I’m trying to speed up some code that takes subsets of columns from a data matrix and calculates a maximum score. The orginal code is complicated, so I’ve tried to simplfy it was much as possible here: using Combinatorics #Helper function to loop through pairs of data columns allpairs(v) = Iterato…

It would presumably help to squeeze out all the allocations from your score function. I’ve been looking for an excuse to play with @Mason ’s neat Bumper.jl as an alternative to writing technical multithreaded code that manually manages local buffers correctly, and this seems like a good opportunity. …

Having issues speeding up code with multithreading

General Usage Performance

LaurentPlagne July 12, 2023, 3:44pm 10

And all the time is spent in allocation required by the linear solve:

2 Likes

Topic		Replies	Views
Threads maxing out all cores, but no performance increase General Usage performance , threads	16	1700	April 6, 2021
Speed up parallel maximum across columns Performance parallel , distributed , loops	1	402	August 18, 2020
Improving the code speed by employing parallelism for asynchronous task Performance	5	470	September 22, 2020
Help speedup a tight triple loop Performance	7	736	June 18, 2020
Performance issue with multithreaded computation with matrix operations at its heart (Threads.@threads vs. BLAS threads) Performance blas , parallel , multithreading , linearalgebra , threads	7	373	November 13, 2023

Having issues speeding up code with multithreading

Related topics