Basically I'm wondering if a principle like cache locality, i.e. it's advantegous to access consecutive pieces of memory because usually bigger chunks of that memory are loaded into cache, also matters at the application level.
In practice - let's assume applications which don't require much extra allocations once started - I wonder if there is an advantage in starting application A and waiting a while, and then starting application B versus starting application A and B simultaneously. For the latter case I could imagine A requesting some memory, then B, then A again and so on (though I'm not sure it happens like that but on the other hand the OS cannot know on beforehand how much memory is going to be needed so it's not like it can reserve one big chunk on beforehand).
Is there a disadvantage to that, i.e. having the application memory consisting of multiple chunks at addresses further away from each other then what could theoretically be achieved if all application memory was allocated as one big chunk?
Recent Questions...
ما را در سایت Recent Questions دنبال میکنید
برچسب:
نویسنده: استخدام کار
بازدید: 299
تاريخ: چهارشنبه
9 تير
1395 ساعت: 15:22