Hi all, I've been trying to run some FS tests on ARM. I just tried to run gem5 without modifications but using a runscript and FS mode on a detailed CPU. When it tried to take a checkpoint (whether with a m5 hook compiled in the code or through an m5 command in the runscript) it hung. Ctrl-c did nothing but restart the event loop.so I had to send a sigkill manually. My command line is:
"./build/ARM/gem5.debug configs/example/fs.py --machine-type=VExpress_EMM -n 4 --script=/home/dkindel/runscripts/4c_ckpt_test.rcS --caches --cpu-type=detailed" My runscript contains: cd /parsec/install/bin.ckpts /sbin/m5 dumpstats /sbin/m5 resetstats echo "Before CKPT" /sbin/m5 checkpoint echo "Done :D" /sbin/m5 exit /sbin/m5 exit On the output, I see the "Before CKPT" displayed but nothing after. This is in the dev repo. In the stable repo, I run with 1 core and get that the skid buffer exceeded the max size after the "Before CKPT" and before "Done." I'm not sure if it's something on my machine or not. I appreciate any help! Thanks, Dave Kindel
_______________________________________________ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
