ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
Itamar Turner-Trauring sped up scikit-learn's gradient histogram boosting binary search 6x by reducing branch mispredictions. The original code used unpredictable branches. The optimized version iterates a fixed number of times and uses Rust's select_unpredictable to avoid branches, achieving mechanical sympathy with the CPU.
Tap to vote and see what everyone thinks.
Summary by ByteBrief