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

[Adreno][OpenCL] Get rid of extra memory copy #12286

Merged
merged 7 commits into from
Aug 12, 2022

Conversation

echuraev
Copy link
Contributor

@echuraev echuraev commented Aug 3, 2022

  • Added device_copy pass
  • Support textures for all injective ops
  • Avoid extra memory copy

cc: @csullivan, @elvin-n

python/tvm/relay/op/strategy/adreno.py Outdated Show resolved Hide resolved
python/tvm/topi/adreno/utils.py Show resolved Hide resolved
src/relay/transforms/annotate_texture_storage.cc Outdated Show resolved Hide resolved
src/relay/backend/build_module.cc Outdated Show resolved Hide resolved
@TejashShah
Copy link

cc @masahi @csullivan

@masahi masahi merged commit 5deb95a into apache:main Aug 12, 2022
xinetzone pushed a commit to daobook/tvm that referenced this pull request Nov 25, 2022
* Add annotation pass for device_copy where we get buffers but expect

textures

* Fix issues with running device_copy

* Get rid of extra memory copy

* Fix build after cherry-picking

* Fix lint

* Fix CI

* Apply comments

Co-authored-by: Andrey Malyshev <elvin.nnov@gmail.com>
@echuraev echuraev deleted the echuraev/no_extra_copy branch April 14, 2023 10:21
mikeseven pushed a commit to mikeseven/tvm that referenced this pull request Sep 27, 2023
* Add annotation pass for device_copy where we get buffers but expect

textures

* Fix issues with running device_copy

* Get rid of extra memory copy

* Fix build after cherry-picking

* Fix lint

* Fix CI

* Apply comments

Co-authored-by: Andrey Malyshev <elvin.nnov@gmail.com>
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.

4 participants