How to efficiently handle parallelism on a DistributedArray

deltaeecs · May 23, 2022, 6:54am

Actually I find that there are 2 most time consuming parts in my work:

spawning the tasks, because args passed to function are large in my task;
passing the parts of array SubDArray, which is inefficient as mentioned in the source code of DistributedArray DistributedArrays.jl/darray.jl at master · JuliaParallel/DistributedArrays.jl · GitHub at line 819.

Topic		Replies	Views
Distributed generation of a DArray General Usage parallel	5	1270	June 26, 2017
Best practice for data-parallel computation using DistributedArrays Julia at Scale	1	840	April 3, 2018
Right way of using DistributedArrays General Usage	0	550	July 5, 2017
How to access the localpart of a distributed array? Julia at Scale	8	1749	October 28, 2017
DistributedArrays: unexpected behavior before modifying localpart Julia at Scale	1	579	November 29, 2017