# Repeated Convolutions With Large 1D Arrays

**URL:** https://discourse.julialang.org/t/repeated-convolutions-with-large-1d-arrays/127194
**Category:** Performance
**Tags:** question, dsp, fft
**Created:** [March 20, 2025, 7:33pm UTC](https://discourse.julialang.org/t/repeated-convolutions-with-large-1d-arrays/127194 "2025-03-20T19:33:57Z")
**Posts on this page:** 1
**Page:** 2

<div class="post-metadata">

### Author: ![donkeysaddle](https://avatars.discourse-cdn.com/v4/letter/d/3e96dc/32.png) [@donkeysaddle](https://discourse.julialang.org/u/donkeysaddle)
#### Post date: [April 14, 2025, 7:45pm UTC](https://discourse.julialang.org/t/repeated-convolutions-with-large-1d-arrays/127194/22 "2025-04-14T19:45:45Z")

</div>

@Dan This is really cool! Thanks. @GunnarFarneback thank you as well. Still need to look into the IIR approach! Are there specific packages you would recommend?

I’ve been playing around with the method @Dan recommended and I’ve found it to be quite fast. I created an example slightly different to the one above where you can stay in the FFT space for the entirety of the loop and it’s essentially just as fast.

Anyways, thanks again.

[Previous page](https://discourse.julialang.org/t/repeated-convolutions-with-large-1d-arrays/127194.md?page=1)