Hm, I think 'total power' isn't really a term that makes sense. Power is a rate parameter (i.e. Joules per second), so in that sense, it's sort of like bandwidth -- you can only measure it per unit time.
If you are interested in energy (i.e. just joules) -- currently DRAMSim2 doesn't do that computation. It should be trivial to add though -- essentially you'd just take sum(average power per epoch * length of an epoch in seconds). If you are interested in that, I could add it for you. On Thu, Sep 29, 2011 at 2:59 PM, Zhe Wang <[email protected]> wrote: > Hi, > > I am using Marssx86 integrated with DRAMsim2 to run the simulation. I have > a question about the statistics of the DRAMsim2. > > I would like to get the total DRAM power statistics. But it seems the power > statistics I got either from dramsim.log file or the .vis file are all the > epoch statistics, not the total power at the end of the simulation. So I am > wondering is there any output regarding the total power consumption? or I > have to calculate it by using the epoch statistics by myself? Thank you. > > > Best > zhe >
_______________________________________________ http://www.marss86.org Marss86-Devel mailing list [email protected] https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel
