Skip to content

Make CAReduce more SIMD and memory friendly #1385

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Make CAReduce more SIMD and memory friendly #1385

wants to merge 1 commit into from

Conversation

@ricardoV94
Copy link
Member

@ricardoV94 ricardoV94 commented Apr 30, 2025 •
edited by github-actions bot
Loading

This PR does two major changes:

  1. Adds a branch with intermediate allocators when reducing over a contiguous dimension that is SIMD friendly.
  2. Allocate output buffer aligned with input dimensions, instead of always allocating C-order.

Performance is now comparable or better than numpy

📚 Documentation preview 📚: https://pytensor--1385.org.readthedocs.build/en/1385/
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

1 participant

@ricardoV94