Skip to content

Conversation

@ClementPinard
Copy link
Contributor

@ClementPinard ClementPinard commented Apr 17, 2019

This PR proposes to use packed accessors in order to index multidimensional tensors inside a kernel function.

I am not particularly happy with how verbose the function parameters became, but at least it's comprehensive !

See the corresponding PR in tutorials here

provides a way to index tensors inside cuda kernels
@soumith soumith merged commit 85bc391 into pytorch:master Apr 17, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants