Software Development

Tilegym CuTile Autotuning

Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.

Publisher / source

NVIDIA Skills (Verified)

Upstream record

NVIDIA/skills

Version

Version 2

Published

2026-06-21

Publication review

Approved for publication

Content fingerprint

f6ec77fb83a032497735ef41c90a370d7c9261d6ee413c590f289caf805de8af