NVIDIA / MatX

An efficient C++17 GPU numerical computing library with Python-like syntax

Home Page:https://nvidia.github.io/MatX

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[FEA] Remove `transpose`

cliffburdick opened this issue · comments

transpose is really the same as permute, except it runs an optimized kernel. This should be an implementation detail and not something exposed to the user.

Closing this since it somewhat makes sense to have a transpose transform if the user intends to swap all dimensions