Pipes are ubiquitous in Unix --- but how fast can they go on Linux? In this post we'll iteratively improve a simple pipe-writing benchmark from 3.5GiB/s to 65GiB/s, guided by Linux `perf`.
That’s a reasonable per-core size, and it doesn’t make much sense to add all the cores up if your goal is to fit your data within L2 (like in the article)
deleted by creator
Fantastic article
Awesome article!
Does anyone know how/where in Linux (I assume proc, somewhere) I can find the L# cache sizes?
lscpu -C
Is this a typo or are they running on a Pentium 3?
That’s a reasonable per-core size, and it doesn’t make much sense to add all the cores up if your goal is to fit your data within L2 (like in the article)