On Thu, Jun 3, 2010 at 1:15 PM, Weixun Wang <wew...@cise.ufl.edu> wrote: > I'm usinig m5.fast now. Everything is OK except the following: > > 1) Benchmarks from CPU 2000 are still executing very slow in M5 (m5.fast). I > tried gcc and mcf. Both of them have taken quite a long time but are still > running. I'm sure they are being executed based on the output. Is it normal?
Define "very slow" :-). This is an instruction-level simulator, so it's going to be a lot slower than native execution. Mostly it depends on how detailed your simulation model is, but at best you're still looking at a slowdown on the order of 1000X. That's life. > 2) MiBench benchmarks work well. However, I found output redirection does > not work. For example, running toast: > > ./m5.fast ../../configs/Test_Weixun/se.py --cmd > ../../../benchmarks/mibench/gsm/toast --options "-fps -c > ../../../benchmarks/mibench/gsm/small.au > > ../../../benchmarks/mibench/gsm/output_small.encode.gsm" > > The redirection part of --options "> > ../../../benchmarks/mibench/gsm/output_small.encode.gsm" does not have any > effect and the output is to the screen no matter what. How to specify > redirection in this scenario? That's not how redirection works... there's no shell to interpret '>' so you have to do it differently, using the --output option to se.py. Run the se.py script with the --help option to see more. > > 3) gzip from CPU 2000 gives the following error after executing for a > certain amount of time: > > panic: Tried to access unmapped address 0x12014a000. > @ cycle 141067250000 > [invoke:build/ALPHA_SE/arch/alpha/faults.cc, line 204] > Memory Usage: 576044 KBytes > For more information see: http://www.m5sim.org/panic/5932f339 > Program aborted at cycle 141067250000 > Abort That's basically a segfault in gzip, but I don't know why it would be happening. Steve _______________________________________________ m5-users mailing list m5-users@m5sim.org http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
