>What if the dish can actually hold 20 fruits in total, but only 2 apples >and 8 oranges are present? What would be the occupancy? Ok. In that case, occ_percent::total =100% = totalocc_percent::apples + occ_percent::oranges + remaining fruits.
Isn't that? Back to the cache, if the items in the cache are only (writebacks, switch_cpu::data, switch_cpu::inst,prefetcher, cpu::inst and cpu::data) then the total occupancy of 97% means that there are 3% *remaining items*. So what is the remaining items then? On 5/26/12, Nilay Vaish <[email protected]> wrote: > On Sat, 26 May 2012, Mahmood Naderan wrote: > >>> Suppose the system is just about to start, that is number of cycles/ticks >>> = 0. What >would be the value of all of these quantities? >> >> There is no problem with the starting point. At starting point there >> is nothing in cache. The stats are calculated at the end of simulation >> and we want to calculate the items in the cache. > > You are right, there is nothing in the cache when the simulation starts, > which means that all the quantities will have a value of 0. How can that > ever sum up to 1? In which case you are wrong in claiming that these > values should add up to 1. > >> >> >>> Why do you expect these numbers should add up to 100%? >> >> Let me say this example: >> There is a dish that contains 2 apples and 8 oranges. Then total >> number of items are 10. Now the occupancy percentage for apples is >> (2/10)*100=20% and the occupancy percentage for oranges is >> (8/10)*100=80% >> => occ_percent::apples + occ_percent::oranges = 100% > > What if the dish can actually hold 20 fruits in total, but only 2 apples > and 8 oranges are present? What would be the occupancy? > > -- > Nilay > _______________________________________________ > gem5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > -- // Naderan *Mahmood; _______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
