On Wed, December 26, 2012 8:26 am, hanfeng QIN wrote: > Hi, > > I collect a group of simulation statistics in ALPHA_SE mode with classic > memory system. The workload is selected from SPEC CPU 2K6 and is run in > detailed measurement with 10 billion instructions. I compare the CPI and > computed MPKI with the one obtained from native run (in x86_64 > architecture). I find these statistics are very different. I am not sure > whether this difference is caused by the simulated architecture. Since > I need to evaluate my idea with prior solutions, these statistics must > be proof enough. >
Why do you think the statistics should be similar? How close are the simulated and native systems in the terms of gem5's configuration? -- Nilay _______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
