Hi

I've got same trace files fro, different benchmarks! For example, I've used
this command for canneal  :


./build/X86/gem5.opt --debug-flags=Exec
--trace-file=/home/dsrt/gem5/trace/X86/canneal/4thread-4core_3.out
configs/example/fs.py
--disk-image=/home/dsrt/gem5/linux-parsec-2-1-m5-with-test-inputs.img
--kernel=/home/dsrt/gem5/x86_64-vmlinux-2.6.28.4-smp --cpu-type="timing"
--caches --l2cache --script=/home/dsrt/gem5/PARSEC/canneal_4c_simmedium.rcS
-m 200000000000 -n 4

I've checked all these benchmarks:  blackscholes, bodytrack, canneal,
dedup, facesim, ferret and swaptions.
But the trace files are same. I don't understand this too.

Another time, I've ran all these benchmarks on ALPHA. for example, the
command for swaptions is


./build/ALPHA/gem5.opt --debug-flags=Exec
--trace-file=/home/dsrt/gem5/trace/ALPHA/swaptions/4thread-4core_3.out
configs/example/fs.py
--disk-image=/home/dsrt/gem5/linux-parsec-2-1-m5-with-test-inputs.img
--kernel/home/dsrt/gem5/vmlinux_2.6.27-gcc_4.3.4 --cpu-type="timing"
--caches --l2cache
--script=/home/dsrt/gem5/PARSEC/swaptions_4c_simmedium.rcS -m 200000000000
-n 4

Unfortunately, the achieved result from different benchmarks are same too .
Note that, I've checked the .rcS files which had been made with "
writescript.pl" for different benchmarks, and it seems there is no mistake
in commands to execute the benchmarks.


Could you please help me?
Thank you





-- 
Bahar Asgari
Department of Computer Engineering
Iran University of Science and Technology
_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to