NVIDIA / NVIDIA/cuda-tile

Feature request: make_im2col_view

Open
#22 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
C++
Stars
1k
Forks
89
PR merge metrics
No merged PRs in 30d

Description

Convolution workloads would greatly benefit from the im2col TMA descriptor. Or are there plans to make tileiras detect it from scatter-gather views?

Contributor guide

No contributing guide indexed for this repository

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

Start by locating the existing TMA descriptor handling and the code for scatter-gather views in the CUDA Tile IR and compiler infrastructure. Determine whether make_im2col_view should create an im2col TMA descriptor or enable detection from scatter-gather views. Done means the intended behavior and scope are defined, with suitable validation for convolution workloads.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
compilers
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.