The page fault you're seeing below is what you would see on a normal
system as a segmentation fault. You're likely referencing a null pointer
plus some offset. You need to look at a trace of the instructions and
memory system, see how that address is generated and assuming it's the
problem I mentioned, why a previous write disappeared or got lost in
your cache modifications. 

Thanks, 

Ali 

On 07.05.2014 09:27, jiakunli2010 via gem5-users wrote: 

> Hello All! 
> 
> I am running SPEC2006 (4 workloads on 4-core) using gem5 classic memory, 
> timing cpu model. The error message are pasted below. 
> 
> However, when I applied one workload to the same 4-core system, I got no 
> errors for any of the four workloads. The system could also run some other 
> mixes of SPEC2006 workloads and the "Hello world!" example. I searched the 
> debug file but did not find any clues. 
> 
> I made considerable modification to the source code of cache system, I 
> suppose it was bugs there. 
> 
> Does anyone have any idea about where the errors may come from or any 
> suggestion on the debugging method? 
> 
> ============================ 
> 
> info: Increaseing stack size by one page. 
> 
> info: Increaseing stack size by one page. 
> 
> Warning line 7126: Column "C918" for row "R10193" ignored 
> 
> Warning line 7189: Column "C932" for row "1." ignored 
> 
> Warning line 7834: Column "C1084" for row "8" ignored 
> 
> info: Increaseing stack size by one page. 
> 
> Warning line 8824: Column "C1306" for row "1." ignored 
> 
> Warning line 8827: Column "C1306" for row "0" ignored 
> 
> Syntax error in line 8829 
> 
> panic: Page table fault when accessing virtual address 0x98 
> 
> @ cycle 32812561593 
> 
> [invoke: build/ARM/sim/faults.cc, line 70] 
> 
> Memory Usage: 2884000 KBytes 
> 
> ======================== 
> 
> jiakunli2010,jiakunli2...@gmail.com 
> 
> 2014/5/7 
> 
> _______________________________________________
> gem5-users mailing list
> gem5-users@gem5.org
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users [1]

 

Links:
------
[1] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to