A loop or data layout:
[describe]. How does it
interact with cache lines and
prefetching, why does the
access pattern cost what it
does, and how to fix it?

Why Cache Makes This Slow

The memory hierarchy explanation behind an unexplained slowdown.

Prompt

Here's a loop or data layout: [describe it]. Explain how it interacts with cache lines and prefetching, why the access pattern costs what it costs, and rewrite it to be cache-friendly without changing what it computes.