I found the problem is that I compile the application on my 32-bit linux while the kernel is 64-bit (which I did not notice in the beginning and then assumed that 64 bit machine should be able to run 32 bit applications by nature )
So, the solution was to recompile the benchamrk with the options "-m64 -fPIC -mfpmath=sse" gets me into the same problem as this thread: http://comments.gmane.org/gmane.comp.emulators.m5.users/11623 The benchmark works fine, but it hangs like forever reporting that these instructions not implemented even though I used -mfpmath=sse any help with this ? Regards From: mostafa.m.has...@hotmail.com To: gem5-users@gem5.org Date: Fri, 11 Jan 2013 17:44:17 +0200 Subject: Re: [gem5-users] Running benchmark on FS X86 : Assertion `!delayedResponse' failed. Thanks alot Steve for the support. I will give it a try Regards Date: Fri, 11 Jan 2013 07:10:29 -0800 From: ste...@gmail.com To: gem5-users@gem5.org Subject: Re: [gem5-users] Running benchmark on FS X86 : Assertion `!delayedResponse' failed. My suggestion for debugging this is to use debug tracing to see how you got there. Since you know when the error happens, you can turn on tracing just a little bit in advance so you're not slowing down the whole simulation. So add soemthing like: --trace-start=5065359000000 --debug-flag=TLB,Ruby --trace-file=trace.out and then look at the output, starting from the end, and see if it shows how you got there. Those might not be the best (or even the correct) debug flags, I'm just doing this off the top of my head. Steve On Fri, Jan 11, 2013 at 5:22 AM, Mostafa Mahmoud Hassan <mostafa.m.has...@hotmail.com> wrote: Then, how could I trace the TLB translations ?? and another question is : why this problem occurs only when I try to run the benchmark, i.e. If I just booted the system without launching a benchmark (no benchmark .rcs file passed in command line) , no errors occur. Could the compilation of the benchmark be the root cause ?? Mostafa > Date: Thu, 10 Jan 2013 19:31:28 -0600 > From: ni...@cs.wisc.edu > To: mostafa.m.has...@hotmail.com > CC: gem5-users@gem5.org > Subject: RE: [gem5-users] Running benchmark on FS X86 : Assertion > `!delayedResponse' failed. > > On Fri, 11 Jan 2013, Mostafa Mahmoud Hassan wrote: > > > > > I could not figure out what is the problem in the first place. All what > > I can see is that the code behavior seems illogical because it will > > certainly cause the assertion to fail consistently in timing mode &g t; > > > If the code that you are claiming is incorrect, it seems not a single > translation would happen. Why don't you test your theory to check if that > is the case? > > -- > Nilay _______________________________________________ gem5-users mailing list gem5-users@gem5.org 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 _______________________________________________ gem5-users mailing list gem5-users@gem5.org 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
