17 Jun 2026

I’ve been working on speeding up AVX-512 vertex decoding in meshoptimizer recently; in the process I stumbled upon two optimizations that I did not end up using but I thought they might be fun to write about! The optimizations that actually made it in require some higher level background / explanations that will have to wait until another day :)

Both optimizations discussed here touch upon two new (for me) features of AVX-512 that I haven’t had a chance to experiment with until now, and both apply to the same problem: how to decode zigzag encoded integers.

Zigzag encoding

Suppose that you have a lot of signed integers to encode; and these integers come as a result of delta encoding, representing differences between input values.…