# Any benchmark comparing Julia on Windows vs Linux vs OSX?

**URL:** <https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394>\
**Category:** Performance\
**Created:** [December 6, 2018, 8:18pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394 "2018-12-06T20:18:45Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![Juan](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/juan/32/7657_2.png) [@Juan](https://discourse.julialang.org/u/Juan)\
**Post date:** [December 6, 2018, 8:18pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394/1 "2018-12-06T20:18:45Z")

</div>

Is there any benchmark comparing the speed and memory usage of Julia on different Operating Systems?

---

<div class="post-metadata">

**Author:** ![kristoffer.carlsson](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/kristoffer.carlsson/32/22_2.png) [@kristoffer.carlsson](https://discourse.julialang.org/u/kristoffer.carlsson)\
**Post date:** [December 6, 2018, 8:32pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394/2 "2018-12-06T20:32:55Z")

</div>

They should be pretty much the same, except for some things that deals directly with the OS, like files. What’s the reason for the question?

---

<div class="post-metadata">

**Author:** ![Seif\_Shebl](https://avatars.discourse-cdn.com/v4/letter/s/eada6e/32.png) [@Seif\_Shebl](https://discourse.julialang.org/u/Seif_Shebl)\
**Post date:** [December 6, 2018, 8:39pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394/3 "2018-12-06T20:39:03Z")

</div>

From my own experience, Julia is a bit faster in Linux (Mint) than in Windows (10) regardless of what the code does, I didn’t try OSX though.

---

<div class="post-metadata">

**Author:** ![PetrKryslUCSD](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/petrkryslucsd/32/215825_2.png) [@PetrKryslUCSD](https://discourse.julialang.org/u/PetrKryslUCSD)\
**Post date:** [December 6, 2018, 8:42pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394/4 "2018-12-06T20:42:55Z")

</div>

Perhaps multithreading?

---

<div class="post-metadata">

**Author:** ![Seif\_Shebl](https://avatars.discourse-cdn.com/v4/letter/s/eada6e/32.png) [@Seif\_Shebl](https://discourse.julialang.org/u/Seif_Shebl)\
**Post date:** [December 6, 2018, 8:49pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394/5 "2018-12-06T20:49:42Z")

</div>

I don’t think so, may be it’s that Linux is more programmers friendly as they say. Also, the difference is around 25 to 30%, so definitely not multi-threading. Furthermore, I use other languages (e.g. Fortran, C) and observe a similar difference.

---

<div class="post-metadata">

**Author:** ![Juan](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/juan/32/7657_2.png) [@Juan](https://discourse.julialang.org/u/Juan)\
**Post date:** [December 6, 2018, 11:32pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394/6 "2018-12-06T23:32:43Z")

</div>

I like benchmarks and it can help to choose between operating systems.

---

<div class="post-metadata">

**Author:** ![mcbro](https://avatars.discourse-cdn.com/v4/letter/m/77aa72/32.png) [@mcbro](https://discourse.julialang.org/u/mcbro)\
**Post date:** [June 29, 2021, 8:54pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394/7 "2021-06-29T20:54:30Z")

</div>

What I’ve seen for large simulations taking a day or so to finish on my linux machine, that it simply slows to a crawl and basically stops on windows 10. This is even with setting the process priority for julia to real time.

It is a significant issue for running long simulations on windows 10. It’s difficult to provide a test case because of the complexity involved, and of course my code is proprietary.

Has anyone else seen this?

---

<div class="post-metadata">

**Author:** ![PetrKryslUCSD](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/petrkryslucsd/32/215825_2.png) [@PetrKryslUCSD](https://discourse.julialang.org/u/PetrKryslUCSD)\
**Post date:** [June 29, 2021, 8:55pm UTC](https://discourse.julialang.org/t/any-benchmark-comparing-julia-on-windows-vs-linux-vs-osx/18394/8 "2021-06-29T20:55:24Z")

</div>

> [@Comparison of Windows 10 and Linux Julia](https://discourse.julialang.org/t/comparison-of-windows-10-and-linux-julia/41227):
>
> I was curious about some recent observations I made concerning the speed of sparse-matrix solve. Here are some measurements comparing Windows 10, WSL2, and Ubuntu 20.4, all running on the same laptop(HP Spectre 360 i7 at 3.1 GHz, 16 GB of memory). Serial execution with default number of threads. Assembly of the left-hand side matrix and the right hand side vector [(source).](https://github.com/PetrKryslUCSD/Elfel.jl/blob/master/examples/heat/heat_poisson_q4_alt_wgradN.jl). 4.2 million degrees of freedom. [image] Solution of 4.2 million coupled linear algebraic equations. Default sparse matr…