This is a short post that explains how to write a high-performance matrix multiplication program on modern processors. In this tutorial I will use a single core of the Skylake-client CPU with AVX2, but the principles in this post also apply to other processors with different instruction sets (such as AVX512).
Matrix multiplication is a mathematical operation that defines the product of
| This text is taken from LinkedIn, where it was a response to this article by Bret Reckard at | |
| Sequoia. Bret's article is reasonably well written and contains decent advice if you're a software | |
| engineer looking to jump into a startup and become a VP of Engineering. Go check this one out, | |
| it's short and worth a read: | |
| https://www.linkedin.com/pulse/accelerate-your-path-vpe-join-series-startup-bret-reckard/ | |
| And now this is my response, which was originally a LinkedIn post plus a number of comments. I'm | |
| reconstructing it here 'cause it's a lot easier to read without trying to guess which order I | |
| originally posted things in. |