I am experiencing the same issue. Wherever one CPU executes exit(), the muti-programmed simulation terminates. Anybody can help? On 11 Oct, 2013, at 1:14 AM, Rodrigo Reynolds Ramírez <rodrigo.r...@hotmail.com> wrote:
> Hello everyone; > > I am using gem5 for multi loads, I am using the below line for executing the > simulator: > > /scratch/gem5/gem5-stable/build/X86/gem5.opt > /scratch/gem5/gem5-stable/configs/example/se.py --caches --l1d_size=32kB > --l1d_assoc=8 --l1i_size=32kB --l1i_assoc=8 --l2_size=256kB --l2_assoc=8 > --l2cache --fast-forward=2000000000 --maxinsts=1000000000 --cpu-type=detailed > -n 4 --cmd="prog1;prog2;prog3;prog4" --options="param1;param2;param3;param4" > --input="in1.txt;in2.txt;in3.txt;in4.txt" --output="out1;out2;out3;out4" > --errout="CLP1.err;CLP2.err;CLP3.err;CLP4.err" > > But I want that each program executes 1 billion instructions in detailed > mode, but it seems that the simulators ends when any program reaches 1 > billion instructions, for different IPC between programs some programs only > executes 1 million instructions or less. > > In summary I need each program executes 1 billion instructions and when one > reaches 1 billion instructions it continues executing for stressing the > memory but not affecting the stats. Is it possible? > > Thanks in advance > Rodrigo > _______________________________________________ > 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
