Hi all,
I am learning the parallel computing in Julia through the manual Multi-processing and Distributed Computing · The Julia Language
In this page, why is advection_shared! much faster than advection_parallel! ? Both implementations split the array by the 2nd index. One is done manually, and the other one is finalized with the help of @distributed.
I don’t understand the explanation “The biggest advantage of advection_shared! is that it minimizes traffic among the workers, allowing each to compute for an extended time on the assigned piece.”
What is the traffic overhead of the macro @distributed ?