NVIDIA / NVIDIA/cuvs

More efficient usage of templates in kernel instantiations

Open
#1,516 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

These are usually the direct cause of heavy binary sizes, and we need to find a way to do smarter template engineering. These can be achieved in the following non-exhaustive ways:

  1. Converting template parameters to runtime parameters
  2. Using a smaller subset of instantiations
  3. Using more specific template types in header-only kernels

A lot of this can come at a tradeoff for performance, so careful evaluation must be done.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named. Start by locating kernel template instantiations and measuring their contribution to binary size, then evaluate the listed runtime-parameter, reduced-instantiation, and more-specific-type approaches. Done means smaller binaries with performance tradeoffs measured and documented.

Written by the indexing model from the issue text.

Assessment

Domain
performance
Issue type
Refactor
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.