):
>> File "<string>", line 1, in <module>
>> File "/users/home/yiding/gem5/gem5/**src/python/m5/main.py", line 359,
>> in
>> main
>> exec filecode in scope
>> File "configs/cmp.py", line 147, in <module>
>> Simulation.run(options, root, system, FutureClass)
>> File "/users/home/yiding/gem5/gem5/**configs/common/Simulation.py", line
>> 506, in run
>> print 'Exiting @ tick %i because %s' % (m5.curTick(),
>> exit_event.getCause())
>> UnboundLocalError: local variable 'exit_event' referenced before
>> assignment
>>
>>
>> But the *real* issue is when I try to restore the checkpoint, gem5 has a
>> segfault:
>> ./build/X86/gem5.opt configs/cmp.py -b perlbench --checkpoint-restore=1
>> --checkpoint-dir=./m5out/**checkpoint/400.perlbench/
>>
>> Global frequency set at 1000000000000 ticks per second
>> 0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000
>> warn: optional parameter system.cpu.workload:M5_pid not present
>> **** REAL SIMULATION ****
>> info: Entering event queue @ 500000000. Starting simulation...
>> Segmentation fault
>>
>>
> It seems that the segmentation fault occurred in gem5, and not the
> application. It should be straight forward to figure out where the
> segmentation fault occurred using gdb. Post the function call stack. It
> should be possible to figure out the cause that.
>
> --
> Nilay
>
--
Ph.D. Candidate, Yiding Han
BRIDGE Lab <http://www.engr.usu.edu/bridge/index.html>, ECE Dept.,
Utah State University, Logan, UT 84322, USA
E-mail: [email protected], [email protected]
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
