numpy / numpy/numpy

ENH: refactor our loop implementations into a stand-alone library

Open
#17,698 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

01 - Enhancement 23 - Wish List component: numpy.ufunc component: SIMD
Dominant language
Python
Stars
32.8k
Forks
12.8k
Avg merge
1d 7h
Merged PRs (30d)
197

Description

We are slowly getting to a best-of-breed set of CPU inner loop functions using Unversal Intrinsics. It would be helpful to other projects if we could refactor these into a stand-alone C/C++ library, so they could be re-used in the growing number of NumPy-like libraries.

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

Review NumPy’s existing CPU inner-loop implementations and their Universal Intrinsics usage first. Define the scope and interface of a standalone C/C++ library that other NumPy-like projects could reuse; done means the refactoring and reuse boundary are agreed and implemented.

Written by the indexing model from the issue text.

Assessment

Tech stack
c, cpp
Domain
performance
Issue type
Refactor
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.