Hi, I have Splash-2 compiled with m5threads for the X86 architecture. I'm trying to run it with the classic memory system, in SE mode, with the TimingSimpleCPU. I'm not sure these runs are making forward progress. They have been running for over 2 days. Looking at a trace I see a lot of repetitive addresses being generated.
Here is the exact command I used: ~/gem5-stable-6a043adb1e8d/build/X86_MESI_CMP_directory/gem5.opt ~/gem5-stable-6a043adb1e8d/configs/example/se.py --l2cache --l1d_size=32kB --l1d_assoc=4 --l1i_size=32kB --l1i_assoc=4 --l2_size=256kB --l2_assoc=8 --cacheline_size=64 --num-cpus=4 --cmd=/home/DREXEL/sn446/ECEC414/X86/splash2/splash2/codes/kernels/lu/non_contiguous_blocks/LU --options=-p4 -t --cpu-type=timing Has anyone encountered this issue before? Has anyone run this particular configuration? When I switch to the AtomicSimpleCPU all my runs finish very quickly. Regards, Sid
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
