There is no problem. I believe the disk image from UT contains hooks into gem5 that exit simulation before the region of interest begins. This allows you to fast forward through the irrelevant section and only collect stats or run in detailed mode for the ROI only. You need to modify the config scripts to switch to a detailed CPU and enter back into simulation.
Anthony Gutierrez http://web.eecs.umich.edu/~atgutier On Wed, Aug 28, 2013 at 9:36 AM, יואב אורן <[email protected]> wrote: > Hi, > > I'm running Parsec benchmark with 1 or 4 CPUs with the Disk image from > http://www.cs.utexas.edu/~parsec_m5/ with the updated linux kernel on > full system mode, ass you can see here: > > /home/epyogi/gem5/build/ALPHA/gem5.opt > --stats-file=results_27_08_13_Aug_1377633911_1 > /home/epyogi/gem5/configs/example/fs.py > --script=./parsec_files/blackscholes_1c_simlarge.rcS > --num-cpus=1 --caches --l1d_size=4kB --l1i_size=2kB --l1d_assoc=2 --l2cache > --l2_size=1MB --num-l2caches=1 --l2_assoc=2 --cpu-type detailed > --kernel=vmlinux_2.6.27-gcc_4.3.4 > --disk-image=linux-parsec-2-1-m5-with-test-inputs.img > --mem-size=512MB > > And the problem is before it even gets to the benchmark it quits because > it says that it is switching CPUs. > > 0: system.tsunami.io.rtc: Real-time clock set to Thu Jan 1 00:00:00 > 2009 > **** REAL SIMULATION **** > info: Entering event queue @ 0. Starting simulation... > Exiting @ tick 2369693711500 because switchcpu > > > What could be the problem? Is there a way to force the simulator to run > even tough it is switching CPUs? > > > Thanks, > > Yoav > > _______________________________________________ > gem5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
