Skip to content
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.

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

Use local complete block and local reduction block to identify compact dataflow #10705

Merged
merged 7 commits into from
Mar 23, 2022

Conversation

yzh119
Copy link
Member

@yzh119 yzh119 commented Mar 22, 2022

Per @Hzfengsy 's proposal: https://gist.github.com/Hzfengsy/eab83a98c0b034af1c6c7fac44bae741,
We use the concept of "local" complete block and "local" reduction block to identify whether a subtree has compact dataflow or not.
Compared to the original concept of complete block and reduction block, we only require a block to dominate a given subtree.

src/tir/schedule/analysis/analysis.cc Show resolved Hide resolved
src/tir/schedule/analysis/analysis.cc Outdated Show resolved Hide resolved
src/tir/schedule/analysis/analysis.cc Outdated Show resolved Hide resolved
src/tir/schedule/analysis/analysis.cc Outdated Show resolved Hide resolved
@Hzfengsy Hzfengsy merged commit 0ddaaa6 into apache:main Mar 23, 2022
pfk-beta pushed a commit to pfk-beta/tvm that referenced this pull request Apr 11, 2022
…t dataflow (apache#10705)

* inint

* upd

* upd

* remove redundant print

* upd

* change the reads/writes region for argmin/val

* fix wrong push
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