Row-major vs column-major traversal and cache performance
Filed under Nvidia
The question
Given two nested loop implementations for summing a 2D array (one row-wise, one column-wise), explain which order is preferred, what cache lines are, and how memory access patterns impact cache performance.
No write-up yet. Related questions below have one.
Related Nvidia questions
Collected from public candidate posts and coding forums. Updated Nov 2026.