In fact, if one of the processors carries 99% of the computational load, then we only lose on parallelization, as the overhead of process synchronization will be added. Good parallelization is impossible without a detailed analysis of the program. All this is done in such a way that the work of one of the employees practically does not interfere with the work of the others (and if it does, then both are trying to get into the same place, but for these cases a system of conflict resolution is provided). They solve subtle problems of maintaining data integrity when changes are received from multiple sources, when server, network, etc. In this case, corporate support systems for distributed work are resorted to (Lotus Works can be cited as a positive example of a stable system, although the author has not worked with it since 2002, so improvements since then could have led to a loss of reliability). I need to, say, make changes to Chapter 3, but I cannot do this, because for a couple of hours someone has been working on Chapter 13, which practically does not depend on Chapter 3. But imagine, for example, the collective work on a puffy technical task. Of course, the easiest way to establish exclusive use of a shared resource: the program that accesses this resource sets the flag, and while the flag is raised, no one else can access it.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
January 2023
Categories |