# Computer specific slowdown on multi-threading on computer cluster (Linux)?

**URL:** <https://discourse.julialang.org/t/computer-specific-slowdown-on-multi-threading-on-computer-cluster-linux/57889>\
**Category:** Performance\
**Tags:** installation\
**Created:** [March 24, 2021, 7:32pm UTC](https://discourse.julialang.org/t/computer-specific-slowdown-on-multi-threading-on-computer-cluster-linux/57889 "2021-03-24T19:32:07Z")\
**Posts on this page:** 1\
**Showing post:** 28

<div class="post-metadata">

**Author:** ![PhilippA](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/philippa/32/21676_2.png) [@PhilippA](https://discourse.julialang.org/u/PhilippA)\
**Post date:** [November 11, 2021, 1:44pm UTC](https://discourse.julialang.org/t/computer-specific-slowdown-on-multi-threading-on-computer-cluster-linux/57889/28 "2021-11-11T13:44:41Z")

</div>

I had the same problem. In my case, [this discussion](https://discourse.julialang.org/t/what-is-the-difference-between-threads-spawn-and-distributed-spawnnat/35560) clarified the issue.  
I use workers (via Distributed) for the more expensive functions now. The less expensive functions are handled by threading via ThreadsX.map() from the package ThreadsX.jl.

---

_[View the full topic](https://discourse.julialang.org/t/computer-specific-slowdown-on-multi-threading-on-computer-cluster-linux/57889)._