Add blog post for pyfftw-rfft optimization

[NimaSarajpoor]

No description provided.

[netlify]

✅ Deploy Preview for the-data-philomath ready!

Name	Link
🔨 Latest commit	c2e5c38
🔍 Latest deploy log	https://app.netlify.com/projects/the-data-philomath/deploys/693cc7ddac55f70008674b2d
😎 Deploy Preview	https://deploy-preview-11--the-data-philomath.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[seanlaw]

Overall, this was very good! The writing seems good and the layout is nice. I think it shows people how you think and problem solve.

[NimaSarajpoor]

@seanlaw
As suggested, my plan was to add a “Bonus” section to show what didn’t improve pyFFTW’s RFFT performance. The only clear example was using the FFTW_DESTROY_INPUT flag. Since that felt too little for its own section, I added two more isolated experiments. However, I feel it is weird as those two show "some" improvements. So, I feel I need to move them to the main section performance optimization.

What do you think?

[seanlaw]

What do you think?

I think that's fine. I would omit any performance gains that are insignificant

[NimaSarajpoor]

I am planning to perform "bootstrapping" to calculate 95% confidence Interval for the speed-up ratio computed for different input sizes. Might increase the complexity of plot a bit....but I think it helps with getting a more accurate conclusion.

Update: Will ignore it for now.

[NimaSarajpoor]

@seanlaw
I think the post is ready! I am planning to publish it in the nearby future. Would you mind taking a quick look and let me know what you think? :)

[seanlaw]

I will find some time to review

[seanlaw]

@NimaSarajpoor Everything looks reasonable 👍

[NimaSarajpoor]

@seanlaw
Thank you for all the inputs & VALUABLE suggestions! Your support is HIGHLY appreciated!