Hi Raymond Just specify the checkpoint directory and try something like this:
build/ALPHA_FS/gem5.opt configs/example/fs.py --detailed --caches -l2cache -n 3 --script=/home/sdhoble/parsecScripts/bodytrack_3c_simsmall_ckpts.rcS --checkpoint-dir=/path/to/checkpoint/dir Then, after running that command you will have the #.cpt folder in the specified directory. Now you can try the same command with --checkpoint-restore=1 (or '-r 1'), and it will start from the checkpoint. Cheers Negar On 1/9/2013 11:41 PM, Raymond wrote: > n > > 发自我的 iPad > > 在 2012-11-29，2:31，Sumit Dhoble <[email protected]> 写道： > >> Hi all, >> >> I am a beginner with Gem5. I need to run PARSEC benchmarks on ALPHA. I >> followed instructions from the document provided by UT Austin. >> >> In order to follow the document completely, I'm using an older version >> of Gem5 (http://repo.gem5.org/gem5/archive/549b72de8f72.tar.bz2) which >> supported --detailed flags. >> To build the older version, I am using gcc 4.5.3, python 2.4.3 and swig 2.0.2 >> The ALPHA_FS build was successful. >> I am using linux image provided by UT Austin. >> >> >> When I try to create checkpoint using : >> >> build/ALPHA_FS/gem5.opt configs/example/fs.py -n 3 >> --script=/home/sdhoble/parsecScripts/bodytrack_3c_simsmall_ckpts.rcS >> >> >> The terminal output is as follows : >> >> Global frequency set at 1000000000000 ticks per second >> info: kernel located at: >> /home/sdhoble/fullSystemImages/m5_system_2.0b3/binaries/vmlinux >> Listening for system connection on port 3456 >> 0: system.tsunami.io.rtc: Real-time clock set to Thu Jan 1 00:00:00 >> 2009 >> 0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000 >> 0: system.remote_gdb.listener: listening for remote gdb #1 on port 7001 >> 0: system.remote_gdb.listener: listening for remote gdb #2 on port 7002 >> **** REAL SIMULATION **** >> info: Entering event queue @ 0. Starting simulation... >> info: Launching CPU 1 @ 170102500 >> info: Launching CPU 2 @ 172013000 >> warn: Prefetch instructions in Alpha do not do anything >> warn: Prefetch instructions in Alpha do not do anything >> hack: be nice to actually delete the event here >> Exiting @ tick 1871961237500 because m5_exit instruction encountered >> >> >> The document says that a pseudo-instruction in M5 creates the >> checkpoint. But the checkpoint is not created in the directory where >> the above command was run. >> To confirm this when I tried to run the actual benchmark using : >> >> build/ALPHA_FS/gem5.opt configs/example/fs.py --detailed --caches >> --l2cache --checkpoint-restore=1 -n 3 >> >> >> I get the following output : >> >> command line: build/ALPHA_FS/gem5.opt configs/example/fs.py --detailed >> --caches --l2cache --checkpoint-restore=1 -n 3 >> fatal: Checkpoint 1 not found >> >> >> Any help would be appreciated. >> >> Thanks, >> Sumit >> _______________________________________________ >> 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
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
